system

Abstract

Provide a system. A means for receiving sound source data; means for analyzing the received sound source data and extracting musical features; means for generating a musical staff based on the extracted musical features; The system includes means for converting the generated musical staff into a number of different notation formats.

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional methods for analyzing audio sources and music and generating musical notation require a lot of manual work, making them inefficient. Furthermore, the conversion from staff notation to other notation formats is often done manually, a process that requires a great deal of time and effort. Furthermore, this process can be very complicated for users without specialized musical knowledge. Therefore, there is a need for a system that can automatically convert audio data into staff notation and then automatically convert that staff notation into various notation formats. [Means for solving the problem]

[0005] The system according to the present invention includes a means for receiving audio data, a means for analyzing the received audio data to extract musical features, a means for generating staff notation based on the extracted musical features, and a means for converting the generated staff notation into a plurality of different notation formats. This enables automatic conversion from audio data to staff notation and from the staff notation into a variety of notation formats (e.g., string notation, bunka notation, tablature, chord notation). This allows even users without specialized musical knowledge to efficiently and easily convert audio data into a variety of notation formats.

[0006] "Audio data" refers to sound information recorded in digital format, such as music files and audio recordings.

[0007] "Means for receiving" refers to an interface or protocol for acquiring sound source data from outside, or a device or software that realizes that function.

[0008] "Means for analyzing" refers to the algorithms or programs used to extract musical characteristics from the received audio data.

[0009] "Musical features" refer to musical elements such as pitch, rhythm, tempo, and frequency spectrum extracted from audio source data.

[0010] "Staff notation" refers to a musical notation format that visually represents music by arranging notes and symbols on five lines.

[0011] "Means for generating" refers to a program or function for creating musical notation based on the extracted musical features.

[0012] "Multiple different notation formats" refers to a variety of musical notation formats generated based on staff notation, such as string notation, cultural notation, tablature, and chord notation.

[0013] "Means for converting" refers to an algorithm or program for converting the generated staff notation into another notation format. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The system of this invention automates the process of receiving and analyzing audio data, generating musical notation based on its musical characteristics, and then converting the notation into multiple different notation formats. This system is primarily composed of three entities: a server, a terminal, and a user.

[0036] overview

[0037] A specific embodiment of the present invention will be described below. This system can be used in a variety of fields, including music education, music score production, and music analysis.

[0038] Receiving audio data

[0039] The user selects audio data (MP3, WAV, etc.) using their own device. This audio data is selected from the device's file system and uploaded to the server via the Internet. The server receives and stores this audio data, and then proceeds to the next analysis process.

[0040] Analysis of sound source data

[0041] To analyze the audio data inside the server, algorithms are used to extract musical features. Specific libraries include LibROSA and pydub. These libraries are used to extract musical features such as frequency, pitch, rhythm, and tempo from the audio data. These feature data are temporarily stored in memory or a database.

[0042] Staff generation

[0043] Based on the extracted musical feature data, the server generates a musical staff. In this process, pitch and rhythm information is arranged as staff data in a visually easy-to-understand format. Standard formats such as ABC notation or MusicXML format are commonly used. The generated musical staff is then sent to the terminal as an image file (e.g., PNG or SVG).

[0044] Selecting the music format

[0045] The user checks the staff notation displayed on the terminal and selects the desired notation format (string notation, bunka notation, tablature, chord notation). The selection information is sent from the terminal to the server.

[0046] Conversion to music notation format

[0047] Based on the selection information received from the user, the server converts the staff notation into other notation formats using corresponding algorithms, for example, conversion to tablature applies logic that maps pitch information to guitar frets and strings.

[0048] Providing converted scores

[0049] The converted music score is then sent to the device as an image file, where the user can view the converted music score on the device and download it if necessary.

[0050] Specific examples

[0051] For example, a user uploads an MP3 file recording of a piano performance to a server. The server analyzes the audio data and extracts that it is in the key of C major and in 4 / 4 time. Next, a musical staff is generated based on this information and sent to the device. The user confirms this and chooses to convert it to tablature. This information is sent to the server, and the musical staff is converted into tablature and sent to the device. The user can finally download this tablature and use it to play the instrument.

[0052] As described above, the system of the present invention efficiently and automatically converts sound source data into a variety of musical score formats.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user selects the audio data (MP3, WAV, etc.) on the device. The user selects the audio file using the file selection dialog and presses the upload button.

[0056] Step 2:

[0057] The device uploads the selected audio data to the server. The audio file selected by the user is sent to the server via an HTTP request. The server receives it and stores it in a database or temporary storage.

[0058] Step 3:

[0059] The server reads the received audio data and begins analysis to extract musical characteristics. Specifically, the server uses music analysis libraries such as LibROSA and pydub to obtain data such as frequency, pitch, rhythm, and tempo.

[0060] Step 4:

[0061] The server generates a staff notation based on the extracted musical feature data. In this process, ABC notation or MusicXML format is used to visually arrange the scale and rhythm information as staff notation data. The generated staff notation data is temporarily saved in an internal format (such as JSON or XML).

[0062] Step 5:

[0063] The server converts the generated music sheet into an image file (such as PNG or SVG), which is then sent to the device as an HTTP response.

[0064] Step 6:

[0065] The terminal displays the image of the musical staff received from the server on the screen, and provides a user interface for the user to check the musical staff and select the desired musical notation format (string notation, Bunka notation, TAB notation, chord notation).

[0066] Step 7:

[0067] The user selects the desired music score format and sends the selected information to the server by pressing the send button on the terminal.

[0068] Step 8:

[0069] The terminal sends the user's selection information to the server. The information on the selected musical score format is sent to the server as an HTTP request.

[0070] Step 9:

[0071] The server converts the staff notation into a different notation format based on the selection information received from the user. In this process, the corresponding algorithm (e.g., staff notation to tablature conversion logic) is applied.

[0072] Step 10:

[0073] The server generates the converted score as an image file again, and sends the converted score image file to the terminal as an HTTP response.

[0074] Step 11:

[0075] The terminal displays the converted music score image received from the server on the screen, and the user is given the option to check it and download the image if necessary.

[0076] Step 12:

[0077] Users can download the converted music sheet images and use them for their own purposes.

[0078] Example 1

[0079] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0080] Conventional music data analysis and score generation systems do not automate the entire process, from analyzing audio data to converting it into multiple notation formats, and require the use of multiple software programs in combination. This forces users to perform complex operations, hindering efficient workflow. Furthermore, the accuracy of conversion between different notation formats is low, making it difficult to accurately reproduce musical nuances.

[0081] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0082] In this invention, the server includes means for receiving audio data, means for analyzing the received audio data and extracting musical features, means for generating staff notation based on the extracted musical features, means for converting the generated staff notation into a plurality of different musical notation formats, means for a user to use a terminal to select audio data and upload it to the server via the Internet, means for the server to save the audio data and extract musical features using a library, means for the server to generate staff notation based on the extracted musical features and send it to the terminal as an image file, means for a user to check the staff notation on the terminal and select a desired musical notation format, means for the server to receive the selection information and convert the staff notation into a different musical notation format, and means for sending the converted musical notation to the terminal as an image file. This makes it possible to centrally and automatically perform the entire process from receiving audio data to analyzing it, generating staff notation, converting it into a different musical notation format, and providing it to the terminal.

[0083] "Sound source data" refers to data that records music or audio information in digital or analog format.

[0084] The "receiving means" is a device or module for receiving sound source data from the outside.

[0085] "Analyzing means" refers to devices or software that perform processing to extract musical characteristics from sound source data.

[0086] "Musical features" are elements such as frequency, pitch, rhythm, and tempo contained in the sound source data.

[0087] "Extraction means" refers to devices or software that identify musical characteristics from sound source data and extract them as data.

[0088] "Staff notation" is a form of notation that visually represents musical features.

[0089] A "generating means" is a device or software for constructing a musical staff based on musical characteristics.

[0090] "Music formats" are different notation formats for musical instrument performance, including staff notation, tablature, cultural notation, string notation, chord notation, etc.

[0091] A "converting means" is a device or software that converts the original staff notation into another notation format.

[0092] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0093] A "library" is a collection of existing programming tools and algorithms used for analysis and transformation.

[0094] A "user" is someone who uses this system to upload audio data and obtain the converted sheet music.

[0095] The "server" is a central control device that analyzes received sound source data, generates musical staves, and performs conversion processing.

[0096] MODE FOR CARRYING OUT THE INVENTION

[0097] The system of this invention automates the process of receiving and analyzing audio data, generating musical notation based on its musical characteristics, and then converting the notation into multiple different notation formats. This system is primarily composed of three entities: a server, a terminal, and a user.

[0098] Receiving audio data

[0099] The user selects audio data (MP3, WAV, etc.) using their own device. This is done by selecting an audio file from the device's file system. The selected audio data is then uploaded from the device to a server via the Internet, using a communication protocol such as an HTTP POST request. The server receives the audio data and saves it in a specified directory on the server.

[0100] Analysis of sound source data

[0101] The server analyzes the received audio data. This analysis uses libraries such as LibROSA and pydub to extract musical features. Specifically, the server loads the audio data into memory and uses LibROSA to extract musical features such as frequency, pitch, rhythm, and tempo. The extracted feature data is temporarily stored in the server's memory or database.

[0102] Staff generation

[0103] The server generates a musical staff based on the extracted musical feature data. In this process, the staff data is constructed using a standard format such as ABC notation or MusicXML format. The generated staff is exported to a visually easy-to-understand format and sent to the terminal as an image file (such as PNG or SVG).

[0104] Selecting the music format

[0105] The user checks the staff notation displayed on the terminal and selects the desired notation format (string notation, bunka notation, tablature, chord notation). The selected information is sent from the terminal to the server via an HTTP request.

[0106] Conversion to music notation format

[0107] The server converts the staff notation into other notation formats based on the user's selections (for example, tablature, which uses an algorithm to map pitch information to guitar frets and strings), and the converted notation is again generated as an image file.

[0108] Providing converted scores

[0109] The server sends the converted music score image file to the terminal, where the user can check the converted music score on the terminal and download it as needed.

[0110] Specific examples

[0111] For example, a user uploads an MP3 file recording a piano performance to a server. The server analyzes the audio data and determines that it is in the key of C major and in 4 / 4 time. Next, a musical staff is generated based on this information and sent to the device. The user confirms this and chooses to convert it to tablature. This information is sent to the server, and the musical staff is converted to tablature and sent to the device. The user can then download the tablature and use it to play their instrument.

[0112] Prompt Sentence Examples

[0113] The user uploads an MP3 file of their piano performance to the server, which analyzes the audio data to generate a 4 / 4 staff in the key of C major and converts it into tablature format.

[0114] As described above, the system of the present invention can centrally and automatically perform all processes from receiving sound source data to analyzing it, generating staff notation, and converting it into different musical notation formats and providing it.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1: Select and upload audio data

[0117] Input: The user selects audio data (MP3, WAV, etc.) using their own device (computer, smartphone, etc.).

[0118] Specific operation: The user opens a file selection dialog on the device and selects an audio file.

[0119] Output: The selected audio data is stored in the specified file path on the device.

[0120] Next process: The audio data is uploaded to the server.

[0121] Step 2: Upload the audio data

[0122] Input: User selected audio data.

[0123] What happens: The user clicks the upload button in their browser or application.

[0124] Output: The audio data is sent to the server via an HTTP POST request.

[0125] Next process: The server receives and stores the audio data.

[0126] Step 3: Receiving and saving audio data

[0127] Input: Audio data uploaded by users to the server.

[0128] Specific operation: The server receives an HTTP request and saves the audio data in a specific directory.

[0129] Output: Audio data stored in the file system.

[0130] Next process: The server prepares to analyze the sound source data.

[0131] Step 4: Loading the sound source data

[0132] Input: Audio data stored in the server's file system.

[0133] Specific operation: The server uses libraries such as LibROSA and pydub to load the audio data into memory.

[0134] Output: Sound source data loaded into memory.

[0135] Next process: Analyze the sound source data.

[0136] Step 5: Analyzing the sound source data

[0137] Input: Sound source data loaded into memory.

[0138] Specific operation: The server uses LibROSA to extract musical features such as frequency, pitch, rhythm, and tempo.

[0139] Output: Extracted musical feature data.

[0140] Next process: Save musical feature data and prepare for staff generation.

[0141] Step 6: Saving musical feature data

[0142] Input: Extracted musical feature data.

[0143] Specific operation: The server temporarily stores the feature data in memory or a database.

[0144] Output: Saved musical feature data.

[0145] Next step: Start the staff generation process.

[0146] Step 7: Generate the staff notation

[0147] Input: Stored musical feature data.

[0148] Specific operation: The server constructs staff data based on the musical feature data using a standard format such as ABC notation or MusicXML format.

[0149] Output: The generated musical staff.

[0150] Next process: Export the generated staff as an image file and send it to the user's device.

[0151] Step 8: Send and review the score

[0152] Input: The generated musical staff.

[0153] Specific operation: The server converts the generated staff into an image file in PNG or SVG format and sends it to the user's device as an HTTP response. The user then checks the staff on their device.

[0154] Output: A staff image displayed on the user's device.

[0155] Next process: The user selects the desired musical score format.

[0156] Step 9: Select the desired music format

[0157] Input: The staff displayed by the user.

[0158] Specific operation: The user selects the desired music notation format (e.g., tablature, bunka notation, string notation, chord notation) on the terminal using a pull-down menu or radio buttons.

[0159] Output: Selected music notation format information.

[0160] Next process: The selection information is sent from the terminal to the server.

[0161] Step 10: Converting the music format

[0162] Input: Selection information of musical score format received by the server.

[0163] What it does: The server uses the corresponding algorithm to convert the musical staff into the format of your choice, for example, to tablature, mapping pitch information to guitar frets and strings.

[0164] Output: The converted score.

[0165] Next process: Send the converted score to the user's terminal.

[0166] Step 11: Providing the converted score

[0167] Input: The converted score.

[0168] Specific operation: The server converts the converted score into an image file in PNG or SVG format and sends it to the user's device as an HTTP response. The user can check the converted score on their device and download it if necessary.

[0169] Output: The converted music score image displayed on the user's device.

[0170] Next process: The user downloads and uses the converted musical score.

[0171] (Application example 1)

[0172] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0173] In recent years, there has been a growing need in music education and music notation production to quickly and accurately convert audio files into sheet music. Furthermore, while it is necessary to provide different notation formats for different instruments and purposes, the reality is that this conversion process takes a great deal of time and effort. Furthermore, there is a need for on-site visual confirmation of sheet music and real-time conversion into different notation formats, but current systems face challenges that make this difficult.

[0174] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0175] In this invention, the server includes means for receiving audio data, means for analyzing the audio data and extracting musical features, means for generating musical notation based on the extracted musical features, means for converting the generated musical notation into a plurality of different musical notation formats, means for displaying the generated musical notation on a visual device in real time, and means for allowing a user to select a desired musical notation format and for instantly converting and displaying the musical notation into a different musical notation format based on the user's selection. This automates the generation of musical notation from audio data and the conversion into different musical notation formats, making it possible to check and operate the musical notation in real time through the visual device.

[0176] "Audio data" refers to information that records music or sound in digital or analog format.

[0177] "Musical features" are musical components such as frequency, pitch, rhythm, and tempo extracted from sound source data.

[0178] A musical staff is a sheet of music consisting of five lines used to write musical melodies and chords.

[0179] "Music format" refers to different notation methods for writing musical scores, such as staff notation, tablature, and cultural notation.

[0180] A "visual device" is a device that allows users to visually confirm information, and specifically includes smart glasses and head-mounted displays.

[0181] "Real-time display" is a function that displays the results of data processing immediately after it is performed.

[0182] The "selection means" is a means by which a user selects a desired option from multiple options.

[0183] "Instant conversion" refers to the rapid conversion of data formats based on user instructions or selections, without delay.

[0184] A specific embodiment of the present invention will be described below. The system has the functions of receiving and analyzing audio source data, generating musical staves, instantly converting them into different musical notation formats, and displaying them on a visual device in real time.

[0185] Receiving audio data

[0186] The user selects audio data (MP3, WAV, etc.) using their own device. The audio data is selected from the device's file system and uploaded to the server via the Internet. The server receives and stores this audio data and proceeds to the next analysis process.

[0187] Analysis of sound source data

[0188] To analyze the audio data inside the server, algorithms are used to extract musical features. Specific libraries include LibROSA and pydub. These libraries are used to extract musical features such as frequency, pitch, rhythm, and tempo from the audio data. These feature data are temporarily stored in memory or a database.

[0189] Staff generation

[0190] The server generates a staff based on the extracted musical feature data. In this process, pitch and rhythm information is arranged as staff data in a visually easy-to-understand format. Standard formats such as ABC notation or MusicXML are commonly used. The generated staff is then sent to the terminal as an image file (e.g., PNG or SVG).

[0191] Selecting and converting music notation formats

[0192] The user checks the staff notation displayed on the device and selects the desired notation format (e.g., tablature). The selection information is sent from the device to the server. The server converts the staff notation into another notation format based on the selection information received from the user. This process uses corresponding algorithms. For example, conversion to tablature applies logic that maps pitch information to guitar frets and strings.

[0193] Real-time display of generated music scores

[0194] The generated score is displayed in real time on a visual device (e.g., smart glasses or a head-mounted display), allowing the user to check the score and continue playing as needed.

[0195] Specific examples

[0196] For example, a user uploads audio data of a performance on an electronic piano. The audio data is analyzed by the server and determined to be in the key of C major and in 4 / 4 time. A staff notation is then generated based on this information and displayed on the user's visual device. If the user selects conversion to tablature, the information is sent to the server, and the staff notation is converted to tablature and displayed instantly on the visual device. The user can then continue playing the instrument using the tablature.

[0197] Prompt Sentence Examples

[0198] "Please receive audio played on an electronic piano via the Internet, analyze it in real time, and display it as musical notation. Furthermore, please create a system that can convert and display the music notation on the spot when the user selects a desired notation format (e.g., tablature)."

[0199] In this way, the system of the present invention efficiently and automatically converts audio data into various musical score formats, and realizes real-time display through a visual device.

[0200] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0201] Step 1: Receiving audio data

[0202] A user selects audio data (MP3, WAV, etc.) using their own device. The selected audio data is uploaded to a server via the Internet. The server receives and stores this audio data. The input is the audio data file, and the output is the audio data stored on the server.

[0203] Step 2: Analyzing the sound source data

[0204] The server analyzes the received audio data. Using libraries such as LibROSA or pydub, it extracts musical features such as frequency, pitch, rhythm, and tempo from the audio data. The extracted feature data is temporarily stored in memory or a database. The input is the audio data, and the output is musical feature data.

[0205] Step 3: Generate the staff notation

[0206] The server generates a staff notation based on the analyzed musical feature data. Using a library such as Music21, pitch and rhythm information is arranged as staff notation data in a visually easy-to-understand format. The generated staff notation data is output as an image file (such as PNG or SVG). The input is musical feature data, and the output is an image file of the staff notation.

[0207] Step 4: Select the music format

[0208] The user checks the staff displayed on the terminal and selects the desired music notation format. This selection information is sent from the user to the server via the terminal. The input is the staff image file and the user's selection information, and the output is the selection information sent to the server.

[0209] Step 5: Converting to music notation format

[0210] The server converts the staff notation into other notation formats based on the selections received from the user. For conversion to tablature and other notation formats, logic is applied to map the pitch information to the appropriate instrument frets and strings. The input is an image file of the staff notation and the selections, and the output is an image file of the different notation formats.

[0211] Step 6: Real-time display

[0212] The server displays the generated musical score in real time on a visual device (such as smart glasses or a head-mounted display). The user can check the score through this device and continue playing if necessary. The input is image files in different musical score formats, and the output is the musical score displayed on the visual device.

[0213] This allows users to generate sheet music from audio data, convert it into the desired notation format, and check it in real time. Through the specific operations and data flow, users can clearly understand how the entire system works.

[0214] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0215] This invention combines a system that analyzes audio data to generate musical notation and converts the notation into multiple different musical notation formats with an emotion engine that recognizes the user's emotions. This system can provide musical notation that reflects the user's emotions in music education, music notation production, and music analysis.

[0216] overview

[0217] A specific embodiment of the present invention will be described below. This system is configured by adding an emotion engine to three main entities: a server, a terminal, and a user.

[0218] Receiving and analyzing sound source data

[0219] The user selects audio data (MP3, WAV, etc.) using a device. This audio data is selected on the device and uploaded to a server via the Internet. Once the server receives the audio data, it begins processing to analyze its musical features. This analysis uses libraries such as LibROSA and pydub to extract musical features such as frequency, pitch, rhythm, and tempo.

[0220] Staff generation

[0221] The server generates a musical staff based on the extracted musical feature data. It uses ABC notation or MusicXML format to visually arrange pitch and rhythm information. The generated musical staff is sent to the device as an image file.

[0222] Recognizing user emotions with an emotion engine

[0223] The device recognizes the user's emotions using an emotion engine. This emotion engine includes algorithms that analyze emotions from the user's voice, facial expressions, input content, etc. For example, it can recognize emotions such as joy, sadness, and surprise by analyzing the user's facial expressions and tone of voice through a camera or microphone.

[0224] Adjusting staff notation and music notation format according to emotions

[0225] The server receives the recognized user emotion information and adjusts the generated staff notation or any other notation format (string notation, music notation, tablature, chord notation), including changing the pitch and tempo, for example, if the user expresses sadness, slow down the tempo and change to a lower pitch.

[0226] Conversion and final output

[0227] The user selects the desired music notation format, and the server converts the staff notation into another music notation format based on the user's selection and the recognized emotion information. The converted music notation is then sent to the terminal as an image file, where the user can view it and download it if necessary.

[0228] Specific examples

[0229] For example, a user uploads an MP3 file recording a piano performance to the server. The server analyzes this audio data and extracts that it is in the key of C major and in 4 / 4 time. The generated staff is then sent to the device. The user reviews this staff, and the emotion engine recognizes the user's emotion (e.g., joy). Based on this emotion, the staff is adjusted to increase the tempo and pitch. The user then selects conversion to TAB notation, and this information is sent to the server, and the converted TAB is sent to the device. Finally, the user can download this TAB and use it to play an instrument.

[0230] As described above, the system of the present invention efficiently and automatically converts sound source data into a variety of musical score formats that take emotion into consideration.

[0231] The processing flow will be explained below.

[0232] Step 1:

[0233] The user selects the audio data (MP3, WAV, etc.) on the device. The user selects the audio file using the file selection dialog and presses the upload button.

[0234] Step 2:

[0235] The device uploads the selected audio data to the server. The audio file selected by the user is sent to the server via an HTTP request. The server receives it and stores it in a database or temporary storage.

[0236] Step 3:

[0237] The server reads the received audio data and begins analysis to extract musical characteristics. Specifically, the server uses music analysis libraries such as LibROSA and pydub to obtain data such as frequency, pitch, rhythm, and tempo.

[0238] Step 4:

[0239] The server generates a staff notation based on the extracted musical feature data. In this process, ABC notation or MusicXML format is used to visually arrange the scale and rhythm information as staff notation data. The generated staff notation data is temporarily stored in memory or a database.

[0240] Step 5:

[0241] The server converts the generated music sheet into an image file (such as PNG or SVG), which is then sent to the device as an HTTP response.

[0242] Step 6:

[0243] The device displays the image of the musical staff received from the server on the screen. The user confirms it, and the emotion engine begins preparations to recognize the user's emotions.

[0244] Step 7:

[0245] To recognize the user's emotions, the device uses a camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes this data and recognizes the user's emotions.

[0246] Step 8:

[0247] The device sends the recognized emotion information to the server, which is then sent as an HTTP request.

[0248] Step 9:

[0249] The server receives the emotion information and makes adjustments to the generated musical staff or other notation format, for example, lowering the pitch and slowing the tempo if sadness is recognized.

[0250] Step 10:

[0251] The user selects the desired music notation format, and the selected information and adjusted staff data are sent to the server.

[0252] Step 11:

[0253] Based on the selected notation format, the server converts the adjusted staff notation into other different notation formats (string notation, bunka notation, tablature, chord notation), using corresponding algorithms in this process.

[0254] Step 12:

[0255] The server generates the converted music score as an image file and sends it to the terminal as an HTTP response.

[0256] Step 13:

[0257] The terminal displays the converted music score image received from the server on the screen, and provides the user with the option to check it and download the image if necessary.

[0258] Step 14:

[0259] Users can download the converted music sheet images and use them for their own purposes.

[0260] Example 2

[0261] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0262] While existing audio data analysis systems can extract musical features and generate musical scores, they lack the ability to adjust the scores to reflect the user's emotions, making it difficult to improve the emotional expressiveness of the scores and the satisfaction of the score users. For this reason, there is a demand for systems with more advanced functions that reflect the user's emotions in the fields of music education, sheet music production, and music analysis.

[0263] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0264] In this invention, the server includes means for receiving sound source data, means for analyzing the received sound source data and extracting musical features, means for generating a staff based on the extracted musical features, means for adjusting the staff generated by the staff generating means based on user emotion information, means for converting the adjusted staff into a plurality of different music notation formats, and means for transmitting the output from the means for converting into a plurality of different music notation formats to a user terminal. This makes it possible to reflect the user's emotions in the musical score generated from the sound source data and provide more expressive music notation.

[0265] "Audio data" refers to music or audio data recorded in digital or analog format.

[0266] "Means for receiving" refers to a mechanism, method, or technology for capturing audio source data into a particular location or system.

[0267] "Means for analyzing and extracting musical features" refers to methods and techniques for identifying and extracting specific musical elements such as frequency, pitch, rhythm, and tempo from audio source data.

[0268] "Means for generating musical staff notation" refers to a method or technology for converting extracted musical features into a musical staff notation format to visually represent the musical pitch, rhythm, and tempo.

[0269] "Emotional information" refers to data on the user's emotional state analyzed from their voice, facial expressions, input, etc.

[0270] "Adjustment means" refers to techniques or methods for changing the pitch, tempo, rhythm, etc. of an existing musical staff based on recognized emotional information.

[0271] "Means for converting into multiple different notation formats" refers to techniques and methods for converting staff notation format data into other formats (e.g., string notation, bunka notation, tablature, chord notation).

[0272] "Transmission means" refers to the method or technology for transferring the generated or converted music score data to the user's terminal.

[0273] "Terminal" means a computer system or device operated by a user to select and upload audio data or to receive final score data.

[0274] This invention combines a system that analyzes audio data to generate musical notation and converts the musical notation into multiple different notation formats with an emotion engine that recognizes the user's emotions. This system can provide musical notation that reflects the user's emotions in music education, music notation production, and music analysis.

[0275] The system's components mainly include a server, a terminal, a user, and an emotion engine. A specific embodiment of this system will be described in detail below.

[0276] Selecting and uploading audio data

[0277] The user selects audio data (MP3 or WAV format) from the local disk using the device's file selection function. The selected audio data is then uploaded to the server via the Internet using an HTTP POST request.

[0278] Analysis of sound source data

[0279] After receiving the uploaded audio data, the server analyzes the musical characteristics using music analysis libraries such as LibROSA and pydub. Specifically, it performs frequency spectrum analysis, pitch detection, rhythm extraction, and tempo calculation. The analysis results are saved in JSON format and used in the next step.

[0280] Staff generation

[0281] The server generates a musical staff using ABC notation or MusicXML based on the analyzed musical feature data. At this stage, pitch and rhythm information is converted into visual symbols and expressed as musical notation. The generated musical staff is converted into an image file (PNG or SVG format) and sent to the device.

[0282] Emotion recognition by emotion engine

[0283] The device uses a built-in emotion engine to analyze the user's emotions in real time. This emotion engine uses a camera and microphone to capture the user's facial expressions and voice, and then uses machine learning models to recognize emotions. OpenCV is used for facial recognition, and a general speech recognition API is used for voice analysis.

[0284] Emotional adjustment of the musical staff

[0285] The server receives the emotion information sent from the device and adjusts the music score accordingly. For example, if the user expresses sadness, the server slows down the tempo and lowers the pitch.

[0286] Musical score format conversion and final output

[0287] The user selects the desired music notation format (e.g., tablature, chord notation), and the information is sent to the server. The server converts the staff notation into the desired format and generates the final music notation. The converted music notation is then resent to the device as an image file, which the user can download and use to play the instrument.

[0288] Specific examples

[0289] For example, a user uploads an MP3 file recording of themselves playing the piano to a server. The server analyzes this audio data and extracts that it is in the key of C major and in 4 / 4 time. The generated staff is sent to the device, where the user can review it. The emotion engine recognizes the user's emotion (e.g., joy), and adjusts the staff to speed up the tempo and raise the pitch based on this emotion. The user selects conversion to tablature, and this information is sent to the server, and the converted tablature is sent to the device. Finally, the user can download the tablature and use it to play an instrument.

[0290] In this way, the present invention can reflect the user's emotions in the musical score generated from the sound source data, thereby providing a more expressive score.

[0291] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0292] Step 1: Select and upload audio data

[0293] The user uses the file selection function of the device to select audio data (MP3 or WAV format) from the local disk. After this audio data is selected, it is uploaded to the server using an HTTP POST request. Specifically, the selected file is attached to the submission form and the audio data is sent to the server by clicking the submit button. The input is the file path of the audio data, and the output is the audio data saved on the server.

[0294] Step 2: Analyzing the sound source data

[0295] After receiving the uploaded audio data, the server analyzes the musical features using music analysis libraries such as LibROSA and pydub. Specifically, it performs frequency spectrum analysis (FFT), pitch tracking, beat detection, and tempo estimation. The input is the audio data stored on the server, and the output is JSON-formatted data containing the musical features.

[0296] Step 3: Generate the staff notation

[0297] The server generates a staff using ABC notation or MusicXML based on the analyzed musical feature data. Specifically, it converts the extracted pitch information into musical notes on a staff, and visually arranges the rhythm information as rhythm symbols. The generated staff is converted into an image file (PNG or SVG format) and sent to the device. The input is JSON data containing the musical features, and the output is an image file of the generated staff.

[0298] Step 4: Emotion Recognition with the Emotion Engine

[0299] The device uses a built-in emotion engine to analyze the user's emotions in real time. This emotion engine uses a camera and microphone to capture the user's facial expressions and voice, and recognizes emotions using a machine learning model. Specifically, it uses OpenCV for facial expression recognition and a general speech recognition API for voice analysis. The input is the user's facial expression and voice data, and the output is recognized emotional information.

[0300] Step 5: Adjusting the staff according to your emotions

[0301] The server receives the emotion information sent from the device and adjusts the generated staff based on it. Specifically, it changes the tempo (for example, slowing down the tempo for sadness) or the pitch (for example, raising the pitch for joy). The input is an image file of the staff and the emotion information, and the output is an image file of the adjusted staff.

[0302] Step 6: Converting the music score format and final output

[0303] The user selects the desired music notation format (e.g., tablature, chord notation), and this information is sent to the server. The server converts the staff notation into the desired format and generates the final music notation. The generated music notation is again sent to the terminal as an image file, which the user can download and use to play an instrument, etc. The input is an image file of the adjusted music notation and the user's selection information, and the output is an image file of the music notation converted into the desired format.

[0304] (Application example 2)

[0305] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0306] Conventional audio data analysis systems have the ability to extract musical features and convert music into staff notation or other notation formats, but they are unable to adjust the music to reflect the user's emotions, making it difficult to provide emotional resonance with the user. Furthermore, in the case of advertising music, the effectiveness of advertising is limited because it is unable to generate optimal music based on the user's emotions. A system that can solve these problems and generate music based on the user's emotions is needed.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0308] In this invention, the server includes means for receiving sound source data, means for analyzing the received sound source data and extracting musical features, means for generating staff notation based on the extracted musical features, means for converting the generated staff notation into a plurality of different musical notation formats, means for recognizing a user's emotion and adjusting the staff notation or other musical notation format based on the recognized emotion, and means for generating and providing the adjusted staff notation or other musical notation format as advertising music. This makes it possible to generate music that reflects the user's emotion, and to provide music that is optimal for advertising.

[0309] "Audio data" refers to digital data containing recorded music or audio, such as MP3 or WAV files.

[0310] "Musical features" are elements that represent the structure of music, and include information such as frequency, pitch, rhythm, and tempo.

[0311] A "staff" is a musical notation used to visually record music, and is used to express musical melodies and chords by arranging notes on five horizontal lines (staff).

[0312] A "music format" is a particular format or method for recording music, including, for example, staff notation, string notation, cultural notation, tablature, chord notation, etc.

[0313] "Emotion recognition" refers to determining a person's emotional state by analyzing their facial expressions, tone of voice, movements, or interaction data.

[0314] "Advertising music" is music created specifically for use in advertising, with the purpose of amplifying the appeal of a brand or product.

[0315] A "system" is an integrated framework that includes multiple components or modules that work in conjunction with each other to achieve a specific purpose.

[0316] The present invention is composed of a system that analyzes audio source data, generates musical notation, and converts it into multiple different musical notation formats, and adds an emotion engine that recognizes user emotions. This system is particularly useful in the advertising field, and can automatically generate advertising music that reflects the user's emotions.

[0317] Receiving and analyzing sound source data

[0318] A user selects audio data (e.g., MP3 or WAV files) using a terminal and uploads it to the server. The server receives the audio data and analyzes its musical characteristics (frequency, pitch, rhythm, tempo, etc.) using a library such as LibROSA.

[0319] Staff generation

[0320] The server generates a staff notation using the MusicXML format based on the extracted musical feature data, and the generated staff notation is sent to the terminal as an image file.

[0321] Recognizing user emotions with an emotion engine

[0322] The device uses an emotion engine to recognize the user's emotions. This emotion engine analyzes the user's facial expressions and tone of voice via a camera and microphone to determine emotions such as joy, sadness, and surprise.

[0323] Adjusting staff notation and music notation format according to emotions

[0324] The server receives the recognized user's emotion information and adjusts the generated staff notation or other musical notation format (e.g., string notation, cultural notation, tablature, chord notation, etc.) For example, if the user expresses joy, the tempo is increased and the pitch is increased.

[0325] Conversion and final output

[0326] The user selects the desired music notation format. Based on the selection and the recognized emotion information, the server converts the staff notation into another music notation format. The converted music notation is sent to the terminal again as an image file, and the user can view it and download it as needed. The converted music notation is used as advertising music.

[0327] Specific examples

[0328] When a user uploads an MP3 file of a piano performance to the server, the server analyzes the audio data and determines that it is in the key of C major and in 4 / 4 time. The generated staff is then sent to the device. The user reviews the staff, and the emotion engine recognizes the user's emotion (e.g., joy). Based on this emotion, the staff is adjusted to increase the tempo and pitch. The user selects conversion to tablature, and this information is sent to the server, and the converted tablature is sent to the device. Finally, the user can download the tablature and use it as advertising music.

[0329] Prompt Sentence Examples

[0330] "Analyze the following audio data, generate a musical score, and create advertising music tailored to the user's emotion, 'joy.' [Audio data file path: path_to_audio_file.mp3]"

[0331] The system of the present invention can analyze musical characteristics and convert music into various musical notation formats that take emotions into account efficiently and automatically, making it possible to provide music optimized for user emotions in the advertising field.

[0332] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0333] Step 1:

[0334] The user selects audio data using the device and uploads it to the server. To do this, the user selects the recorded MP3 or WAV file and presses the "Upload" button. The audio data file is the input, which is transferred to the server. The audio data is stored on the server as the output.

[0335] Step 2:

[0336] The audio data received by the server is analyzed using the LibROSA library. Specifically, the audio data is loaded and musical features such as frequency, pitch, rhythm, and tempo are extracted. In this process, the audio data is read using LibROSA's load function, and various features are extracted using the beat_track and piptrack functions. The audio data is input, and musical feature data (tempo, beat, pitch, etc.) is obtained as output.

[0337] Step 3:

[0338] The server generates a staff notation in MusicXML format based on the extracted musical feature data. Specifically, it uses the Music21 library to convert musical features (e.g., pitch and beat) into a staff notation. This process uses Music21's stream.Stream and note.Note to generate the staff notation. The input is musical feature data, and the output is staff notation data in MusicXML format.

[0339] Step 4:

[0340] The server sends the generated staff data to the device as an image file. Specifically, it converts the MusicXML format staff data into an image format (PNG or PDF) and transfers that file to the device. The staff data is input, and the image file is transferred to the device as output.

[0341] Step 5:

[0342] The device uses an emotion engine to recognize the user's emotions. Specifically, it uses a camera and microphone to analyze the user's facial expressions and voice in real time to identify emotions. In this process, an emotion recognition algorithm is used to analyze input audio and video data and output emotions such as joy, sadness, and surprise. The input is the user's audio and video data, and the output is recognized emotional data.

[0343] Step 6:

[0344] The server receives the recognized emotion information and adjusts the generated staff or other notation format. Specifically, it changes the tempo and adjusts the pitch based on the recognized emotion. This process uses an algorithm that changes the tempo and pitch of the staff based on the emotion data. The inputs are the recognized emotion data and staff data, and the output is the adjusted notation data.

[0345] Step 7:

[0346] The user selects the desired music notation format, and the server converts the staff notation into another music notation format based on the selection information and the recognized emotion information. Specifically, it converts it into the desired format (e.g., TAB notation, chord notation). In this process, the staff notation is converted using a music notation format conversion algorithm. The inputs are the staff notation data and the selection information, and the converted music notation data is obtained as the output.

[0347] Step 8:

[0348] The server then sends the converted music score data back to the terminal as an image file, which the user can then check and download. Specifically, the generated music score is converted into an image format and transferred to the terminal. The converted music score data is the input, and the image file is transferred to the terminal as the output.

[0349] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0350] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0351] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0352] [Second embodiment]

[0353] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0354] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0355] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0356] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0357] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0358] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0359] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0360] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0361] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0362] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0363] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0364] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0365] The system of this invention automates the process of receiving and analyzing audio data, generating musical notation based on its musical characteristics, and then converting the notation into multiple different notation formats. This system is primarily composed of three entities: a server, a terminal, and a user.

[0366] overview

[0367] A specific embodiment of the present invention will be described below. This system can be used in a variety of fields, including music education, music score production, and music analysis.

[0368] Receiving audio data

[0369] The user selects audio data (MP3, WAV, etc.) using their own device. This audio data is selected from the device's file system and uploaded to the server via the Internet. The server receives and stores this audio data, and then proceeds to the next analysis process.

[0370] Analysis of sound source data

[0371] To analyze the audio data inside the server, algorithms are used to extract musical features. Specific libraries include LibROSA and pydub. These libraries are used to extract musical features such as frequency, pitch, rhythm, and tempo from the audio data. These feature data are temporarily stored in memory or a database.

[0372] Staff generation

[0373] Based on the extracted musical feature data, the server generates a musical staff. In this process, pitch and rhythm information is arranged as staff data in a visually easy-to-understand format. Standard formats such as ABC notation or MusicXML format are commonly used. The generated musical staff is then sent to the terminal as an image file (e.g., PNG or SVG).

[0374] Selecting the music format

[0375] The user checks the staff notation displayed on the terminal and selects the desired notation format (string notation, bunka notation, tablature, chord notation). The selection information is sent from the terminal to the server.

[0376] Conversion to music notation format

[0377] Based on the selection information received from the user, the server converts the staff notation into other notation formats using corresponding algorithms, for example, conversion to tablature applies logic that maps pitch information to guitar frets and strings.

[0378] Providing converted scores

[0379] The converted music score is then sent to the device as an image file, where the user can view the converted music score on the device and download it if necessary.

[0380] Specific examples

[0381] For example, a user uploads an MP3 file recording of a piano performance to a server. The server analyzes the audio data and extracts that it is in the key of C major and in 4 / 4 time. Next, a musical staff is generated based on this information and sent to the device. The user confirms this and chooses to convert it to tablature. This information is sent to the server, and the musical staff is converted into tablature and sent to the device. The user can finally download this tablature and use it to play the instrument.

[0382] As described above, the system of the present invention efficiently and automatically converts sound source data into a variety of musical score formats.

[0383] The processing flow will be explained below.

[0384] Step 1:

[0385] The user selects the audio data (MP3, WAV, etc.) on the device. The user selects the audio file using the file selection dialog and presses the upload button.

[0386] Step 2:

[0387] The device uploads the selected audio data to the server. The audio file selected by the user is sent to the server via an HTTP request. The server receives it and stores it in a database or temporary storage.

[0388] Step 3:

[0389] The server reads the received audio data and begins analysis to extract musical characteristics. Specifically, the server uses music analysis libraries such as LibROSA and pydub to obtain data such as frequency, pitch, rhythm, and tempo.

[0390] Step 4:

[0391] The server generates a staff notation based on the extracted musical feature data. In this process, ABC notation or MusicXML format is used to visually arrange the scale and rhythm information as staff notation data. The generated staff notation data is temporarily saved in an internal format (such as JSON or XML).

[0392] Step 5:

[0393] The server converts the generated music sheet into an image file (such as PNG or SVG), which is then sent to the device as an HTTP response.

[0394] Step 6:

[0395] The terminal displays the image of the musical staff received from the server on the screen, and provides a user interface for the user to check the musical staff and select the desired musical notation format (string notation, Bunka notation, TAB notation, chord notation).

[0396] Step 7:

[0397] The user selects the desired music score format and sends the selected information to the server by pressing the send button on the terminal.

[0398] Step 8:

[0399] The terminal sends the user's selection information to the server. The information on the selected musical score format is sent to the server as an HTTP request.

[0400] Step 9:

[0401] The server converts the staff notation into a different notation format based on the selection information received from the user. In this process, the corresponding algorithm (e.g., staff notation to tablature conversion logic) is applied.

[0402] Step 10:

[0403] The server generates the converted score as an image file again, and sends the converted score image file to the terminal as an HTTP response.

[0404] Step 11:

[0405] The terminal displays the converted music score image received from the server on the screen, and the user is given the option to check it and download the image if necessary.

[0406] Step 12:

[0407] Users can download the converted music sheet images and use them for their own purposes.

[0408] Example 1

[0409] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0410] Conventional music data analysis and score generation systems do not automate the entire process, from analyzing audio data to converting it into multiple notation formats, and require the use of multiple software programs in combination. This forces users to perform complex operations, hindering efficient workflow. Furthermore, the accuracy of conversion between different notation formats is low, making it difficult to accurately reproduce musical nuances.

[0411] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0412] In this invention, the server includes means for receiving audio data, means for analyzing the received audio data and extracting musical features, means for generating staff notation based on the extracted musical features, means for converting the generated staff notation into a plurality of different musical notation formats, means for a user to use a terminal to select audio data and upload it to the server via the Internet, means for the server to save the audio data and extract musical features using a library, means for the server to generate staff notation based on the extracted musical features and send it to the terminal as an image file, means for a user to check the staff notation on the terminal and select a desired musical notation format, means for the server to receive the selection information and convert the staff notation into a different musical notation format, and means for sending the converted musical notation to the terminal as an image file. This makes it possible to centrally and automatically perform the entire process from receiving audio data to analyzing it, generating staff notation, converting it into a different musical notation format, and providing it to the terminal.

[0413] "Sound source data" refers to data that records music or audio information in digital or analog format.

[0414] The "receiving means" is a device or module for receiving sound source data from the outside.

[0415] "Analyzing means" refers to devices or software that perform processing to extract musical characteristics from sound source data.

[0416] "Musical features" are elements such as frequency, pitch, rhythm, and tempo contained in the sound source data.

[0417] "Extraction means" refers to devices or software that identify musical characteristics from sound source data and extract them as data.

[0418] "Staff notation" is a form of notation that visually represents musical features.

[0419] A "generating means" is a device or software for constructing a musical staff based on musical characteristics.

[0420] "Music formats" are different notation formats for musical instrument performance, including staff notation, tablature, cultural notation, string notation, chord notation, etc.

[0421] A "converting means" is a device or software that converts the original staff notation into another notation format.

[0422] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0423] A "library" is a collection of existing programming tools and algorithms used for analysis and transformation.

[0424] A "user" is someone who uses this system to upload audio data and obtain the converted sheet music.

[0425] The "server" is a central control device that analyzes received sound source data, generates musical staves, and performs conversion processing.

[0426] MODE FOR CARRYING OUT THE INVENTION

[0427] The system of this invention automates the process of receiving and analyzing audio data, generating musical notation based on its musical characteristics, and then converting the notation into multiple different notation formats. This system is primarily composed of three entities: a server, a terminal, and a user.

[0428] Receiving audio data

[0429] The user selects audio data (MP3, WAV, etc.) using their own device. This is done by selecting an audio file from the device's file system. The selected audio data is then uploaded from the device to a server via the Internet, using a communication protocol such as an HTTP POST request. The server receives the audio data and saves it in a specified directory on the server.

[0430] Analysis of sound source data

[0431] The server analyzes the received audio data. This analysis uses libraries such as LibROSA and pydub to extract musical features. Specifically, the server loads the audio data into memory and uses LibROSA to extract musical features such as frequency, pitch, rhythm, and tempo. The extracted feature data is temporarily stored in the server's memory or database.

[0432] Staff generation

[0433] The server generates a musical staff based on the extracted musical feature data. In this process, the staff data is constructed using a standard format such as ABC notation or MusicXML format. The generated staff is exported to a visually easy-to-understand format and sent to the terminal as an image file (such as PNG or SVG).

[0434] Selecting the music format

[0435] The user checks the staff notation displayed on the terminal and selects the desired notation format (string notation, bunka notation, tablature, chord notation). The selected information is sent from the terminal to the server via an HTTP request.

[0436] Conversion to music notation format

[0437] The server converts the staff notation into other notation formats based on the user's selections (for example, tablature, which uses an algorithm to map pitch information to guitar frets and strings), and the converted notation is again generated as an image file.

[0438] Providing converted scores

[0439] The server sends the converted music score image file to the terminal, where the user can check the converted music score on the terminal and download it as needed.

[0440] Specific examples

[0441] For example, a user uploads an MP3 file recording a piano performance to a server. The server analyzes the audio data and determines that it is in the key of C major and in 4 / 4 time. Next, a musical staff is generated based on this information and sent to the device. The user confirms this and chooses to convert it to tablature. This information is sent to the server, and the musical staff is converted to tablature and sent to the device. The user can then download the tablature and use it to play their instrument.

[0442] Prompt Sentence Examples

[0443] The user uploads an MP3 file of their piano performance to the server, which analyzes the audio data to generate a 4 / 4 staff in the key of C major and converts it into tablature format.

[0444] As described above, the system of the present invention can centrally and automatically perform all processes from receiving sound source data to analyzing it, generating staff notation, and converting it into different musical notation formats and providing it.

[0445] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0446] Step 1: Select and upload audio data

[0447] Input: The user selects audio data (MP3, WAV, etc.) using their own device (computer, smartphone, etc.).

[0448] Specific operation: The user opens a file selection dialog on the device and selects an audio file.

[0449] Output: The selected audio data is stored in the specified file path on the device.

[0450] Next process: The audio data is uploaded to the server.

[0451] Step 2: Upload the audio data

[0452] Input: User selected audio data.

[0453] What happens: The user clicks the upload button in their browser or application.

[0454] Output: The audio data is sent to the server via an HTTP POST request.

[0455] Next process: The server receives and stores the audio data.

[0456] Step 3: Receiving and saving audio data

[0457] Input: Audio data uploaded by users to the server.

[0458] Specific operation: The server receives an HTTP request and saves the audio data in a specific directory.

[0459] Output: Audio data stored in the file system.

[0460] Next process: The server prepares to analyze the sound source data.

[0461] Step 4: Loading the sound source data

[0462] Input: Audio data stored in the server's file system.

[0463] Specific operation: The server uses libraries such as LibROSA and pydub to load the audio data into memory.

[0464] Output: Sound source data loaded into memory.

[0465] Next process: Analyze the sound source data.

[0466] Step 5: Analyzing the sound source data

[0467] Input: Sound source data loaded into memory.

[0468] Specific operation: The server uses LibROSA to extract musical features such as frequency, pitch, rhythm, and tempo.

[0469] Output: Extracted musical feature data.

[0470] Next process: Save musical feature data and prepare for staff generation.

[0471] Step 6: Saving musical feature data

[0472] Input: Extracted musical feature data.

[0473] Specific operation: The server temporarily stores the feature data in memory or a database.

[0474] Output: Saved musical feature data.

[0475] Next step: Start the staff generation process.

[0476] Step 7: Generate the staff notation

[0477] Input: Stored musical feature data.

[0478] Specific operation: The server constructs staff data based on the musical feature data using a standard format such as ABC notation or MusicXML format.

[0479] Output: The generated musical staff.

[0480] Next process: Export the generated staff as an image file and send it to the user's device.

[0481] Step 8: Send and review the score

[0482] Input: The generated musical staff.

[0483] Specific operation: The server converts the generated staff into an image file in PNG or SVG format and sends it to the user's device as an HTTP response. The user then checks the staff on their device.

[0484] Output: A staff image displayed on the user's device.

[0485] Next process: The user selects the desired musical score format.

[0486] Step 9: Select the desired music format

[0487] Input: The staff displayed by the user.

[0488] Specific operation: The user selects the desired music notation format (e.g., tablature, bunka notation, string notation, chord notation) on the terminal using a pull-down menu or radio buttons.

[0489] Output: Selected music notation format information.

[0490] Next process: The selection information is sent from the terminal to the server.

[0491] Step 10: Converting the music format

[0492] Input: Selection information of musical score format received by the server.

[0493] What it does: The server uses the corresponding algorithm to convert the musical staff into the format of your choice, for example, to tablature, mapping pitch information to guitar frets and strings.

[0494] Output: The converted score.

[0495] Next process: Send the converted score to the user's terminal.

[0496] Step 11: Providing the converted score

[0497] Input: The converted score.

[0498] Specific operation: The server converts the converted score into an image file in PNG or SVG format and sends it to the user's device as an HTTP response. The user can check the converted score on their device and download it if necessary.

[0499] Output: The converted music score image displayed on the user's device.

[0500] Next process: The user downloads and uses the converted musical score.

[0501] (Application example 1)

[0502] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0503] In recent years, there has been a growing need in music education and music notation production to quickly and accurately convert audio files into sheet music. Furthermore, while it is necessary to provide different notation formats for different instruments and purposes, the reality is that this conversion process takes a great deal of time and effort. Furthermore, there is a need for on-site visual confirmation of sheet music and real-time conversion into different notation formats, but current systems face challenges that make this difficult.

[0504] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0505] In this invention, the server includes means for receiving audio data, means for analyzing the audio data and extracting musical features, means for generating musical notation based on the extracted musical features, means for converting the generated musical notation into a plurality of different musical notation formats, means for displaying the generated musical notation on a visual device in real time, and means for allowing a user to select a desired musical notation format and for instantly converting and displaying the musical notation into a different musical notation format based on the user's selection. This automates the generation of musical notation from audio data and the conversion into different musical notation formats, making it possible to check and operate the musical notation in real time through the visual device.

[0506] "Audio data" refers to information that records music or sound in digital or analog format.

[0507] "Musical features" are musical components such as frequency, pitch, rhythm, and tempo extracted from sound source data.

[0508] A musical staff is a sheet of music consisting of five lines used to write musical melodies and chords.

[0509] "Music format" refers to different notation methods for writing musical scores, such as staff notation, tablature, and cultural notation.

[0510] A "visual device" is a device that allows users to visually confirm information, and specifically includes smart glasses and head-mounted displays.

[0511] "Real-time display" is a function that displays the results of data processing immediately after it is performed.

[0512] The "selection means" is a means by which a user selects a desired option from multiple options.

[0513] "Instant conversion" refers to the rapid conversion of data formats based on user instructions or selections, without delay.

[0514] A specific embodiment of the present invention will be described below. The system has the functions of receiving and analyzing audio source data, generating musical staves, instantly converting them into different musical notation formats, and displaying them on a visual device in real time.

[0515] Receiving audio data

[0516] The user selects audio data (MP3, WAV, etc.) using their own device. The audio data is selected from the device's file system and uploaded to the server via the Internet. The server receives and stores this audio data and proceeds to the next analysis process.

[0517] Analysis of sound source data

[0518] To analyze the audio data inside the server, algorithms are used to extract musical features. Specific libraries include LibROSA and pydub. These libraries are used to extract musical features such as frequency, pitch, rhythm, and tempo from the audio data. These feature data are temporarily stored in memory or a database.

[0519] Staff generation

[0520] The server generates a staff based on the extracted musical feature data. In this process, pitch and rhythm information is arranged as staff data in a visually easy-to-understand format. Standard formats such as ABC notation or MusicXML are commonly used. The generated staff is then sent to the terminal as an image file (e.g., PNG or SVG).

[0521] Selecting and converting music notation formats

[0522] The user checks the staff notation displayed on the device and selects the desired notation format (e.g., tablature). The selection information is sent from the device to the server. The server converts the staff notation into another notation format based on the selection information received from the user. This process uses corresponding algorithms. For example, conversion to tablature applies logic that maps pitch information to guitar frets and strings.

[0523] Real-time display of generated music scores

[0524] The generated score is displayed in real time on a visual device (e.g., smart glasses or a head-mounted display), allowing the user to check the score and continue playing as needed.

[0525] Specific examples

[0526] For example, a user uploads audio data of a performance on an electronic piano. The audio data is analyzed by the server and determined to be in the key of C major and in 4 / 4 time. A staff notation is then generated based on this information and displayed on the user's visual device. If the user selects conversion to tablature, the information is sent to the server, and the staff notation is converted to tablature and displayed instantly on the visual device. The user can then continue playing the instrument using the tablature.

[0527] Prompt Sentence Examples

[0528] "Please receive audio played on an electronic piano via the Internet, analyze it in real time, and display it as musical notation. Furthermore, please create a system that can convert and display the music notation on the spot when the user selects a desired notation format (e.g., tablature)."

[0529] In this way, the system of the present invention efficiently and automatically converts audio data into various musical score formats, and realizes real-time display through a visual device.

[0530] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0531] Step 1: Receiving audio data

[0532] A user selects audio data (MP3, WAV, etc.) using their own device. The selected audio data is uploaded to a server via the Internet. The server receives and stores this audio data. The input is the audio data file, and the output is the audio data stored on the server.

[0533] Step 2: Analyzing the sound source data

[0534] The server analyzes the received audio data. Using libraries such as LibROSA or pydub, it extracts musical features such as frequency, pitch, rhythm, and tempo from the audio data. The extracted feature data is temporarily stored in memory or a database. The input is the audio data, and the output is musical feature data.

[0535] Step 3: Generate the staff notation

[0536] The server generates a staff notation based on the analyzed musical feature data. Using a library such as Music21, pitch and rhythm information is arranged as staff notation data in a visually easy-to-understand format. The generated staff notation data is output as an image file (such as PNG or SVG). The input is musical feature data, and the output is an image file of the staff notation.

[0537] Step 4: Select the music format

[0538] The user checks the staff displayed on the terminal and selects the desired music notation format. This selection information is sent from the user to the server via the terminal. The input is the staff image file and the user's selection information, and the output is the selection information sent to the server.

[0539] Step 5: Converting to music notation format

[0540] The server converts the staff notation into other notation formats based on the selections received from the user. For conversion to tablature and other notation formats, logic is applied to map the pitch information to the appropriate instrument frets and strings. The input is an image file of the staff notation and the selections, and the output is an image file of the different notation formats.

[0541] Step 6: Real-time display

[0542] The server displays the generated musical score in real time on a visual device (such as smart glasses or a head-mounted display). The user can check the score through this device and continue playing if necessary. The input is image files in different musical score formats, and the output is the musical score displayed on the visual device.

[0543] This allows users to generate sheet music from audio data, convert it into the desired notation format, and check it in real time. Through the specific operations and data flow, users can clearly understand how the entire system works.

[0544] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0545] This invention combines a system that analyzes audio data to generate musical notation and converts the notation into multiple different musical notation formats with an emotion engine that recognizes the user's emotions. This system can provide musical notation that reflects the user's emotions in music education, music notation production, and music analysis.

[0546] overview

[0547] A specific embodiment of the present invention will be described below. This system is configured by adding an emotion engine to three main entities: a server, a terminal, and a user.

[0548] Receiving and analyzing sound source data

[0549] The user selects audio data (MP3, WAV, etc.) using a device. This audio data is selected on the device and uploaded to a server via the Internet. Once the server receives the audio data, it begins processing to analyze its musical features. This analysis uses libraries such as LibROSA and pydub to extract musical features such as frequency, pitch, rhythm, and tempo.

[0550] Staff generation

[0551] The server generates a musical staff based on the extracted musical feature data. It uses ABC notation or MusicXML format to visually arrange pitch and rhythm information. The generated musical staff is sent to the device as an image file.

[0552] Recognizing user emotions with an emotion engine

[0553] The device recognizes the user's emotions using an emotion engine. This emotion engine includes algorithms that analyze emotions from the user's voice, facial expressions, input content, etc. For example, it can recognize emotions such as joy, sadness, and surprise by analyzing the user's facial expressions and tone of voice through a camera or microphone.

[0554] Adjusting staff notation and music notation format according to emotions

[0555] The server receives the recognized user emotion information and adjusts the generated staff notation or any other notation format (string notation, music notation, tablature, chord notation), including changing the pitch and tempo, for example, if the user expresses sadness, slow down the tempo and change to a lower pitch.

[0556] Conversion and final output

[0557] The user selects the desired music notation format, and the server converts the staff notation into another music notation format based on the user's selection and the recognized emotion information. The converted music notation is then sent to the terminal as an image file, where the user can view it and download it if necessary.

[0558] Specific examples

[0559] For example, a user uploads an MP3 file recording a piano performance to the server. The server analyzes this audio data and extracts that it is in the key of C major and in 4 / 4 time. The generated staff is then sent to the device. The user reviews this staff, and the emotion engine recognizes the user's emotion (e.g., joy). Based on this emotion, the staff is adjusted to increase the tempo and pitch. The user then selects conversion to TAB notation, and this information is sent to the server, and the converted TAB is sent to the device. Finally, the user can download this TAB and use it to play an instrument.

[0560] As described above, the system of the present invention efficiently and automatically converts sound source data into a variety of musical score formats that take emotion into consideration.

[0561] The processing flow will be explained below.

[0562] Step 1:

[0563] The user selects the audio data (MP3, WAV, etc.) on the device. The user selects the audio file using the file selection dialog and presses the upload button.

[0564] Step 2:

[0565] The device uploads the selected audio data to the server. The audio file selected by the user is sent to the server via an HTTP request. The server receives it and stores it in a database or temporary storage.

[0566] Step 3:

[0567] The server reads the received audio data and begins analysis to extract musical characteristics. Specifically, the server uses music analysis libraries such as LibROSA and pydub to obtain data such as frequency, pitch, rhythm, and tempo.

[0568] Step 4:

[0569] The server generates a staff notation based on the extracted musical feature data. In this process, ABC notation or MusicXML format is used to visually arrange the scale and rhythm information as staff notation data. The generated staff notation data is temporarily stored in memory or a database.

[0570] Step 5:

[0571] The server converts the generated music sheet into an image file (such as PNG or SVG), which is then sent to the device as an HTTP response.

[0572] Step 6:

[0573] The device displays the image of the musical staff received from the server on the screen. The user confirms it, and the emotion engine begins preparations to recognize the user's emotions.

[0574] Step 7:

[0575] To recognize the user's emotions, the device uses a camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes this data and recognizes the user's emotions.

[0576] Step 8:

[0577] The device sends the recognized emotion information to the server, which is then sent as an HTTP request.

[0578] Step 9:

[0579] The server receives the emotion information and makes adjustments to the generated musical staff or other notation format, for example, lowering the pitch and slowing the tempo if sadness is recognized.

[0580] Step 10:

[0581] The user selects the desired music notation format, and the selected information and adjusted staff data are sent to the server.

[0582] Step 11:

[0583] Based on the selected notation format, the server converts the adjusted staff notation into other different notation formats (string notation, bunka notation, tablature, chord notation), using corresponding algorithms in this process.

[0584] Step 12:

[0585] The server generates the converted music score as an image file and sends it to the terminal as an HTTP response.

[0586] Step 13:

[0587] The terminal displays the converted music score image received from the server on the screen, and provides the user with the option to check it and download the image if necessary.

[0588] Step 14:

[0589] Users can download the converted music sheet images and use them for their own purposes.

[0590] Example 2

[0591] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0592] While existing audio data analysis systems can extract musical features and generate musical scores, they lack the ability to adjust the scores to reflect the user's emotions, making it difficult to improve the emotional expressiveness of the scores and the satisfaction of the score users. For this reason, there is a demand for systems with more advanced functions that reflect the user's emotions in the fields of music education, sheet music production, and music analysis.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0594] In this invention, the server includes means for receiving sound source data, means for analyzing the received sound source data and extracting musical features, means for generating a staff based on the extracted musical features, means for adjusting the staff generated by the staff generating means based on user emotion information, means for converting the adjusted staff into a plurality of different music notation formats, and means for transmitting the output from the means for converting into a plurality of different music notation formats to a user terminal. This makes it possible to reflect the user's emotions in the musical score generated from the sound source data and provide more expressive music notation.

[0595] "Audio data" refers to music or audio data recorded in digital or analog format.

[0596] "Means for receiving" refers to a mechanism, method, or technology for capturing audio source data into a particular location or system.

[0597] "Means for analyzing and extracting musical features" refers to methods and techniques for identifying and extracting specific musical elements such as frequency, pitch, rhythm, and tempo from audio source data.

[0598] "Means for generating musical staff notation" refers to a method or technology for converting extracted musical features into a musical staff notation format to visually represent the musical pitch, rhythm, and tempo.

[0599] "Emotional information" refers to data on the user's emotional state analyzed from their voice, facial expressions, input, etc.

[0600] "Adjustment means" refers to techniques or methods for changing the pitch, tempo, rhythm, etc. of an existing musical staff based on recognized emotional information.

[0601] "Means for converting into multiple different notation formats" refers to techniques and methods for converting staff notation format data into other formats (e.g., string notation, bunka notation, tablature, chord notation).

[0602] "Transmission means" refers to the method or technology for transferring the generated or converted music score data to the user's terminal.

[0603] "Terminal" means a computer system or device operated by a user to select and upload audio data or to receive final score data.

[0604] This invention combines a system that analyzes audio data to generate musical notation and converts the musical notation into multiple different notation formats with an emotion engine that recognizes the user's emotions. This system can provide musical notation that reflects the user's emotions in music education, music notation production, and music analysis.

[0605] The system's components mainly include a server, a terminal, a user, and an emotion engine. A specific embodiment of this system will be described in detail below.

[0606] Selecting and uploading audio data

[0607] The user selects audio data (MP3 or WAV format) from the local disk using the device's file selection function. The selected audio data is then uploaded to the server via the Internet using an HTTP POST request.

[0608] Analysis of sound source data

[0609] After receiving the uploaded audio data, the server analyzes the musical characteristics using music analysis libraries such as LibROSA and pydub. Specifically, it performs frequency spectrum analysis, pitch detection, rhythm extraction, and tempo calculation. The analysis results are saved in JSON format and used in the next step.

[0610] Staff generation

[0611] The server generates a musical staff using ABC notation or MusicXML based on the analyzed musical feature data. At this stage, pitch and rhythm information is converted into visual symbols and expressed as musical notation. The generated musical staff is converted into an image file (PNG or SVG format) and sent to the device.

[0612] Emotion recognition by emotion engine

[0613] The device uses a built-in emotion engine to analyze the user's emotions in real time. This emotion engine uses a camera and microphone to capture the user's facial expressions and voice, and then uses machine learning models to recognize emotions. OpenCV is used for facial recognition, and a general speech recognition API is used for voice analysis.

[0614] Emotional adjustment of the musical staff

[0615] The server receives the emotion information sent from the device and adjusts the music score accordingly. For example, if the user expresses sadness, the server slows down the tempo and lowers the pitch.

[0616] Musical score format conversion and final output

[0617] The user selects the desired music notation format (e.g., tablature, chord notation), and the information is sent to the server. The server converts the staff notation into the desired format and generates the final music notation. The converted music notation is then resent to the device as an image file, which the user can download and use to play the instrument.

[0618] Specific examples

[0619] For example, a user uploads an MP3 file recording of themselves playing the piano to a server. The server analyzes this audio data and extracts that it is in the key of C major and in 4 / 4 time. The generated staff is sent to the device, where the user can review it. The emotion engine recognizes the user's emotion (e.g., joy), and adjusts the staff to speed up the tempo and raise the pitch based on this emotion. The user selects conversion to tablature, and this information is sent to the server, and the converted tablature is sent to the device. Finally, the user can download the tablature and use it to play an instrument.

[0620] In this way, the present invention can reflect the user's emotions in the musical score generated from the sound source data, thereby providing a more expressive score.

[0621] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0622] Step 1: Select and upload audio data

[0623] The user uses the file selection function of the device to select audio data (MP3 or WAV format) from the local disk. After this audio data is selected, it is uploaded to the server using an HTTP POST request. Specifically, the selected file is attached to the submission form and the audio data is sent to the server by clicking the submit button. The input is the file path of the audio data, and the output is the audio data saved on the server.

[0624] Step 2: Analyzing the sound source data

[0625] After receiving the uploaded audio data, the server analyzes the musical features using music analysis libraries such as LibROSA and pydub. Specifically, it performs frequency spectrum analysis (FFT), pitch tracking, beat detection, and tempo estimation. The input is the audio data stored on the server, and the output is JSON-formatted data containing the musical features.

[0626] Step 3: Generate the staff notation

[0627] The server generates a staff using ABC notation or MusicXML based on the analyzed musical feature data. Specifically, it converts the extracted pitch information into musical notes on a staff, and visually arranges the rhythm information as rhythm symbols. The generated staff is converted into an image file (PNG or SVG format) and sent to the device. The input is JSON data containing the musical features, and the output is an image file of the generated staff.

[0628] Step 4: Emotion Recognition with the Emotion Engine

[0629] The device uses a built-in emotion engine to analyze the user's emotions in real time. This emotion engine uses a camera and microphone to capture the user's facial expressions and voice, and recognizes emotions using a machine learning model. Specifically, it uses OpenCV for facial expression recognition and a general speech recognition API for voice analysis. The input is the user's facial expression and voice data, and the output is recognized emotional information.

[0630] Step 5: Adjusting the staff according to your emotions

[0631] The server receives the emotion information sent from the device and adjusts the generated staff based on it. Specifically, it changes the tempo (for example, slowing down the tempo for sadness) or the pitch (for example, raising the pitch for joy). The input is an image file of the staff and the emotion information, and the output is an image file of the adjusted staff.

[0632] Step 6: Converting the music score format and final output

[0633] The user selects the desired music notation format (e.g., tablature, chord notation), and this information is sent to the server. The server converts the staff notation into the desired format and generates the final music notation. The generated music notation is again sent to the terminal as an image file, which the user can download and use to play an instrument, etc. The input is an image file of the adjusted music notation and the user's selection information, and the output is an image file of the music notation converted into the desired format.

[0634] (Application example 2)

[0635] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0636] Conventional audio data analysis systems have the ability to extract musical features and convert music into staff notation or other notation formats, but they are unable to adjust the music to reflect the user's emotions, making it difficult to provide emotional resonance with the user. Furthermore, in the case of advertising music, the effectiveness of advertising is limited because it is unable to generate optimal music based on the user's emotions. A system that can solve these problems and generate music based on the user's emotions is needed.

[0637] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0638] In this invention, the server includes means for receiving sound source data, means for analyzing the received sound source data and extracting musical features, means for generating staff notation based on the extracted musical features, means for converting the generated staff notation into a plurality of different musical notation formats, means for recognizing a user's emotion and adjusting the staff notation or other musical notation format based on the recognized emotion, and means for generating and providing the adjusted staff notation or other musical notation format as advertising music. This makes it possible to generate music that reflects the user's emotion, and to provide music that is optimal for advertising.

[0639] "Audio data" refers to digital data containing recorded music or audio, such as MP3 or WAV files.

[0640] "Musical features" are elements that represent the structure of music, and include information such as frequency, pitch, rhythm, and tempo.

[0641] A "staff" is a musical notation used to visually record music, and is used to express musical melodies and chords by arranging notes on five horizontal lines (staff).

[0642] A "music format" is a particular format or method for recording music, including, for example, staff notation, string notation, cultural notation, tablature, chord notation, etc.

[0643] "Emotion recognition" refers to determining a person's emotional state by analyzing their facial expressions, tone of voice, movements, or interaction data.

[0644] "Advertising music" is music created specifically for use in advertising, with the purpose of amplifying the appeal of a brand or product.

[0645] A "system" is an integrated framework that includes multiple components or modules that work in conjunction with each other to achieve a specific purpose.

[0646] The present invention is composed of a system that analyzes audio source data, generates musical notation, and converts it into multiple different musical notation formats, and adds an emotion engine that recognizes user emotions. This system is particularly useful in the advertising field, and can automatically generate advertising music that reflects the user's emotions.

[0647] Receiving and analyzing sound source data

[0648] A user selects audio data (e.g., MP3 or WAV files) using a terminal and uploads it to the server. The server receives the audio data and analyzes its musical characteristics (frequency, pitch, rhythm, tempo, etc.) using a library such as LibROSA.

[0649] Staff generation

[0650] The server generates a staff notation using the MusicXML format based on the extracted musical feature data, and the generated staff notation is sent to the terminal as an image file.

[0651] Recognizing user emotions with an emotion engine

[0652] The device uses an emotion engine to recognize the user's emotions. This emotion engine analyzes the user's facial expressions and tone of voice via a camera and microphone to determine emotions such as joy, sadness, and surprise.

[0653] Adjusting staff notation and music notation format according to emotions

[0654] The server receives the recognized user's emotion information and adjusts the generated staff notation or other musical notation format (e.g., string notation, cultural notation, tablature, chord notation, etc.) For example, if the user expresses joy, the tempo is increased and the pitch is increased.

[0655] Conversion and final output

[0656] The user selects the desired music notation format. Based on the selection and the recognized emotion information, the server converts the staff notation into another music notation format. The converted music notation is sent to the terminal again as an image file, and the user can view it and download it as needed. The converted music notation is used as advertising music.

[0657] Specific examples

[0658] When a user uploads an MP3 file of a piano performance to the server, the server analyzes the audio data and determines that it is in the key of C major and in 4 / 4 time. The generated staff is then sent to the device. The user reviews the staff, and the emotion engine recognizes the user's emotion (e.g., joy). Based on this emotion, the staff is adjusted to increase the tempo and pitch. The user selects conversion to tablature, and this information is sent to the server, and the converted tablature is sent to the device. Finally, the user can download the tablature and use it as advertising music.

[0659] Prompt Sentence Examples

[0660] "Analyze the following audio data, generate a musical score, and create advertising music tailored to the user's emotion, 'joy.' [Audio data file path: path_to_audio_file.mp3]"

[0661] The system of the present invention can analyze musical characteristics and convert music into various musical notation formats that take emotions into account efficiently and automatically, making it possible to provide music optimized for user emotions in the advertising field.

[0662] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0663] Step 1:

[0664] The user selects audio data using the device and uploads it to the server. To do this, the user selects the recorded MP3 or WAV file and presses the "Upload" button. The audio data file is the input, which is transferred to the server. The audio data is stored on the server as the output.

[0665] Step 2:

[0666] The audio data received by the server is analyzed using the LibROSA library. Specifically, the audio data is loaded and musical features such as frequency, pitch, rhythm, and tempo are extracted. In this process, the audio data is read using LibROSA's load function, and various features are extracted using the beat_track and piptrack functions. The audio data is input, and musical feature data (tempo, beat, pitch, etc.) is obtained as output.

[0667] Step 3:

[0668] The server generates a staff notation in MusicXML format based on the extracted musical feature data. Specifically, it uses the Music21 library to convert musical features (e.g., pitch and beat) into a staff notation. This process uses Music21's stream.Stream and note.Note to generate the staff notation. The input is musical feature data, and the output is staff notation data in MusicXML format.

[0669] Step 4:

[0670] The server sends the generated staff data to the device as an image file. Specifically, it converts the MusicXML format staff data into an image format (PNG or PDF) and transfers that file to the device. The staff data is input, and the image file is transferred to the device as output.

[0671] Step 5:

[0672] The device uses an emotion engine to recognize the user's emotions. Specifically, it uses a camera and microphone to analyze the user's facial expressions and voice in real time to identify emotions. In this process, an emotion recognition algorithm is used to analyze input audio and video data and output emotions such as joy, sadness, and surprise. The input is the user's audio and video data, and the output is recognized emotional data.

[0673] Step 6:

[0674] The server receives the recognized emotion information and adjusts the generated staff or other notation format. Specifically, it changes the tempo and adjusts the pitch based on the recognized emotion. This process uses an algorithm that changes the tempo and pitch of the staff based on the emotion data. The inputs are the recognized emotion data and staff data, and the output is the adjusted notation data.

[0675] Step 7:

[0676] The user selects the desired music notation format, and the server converts the staff notation into another music notation format based on the selection information and the recognized emotion information. Specifically, it converts it into the desired format (e.g., TAB notation, chord notation). In this process, the staff notation is converted using a music notation format conversion algorithm. The inputs are the staff notation data and the selection information, and the converted music notation data is obtained as the output.

[0677] Step 8:

[0678] The server then sends the converted music score data back to the terminal as an image file, which the user can then check and download. Specifically, the generated music score is converted into an image format and transferred to the terminal. The converted music score data is the input, and the image file is transferred to the terminal as the output.

[0679] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0680] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0681] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0682] [Third embodiment]

[0683] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0684] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0685] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0686] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0687] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0688] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0689] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0690] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0691] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0692] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0693] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0694] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0695] The system of this invention automates the process of receiving and analyzing audio data, generating musical notation based on its musical characteristics, and then converting the notation into multiple different notation formats. This system is primarily composed of three entities: a server, a terminal, and a user.

[0696] overview

[0697] A specific embodiment of the present invention will be described below. This system can be used in a variety of fields, including music education, music score production, and music analysis.

[0698] Receiving audio data

[0699] The user selects audio data (MP3, WAV, etc.) using their own device. This audio data is selected from the device's file system and uploaded to the server via the Internet. The server receives and stores this audio data, and then proceeds to the next analysis process.

[0700] Analysis of sound source data

[0701] To analyze the audio data inside the server, algorithms are used to extract musical features. Specific libraries include LibROSA and pydub. These libraries are used to extract musical features such as frequency, pitch, rhythm, and tempo from the audio data. These feature data are temporarily stored in memory or a database.

[0702] Staff generation

[0703] Based on the extracted musical feature data, the server generates a musical staff. In this process, pitch and rhythm information is arranged as staff data in a visually easy-to-understand format. Standard formats such as ABC notation or MusicXML format are commonly used. The generated musical staff is then sent to the terminal as an image file (e.g., PNG or SVG).

[0704] Selecting the music format

[0705] The user checks the staff notation displayed on the terminal and selects the desired notation format (string notation, bunka notation, tablature, chord notation). The selection information is sent from the terminal to the server.

[0706] Conversion to music notation format

[0707] Based on the selection information received from the user, the server converts the staff notation into other notation formats using corresponding algorithms, for example, conversion to tablature applies logic that maps pitch information to guitar frets and strings.

[0708] Providing converted scores

[0709] The converted music score is then sent to the device as an image file, where the user can view the converted music score on the device and download it if necessary.

[0710] Specific examples

[0711] For example, a user uploads an MP3 file recording of a piano performance to a server. The server analyzes the audio data and extracts that it is in the key of C major and in 4 / 4 time. Next, a musical staff is generated based on this information and sent to the device. The user confirms this and chooses to convert it to tablature. This information is sent to the server, and the musical staff is converted into tablature and sent to the device. The user can finally download this tablature and use it to play the instrument.

[0712] As described above, the system of the present invention efficiently and automatically converts sound source data into a variety of musical score formats.

[0713] The processing flow will be explained below.

[0714] Step 1:

[0715] The user selects the audio data (MP3, WAV, etc.) on the device. The user selects the audio file using the file selection dialog and presses the upload button.

[0716] Step 2:

[0717] The device uploads the selected audio data to the server. The audio file selected by the user is sent to the server via an HTTP request. The server receives it and stores it in a database or temporary storage.

[0718] Step 3:

[0719] The server reads the received audio data and begins analysis to extract musical characteristics. Specifically, the server uses music analysis libraries such as LibROSA and pydub to obtain data such as frequency, pitch, rhythm, and tempo.

[0720] Step 4:

[0721] The server generates a staff notation based on the extracted musical feature data. In this process, ABC notation or MusicXML format is used to visually arrange the scale and rhythm information as staff notation data. The generated staff notation data is temporarily saved in an internal format (such as JSON or XML).

[0722] Step 5:

[0723] The server converts the generated music sheet into an image file (such as PNG or SVG), which is then sent to the device as an HTTP response.

[0724] Step 6:

[0725] The terminal displays the image of the musical staff received from the server on the screen, and provides a user interface for the user to check the musical staff and select the desired musical notation format (string notation, Bunka notation, TAB notation, chord notation).

[0726] Step 7:

[0727] The user selects the desired music score format and sends the selected information to the server by pressing the send button on the terminal.

[0728] Step 8:

[0729] The terminal sends the user's selection information to the server. The information on the selected musical score format is sent to the server as an HTTP request.

[0730] Step 9:

[0731] The server converts the staff notation into a different notation format based on the selection information received from the user. In this process, the corresponding algorithm (e.g., staff notation to tablature conversion logic) is applied.

[0732] Step 10:

[0733] The server generates the converted score as an image file again, and sends the converted score image file to the terminal as an HTTP response.

[0734] Step 11:

[0735] The terminal displays the converted music score image received from the server on the screen, and the user is given the option to check it and download the image if necessary.

[0736] Step 12:

[0737] Users can download the converted music sheet images and use them for their own purposes.

[0738] Example 1

[0739] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0740] Conventional music data analysis and score generation systems do not automate the entire process, from analyzing audio data to converting it into multiple notation formats, and require the use of multiple software programs in combination. This forces users to perform complex operations, hindering efficient workflow. Furthermore, the accuracy of conversion between different notation formats is low, making it difficult to accurately reproduce musical nuances.

[0741] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0742] In this invention, the server includes means for receiving audio data, means for analyzing the received audio data and extracting musical features, means for generating staff notation based on the extracted musical features, means for converting the generated staff notation into a plurality of different musical notation formats, means for a user to use a terminal to select audio data and upload it to the server via the Internet, means for the server to save the audio data and extract musical features using a library, means for the server to generate staff notation based on the extracted musical features and send it to the terminal as an image file, means for a user to check the staff notation on the terminal and select a desired musical notation format, means for the server to receive the selection information and convert the staff notation into a different musical notation format, and means for sending the converted musical notation to the terminal as an image file. This makes it possible to centrally and automatically perform the entire process from receiving audio data to analyzing it, generating staff notation, converting it into a different musical notation format, and providing it to the terminal.

[0743] "Sound source data" refers to data that records music or audio information in digital or analog format.

[0744] The "receiving means" is a device or module for receiving sound source data from the outside.

[0745] "Analyzing means" refers to devices or software that perform processing to extract musical characteristics from sound source data.

[0746] "Musical features" are elements such as frequency, pitch, rhythm, and tempo contained in the sound source data.

[0747] "Extraction means" refers to devices or software that identify musical characteristics from sound source data and extract them as data.

[0748] "Staff notation" is a form of notation that visually represents musical features.

[0749] A "generating means" is a device or software for constructing a musical staff based on musical characteristics.

[0750] "Music formats" are different notation formats for musical instrument performance, including staff notation, tablature, cultural notation, string notation, chord notation, etc.

[0751] A "converting means" is a device or software that converts the original staff notation into another notation format.

[0752] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[0753] A "library" is a collection of existing programming tools and algorithms used for analysis and transformation.

[0754] A "user" is someone who uses this system to upload audio data and obtain the converted sheet music.

[0755] The "server" is a central control device that analyzes received sound source data, generates musical staves, and performs conversion processing.

[0756] MODE FOR CARRYING OUT THE INVENTION

[0757] The system of this invention automates the process of receiving and analyzing audio data, generating musical notation based on its musical characteristics, and then converting the notation into multiple different notation formats. This system is primarily composed of three entities: a server, a terminal, and a user.

[0758] Receiving audio data

[0759] The user selects audio data (MP3, WAV, etc.) using their own device. This is done by selecting an audio file from the device's file system. The selected audio data is then uploaded from the device to a server via the Internet, using a communication protocol such as an HTTP POST request. The server receives the audio data and saves it in a specified directory on the server.

[0760] Analysis of sound source data

[0761] The server analyzes the received audio data. This analysis uses libraries such as LibROSA and pydub to extract musical features. Specifically, the server loads the audio data into memory and uses LibROSA to extract musical features such as frequency, pitch, rhythm, and tempo. The extracted feature data is temporarily stored in the server's memory or database.

[0762] Staff generation

[0763] The server generates a musical staff based on the extracted musical feature data. In this process, the staff data is constructed using a standard format such as ABC notation or MusicXML format. The generated staff is exported to a visually easy-to-understand format and sent to the terminal as an image file (such as PNG or SVG).

[0764] Selecting the music format

[0765] The user checks the staff notation displayed on the terminal and selects the desired notation format (string notation, bunka notation, tablature, chord notation). The selected information is sent from the terminal to the server via an HTTP request.

[0766] Conversion to music notation format

[0767] The server converts the staff notation into other notation formats based on the user's selections (for example, tablature, which uses an algorithm to map pitch information to guitar frets and strings), and the converted notation is again generated as an image file.

[0768] Providing converted scores

[0769] The server sends the converted music score image file to the terminal, where the user can check the converted music score on the terminal and download it as needed.

[0770] Specific examples

[0771] For example, a user uploads an MP3 file recording a piano performance to a server. The server analyzes the audio data and determines that it is in the key of C major and in 4 / 4 time. Next, a musical staff is generated based on this information and sent to the device. The user confirms this and chooses to convert it to tablature. This information is sent to the server, and the musical staff is converted to tablature and sent to the device. The user can then download the tablature and use it to play their instrument.

[0772] Prompt Sentence Examples

[0773] The user uploads an MP3 file of their piano performance to the server, which analyzes the audio data to generate a 4 / 4 staff in the key of C major and converts it into tablature format.

[0774] As described above, the system of the present invention can centrally and automatically perform all processes from receiving sound source data to analyzing it, generating staff notation, and converting it into different musical notation formats and providing it.

[0775] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0776] Step 1: Select and upload audio data

[0777] Input: The user selects audio data (MP3, WAV, etc.) using their own device (computer, smartphone, etc.).

[0778] Specific operation: The user opens a file selection dialog on the device and selects an audio file.

[0779] Output: The selected audio data is stored in the specified file path on the device.

[0780] Next process: The audio data is uploaded to the server.

[0781] Step 2: Upload the audio data

[0782] Input: User selected audio data.

[0783] What happens: The user clicks the upload button in their browser or application.

[0784] Output: The audio data is sent to the server via an HTTP POST request.

[0785] Next process: The server receives and stores the audio data.

[0786] Step 3: Receiving and saving audio data

[0787] Input: Audio data uploaded by users to the server.

[0788] Specific operation: The server receives an HTTP request and saves the audio data in a specific directory.

[0789] Output: Audio data stored in the file system.

[0790] Next process: The server prepares to analyze the sound source data.

[0791] Step 4: Loading the sound source data

[0792] Input: Audio data stored in the server's file system.

[0793] Specific operation: The server uses libraries such as LibROSA and pydub to load the audio data into memory.

[0794] Output: Sound source data loaded into memory.

[0795] Next process: Analyze the sound source data.

[0796] Step 5: Analyzing the sound source data

[0797] Input: Sound source data loaded into memory.

[0798] Specific operation: The server uses LibROSA to extract musical features such as frequency, pitch, rhythm, and tempo.

[0799] Output: Extracted musical feature data.

[0800] Next process: Save musical feature data and prepare for staff generation.

[0801] Step 6: Saving musical feature data

[0802] Input: Extracted musical feature data.

[0803] Specific operation: The server temporarily stores the feature data in memory or a database.

[0804] Output: Saved musical feature data.

[0805] Next step: Start the staff generation process.

[0806] Step 7: Generate the staff notation

[0807] Input: Stored musical feature data.

[0808] Specific operation: The server constructs staff data based on the musical feature data using a standard format such as ABC notation or MusicXML format.

[0809] Output: The generated musical staff.

[0810] Next process: Export the generated staff as an image file and send it to the user's device.

[0811] Step 8: Send and review the score

[0812] Input: The generated musical staff.

[0813] Specific operation: The server converts the generated staff into an image file in PNG or SVG format and sends it to the user's device as an HTTP response. The user then checks the staff on their device.

[0814] Output: A staff image displayed on the user's device.

[0815] Next process: The user selects the desired musical score format.

[0816] Step 9: Select the desired music format

[0817] Input: The staff displayed by the user.

[0818] Specific operation: The user selects the desired music notation format (e.g., tablature, bunka notation, string notation, chord notation) on the terminal using a pull-down menu or radio buttons.

[0819] Output: Selected music notation format information.

[0820] Next process: The selection information is sent from the terminal to the server.

[0821] Step 10: Converting the music format

[0822] Input: Selection information of musical score format received by the server.

[0823] What it does: The server uses the corresponding algorithm to convert the musical staff into the format of your choice, for example, to tablature, mapping pitch information to guitar frets and strings.

[0824] Output: The converted score.

[0825] Next process: Send the converted score to the user's terminal.

[0826] Step 11: Providing the converted score

[0827] Input: The converted score.

[0828] Specific operation: The server converts the converted score into an image file in PNG or SVG format and sends it to the user's device as an HTTP response. The user can check the converted score on their device and download it if necessary.

[0829] Output: The converted music score image displayed on the user's device.

[0830] Next process: The user downloads and uses the converted musical score.

[0831] (Application example 1)

[0832] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0833] In recent years, there has been a growing need in music education and music notation production to quickly and accurately convert audio files into sheet music. Furthermore, while it is necessary to provide different notation formats for different instruments and purposes, the reality is that this conversion process takes a great deal of time and effort. Furthermore, there is a need for on-site visual confirmation of sheet music and real-time conversion into different notation formats, but current systems face challenges that make this difficult.

[0834] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0835] In this invention, the server includes means for receiving audio data, means for analyzing the audio data and extracting musical features, means for generating musical notation based on the extracted musical features, means for converting the generated musical notation into a plurality of different musical notation formats, means for displaying the generated musical notation on a visual device in real time, and means for allowing a user to select a desired musical notation format and for instantly converting and displaying the musical notation into a different musical notation format based on the user's selection. This automates the generation of musical notation from audio data and the conversion into different musical notation formats, making it possible to check and operate the musical notation in real time through the visual device.

[0836] "Audio data" refers to information that records music or sound in digital or analog format.

[0837] "Musical features" are musical components such as frequency, pitch, rhythm, and tempo extracted from sound source data.

[0838] A musical staff is a sheet of music consisting of five lines used to write musical melodies and chords.

[0839] "Music format" refers to different notation methods for writing musical scores, such as staff notation, tablature, and cultural notation.

[0840] A "visual device" is a device that allows users to visually confirm information, and specifically includes smart glasses and head-mounted displays.

[0841] "Real-time display" is a function that displays the results of data processing immediately after it is performed.

[0842] The "selection means" is a means by which a user selects a desired option from multiple options.

[0843] "Instant conversion" refers to the rapid conversion of data formats based on user instructions or selections, without delay.

[0844] A specific embodiment of the present invention will be described below. The system has the functions of receiving and analyzing audio source data, generating musical staves, instantly converting them into different musical notation formats, and displaying them on a visual device in real time.

[0845] Receiving audio data

[0846] The user selects audio data (MP3, WAV, etc.) using their own device. The audio data is selected from the device's file system and uploaded to the server via the Internet. The server receives and stores this audio data and proceeds to the next analysis process.

[0847] Analysis of sound source data

[0848] To analyze the audio data inside the server, algorithms are used to extract musical features. Specific libraries include LibROSA and pydub. These libraries are used to extract musical features such as frequency, pitch, rhythm, and tempo from the audio data. These feature data are temporarily stored in memory or a database.

[0849] Staff generation

[0850] The server generates a staff based on the extracted musical feature data. In this process, pitch and rhythm information is arranged as staff data in a visually easy-to-understand format. Standard formats such as ABC notation or MusicXML are commonly used. The generated staff is then sent to the terminal as an image file (e.g., PNG or SVG).

[0851] Selecting and converting music notation formats

[0852] The user checks the staff notation displayed on the device and selects the desired notation format (e.g., tablature). The selection information is sent from the device to the server. The server converts the staff notation into another notation format based on the selection information received from the user. This process uses corresponding algorithms. For example, conversion to tablature applies logic that maps pitch information to guitar frets and strings.

[0853] Real-time display of generated music scores

[0854] The generated score is displayed in real time on a visual device (e.g., smart glasses or a head-mounted display), allowing the user to check the score and continue playing as needed.

[0855] Specific examples

[0856] For example, a user uploads audio data of a performance on an electronic piano. The audio data is analyzed by the server and determined to be in the key of C major and in 4 / 4 time. A staff notation is then generated based on this information and displayed on the user's visual device. If the user selects conversion to tablature, the information is sent to the server, and the staff notation is converted to tablature and displayed instantly on the visual device. The user can then continue playing the instrument using the tablature.

[0857] Prompt Sentence Examples

[0858] "Please receive audio played on an electronic piano via the Internet, analyze it in real time, and display it as musical notation. Furthermore, please create a system that can convert and display the music notation on the spot when the user selects a desired notation format (e.g., tablature)."

[0859] In this way, the system of the present invention efficiently and automatically converts audio data into various musical score formats, and realizes real-time display through a visual device.

[0860] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0861] Step 1: Receiving audio data

[0862] A user selects audio data (MP3, WAV, etc.) using their own device. The selected audio data is uploaded to a server via the Internet. The server receives and stores this audio data. The input is the audio data file, and the output is the audio data stored on the server.

[0863] Step 2: Analyzing the sound source data

[0864] The server analyzes the received audio data. Using libraries such as LibROSA or pydub, it extracts musical features such as frequency, pitch, rhythm, and tempo from the audio data. The extracted feature data is temporarily stored in memory or a database. The input is the audio data, and the output is musical feature data.

[0865] Step 3: Generate the staff notation

[0866] The server generates a staff notation based on the analyzed musical feature data. Using a library such as Music21, pitch and rhythm information is arranged as staff notation data in a visually easy-to-understand format. The generated staff notation data is output as an image file (such as PNG or SVG). The input is musical feature data, and the output is an image file of the staff notation.

[0867] Step 4: Select the music format

[0868] The user checks the staff displayed on the terminal and selects the desired music notation format. This selection information is sent from the user to the server via the terminal. The input is the staff image file and the user's selection information, and the output is the selection information sent to the server.

[0869] Step 5: Converting to music notation format

[0870] The server converts the staff notation into other notation formats based on the selections received from the user. For conversion to tablature and other notation formats, logic is applied to map the pitch information to the appropriate instrument frets and strings. The input is an image file of the staff notation and the selections, and the output is an image file of the different notation formats.

[0871] Step 6: Real-time display

[0872] The server displays the generated musical score in real time on a visual device (such as smart glasses or a head-mounted display). The user can check the score through this device and continue playing if necessary. The input is image files in different musical score formats, and the output is the musical score displayed on the visual device.

[0873] This allows users to generate sheet music from audio data, convert it into the desired notation format, and check it in real time. Through the specific operations and data flow, users can clearly understand how the entire system works.

[0874] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0875] This invention combines a system that analyzes audio data to generate musical notation and converts the notation into multiple different musical notation formats with an emotion engine that recognizes the user's emotions. This system can provide musical notation that reflects the user's emotions in music education, music notation production, and music analysis.

[0876] overview

[0877] A specific embodiment of the present invention will be described below. This system is configured by adding an emotion engine to three main entities: a server, a terminal, and a user.

[0878] Receiving and analyzing sound source data

[0879] The user selects audio data (MP3, WAV, etc.) using a device. This audio data is selected on the device and uploaded to a server via the Internet. Once the server receives the audio data, it begins processing to analyze its musical features. This analysis uses libraries such as LibROSA and pydub to extract musical features such as frequency, pitch, rhythm, and tempo.

[0880] Staff generation

[0881] The server generates a musical staff based on the extracted musical feature data. It uses ABC notation or MusicXML format to visually arrange pitch and rhythm information. The generated musical staff is sent to the device as an image file.

[0882] Recognizing user emotions with an emotion engine

[0883] The device recognizes the user's emotions using an emotion engine. This emotion engine includes algorithms that analyze emotions from the user's voice, facial expressions, input content, etc. For example, it can recognize emotions such as joy, sadness, and surprise by analyzing the user's facial expressions and tone of voice through a camera or microphone.

[0884] Adjusting staff notation and music notation format according to emotions

[0885] The server receives the recognized user emotion information and adjusts the generated staff notation or any other notation format (string notation, music notation, tablature, chord notation), including changing the pitch and tempo, for example, if the user expresses sadness, slow down the tempo and change to a lower pitch.

[0886] Conversion and final output

[0887] The user selects the desired music notation format, and the server converts the staff notation into another music notation format based on the user's selection and the recognized emotion information. The converted music notation is then sent to the terminal as an image file, where the user can view it and download it if necessary.

[0888] Specific examples

[0889] For example, a user uploads an MP3 file recording a piano performance to the server. The server analyzes this audio data and extracts that it is in the key of C major and in 4 / 4 time. The generated staff is then sent to the device. The user reviews this staff, and the emotion engine recognizes the user's emotion (e.g., joy). Based on this emotion, the staff is adjusted to increase the tempo and pitch. The user then selects conversion to TAB notation, and this information is sent to the server, and the converted TAB is sent to the device. Finally, the user can download this TAB and use it to play an instrument.

[0890] As described above, the system of the present invention efficiently and automatically converts sound source data into a variety of musical score formats that take emotion into consideration.

[0891] The processing flow will be explained below.

[0892] Step 1:

[0893] The user selects the audio data (MP3, WAV, etc.) on the device. The user selects the audio file using the file selection dialog and presses the upload button.

[0894] Step 2:

[0895] The device uploads the selected audio data to the server. The audio file selected by the user is sent to the server via an HTTP request. The server receives it and stores it in a database or temporary storage.

[0896] Step 3:

[0897] The server reads the received audio data and begins analysis to extract musical characteristics. Specifically, the server uses music analysis libraries such as LibROSA and pydub to obtain data such as frequency, pitch, rhythm, and tempo.

[0898] Step 4:

[0899] The server generates a staff notation based on the extracted musical feature data. In this process, ABC notation or MusicXML format is used to visually arrange the scale and rhythm information as staff notation data. The generated staff notation data is temporarily stored in memory or a database.

[0900] Step 5:

[0901] The server converts the generated music sheet into an image file (such as PNG or SVG), which is then sent to the device as an HTTP response.

[0902] Step 6:

[0903] The device displays the image of the musical staff received from the server on the screen. The user confirms it, and the emotion engine begins preparations to recognize the user's emotions.

[0904] Step 7:

[0905] To recognize the user's emotions, the device uses a camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes this data and recognizes the user's emotions.

[0906] Step 8:

[0907] The device sends the recognized emotion information to the server, which is then sent as an HTTP request.

[0908] Step 9:

[0909] The server receives the emotion information and makes adjustments to the generated musical staff or other notation format, for example, lowering the pitch and slowing the tempo if sadness is recognized.

[0910] Step 10:

[0911] The user selects the desired music notation format, and the selected information and adjusted staff data are sent to the server.

[0912] Step 11:

[0913] Based on the selected notation format, the server converts the adjusted staff notation into other different notation formats (string notation, bunka notation, tablature, chord notation), using corresponding algorithms in this process.

[0914] Step 12:

[0915] The server generates the converted music score as an image file and sends it to the terminal as an HTTP response.

[0916] Step 13:

[0917] The terminal displays the converted music score image received from the server on the screen, and provides the user with the option to check it and download the image if necessary.

[0918] Step 14:

[0919] Users can download the converted music sheet images and use them for their own purposes.

[0920] Example 2

[0921] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0922] While existing audio data analysis systems can extract musical features and generate musical scores, they lack the ability to adjust the scores to reflect the user's emotions, making it difficult to improve the emotional expressiveness of the scores and the satisfaction of the score users. For this reason, there is a demand for systems with more advanced functions that reflect the user's emotions in the fields of music education, sheet music production, and music analysis.

[0923] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0924] In this invention, the server includes means for receiving sound source data, means for analyzing the received sound source data and extracting musical features, means for generating a staff based on the extracted musical features, means for adjusting the staff generated by the staff generating means based on user emotion information, means for converting the adjusted staff into a plurality of different music notation formats, and means for transmitting the output from the means for converting into a plurality of different music notation formats to a user terminal. This makes it possible to reflect the user's emotions in the musical score generated from the sound source data and provide more expressive music notation.

[0925] "Audio data" refers to music or audio data recorded in digital or analog format.

[0926] "Means for receiving" refers to a mechanism, method, or technology for capturing audio source data into a particular location or system.

[0927] "Means for analyzing and extracting musical features" refers to methods and techniques for identifying and extracting specific musical elements such as frequency, pitch, rhythm, and tempo from audio source data.

[0928] "Means for generating musical staff notation" refers to a method or technology for converting extracted musical features into a musical staff notation format to visually represent the musical pitch, rhythm, and tempo.

[0929] "Emotional information" refers to data on the user's emotional state analyzed from their voice, facial expressions, input, etc.

[0930] "Adjustment means" refers to techniques or methods for changing the pitch, tempo, rhythm, etc. of an existing musical staff based on recognized emotional information.

[0931] "Means for converting into multiple different notation formats" refers to techniques and methods for converting staff notation format data into other formats (e.g., string notation, bunka notation, tablature, chord notation).

[0932] "Transmission means" refers to the method or technology for transferring the generated or converted music score data to the user's terminal.

[0933] "Terminal" means a computer system or device operated by a user to select and upload audio data or to receive final score data.

[0934] This invention combines a system that analyzes audio data to generate musical notation and converts the musical notation into multiple different notation formats with an emotion engine that recognizes the user's emotions. This system can provide musical notation that reflects the user's emotions in music education, music notation production, and music analysis.

[0935] The system's components mainly include a server, a terminal, a user, and an emotion engine. A specific embodiment of this system will be described in detail below.

[0936] Selecting and uploading audio data

[0937] The user selects audio data (MP3 or WAV format) from the local disk using the device's file selection function. The selected audio data is then uploaded to the server via the Internet using an HTTP POST request.

[0938] Analysis of sound source data

[0939] After receiving the uploaded audio data, the server analyzes the musical characteristics using music analysis libraries such as LibROSA and pydub. Specifically, it performs frequency spectrum analysis, pitch detection, rhythm extraction, and tempo calculation. The analysis results are saved in JSON format and used in the next step.

[0940] Staff generation

[0941] The server generates a musical staff using ABC notation or MusicXML based on the analyzed musical feature data. At this stage, pitch and rhythm information is converted into visual symbols and expressed as musical notation. The generated musical staff is converted into an image file (PNG or SVG format) and sent to the device.

[0942] Emotion recognition by emotion engine

[0943] The device uses a built-in emotion engine to analyze the user's emotions in real time. This emotion engine uses a camera and microphone to capture the user's facial expressions and voice, and then uses machine learning models to recognize emotions. OpenCV is used for facial recognition, and a general speech recognition API is used for voice analysis.

[0944] Emotional adjustment of the musical staff

[0945] The server receives the emotion information sent from the device and adjusts the music score accordingly. For example, if the user expresses sadness, the server slows down the tempo and lowers the pitch.

[0946] Musical score format conversion and final output

[0947] The user selects the desired music notation format (e.g., tablature, chord notation), and the information is sent to the server. The server converts the staff notation into the desired format and generates the final music notation. The converted music notation is then resent to the device as an image file, which the user can download and use to play the instrument.

[0948] Specific examples

[0949] For example, a user uploads an MP3 file recording of themselves playing the piano to a server. The server analyzes this audio data and extracts that it is in the key of C major and in 4 / 4 time. The generated staff is sent to the device, where the user can review it. The emotion engine recognizes the user's emotion (e.g., joy), and adjusts the staff to speed up the tempo and raise the pitch based on this emotion. The user selects conversion to tablature, and this information is sent to the server, and the converted tablature is sent to the device. Finally, the user can download the tablature and use it to play an instrument.

[0950] In this way, the present invention can reflect the user's emotions in the musical score generated from the sound source data, thereby providing a more expressive score.

[0951] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0952] Step 1: Select and upload audio data

[0953] The user uses the file selection function of the device to select audio data (MP3 or WAV format) from the local disk. After this audio data is selected, it is uploaded to the server using an HTTP POST request. Specifically, the selected file is attached to the submission form and the audio data is sent to the server by clicking the submit button. The input is the file path of the audio data, and the output is the audio data saved on the server.

[0954] Step 2: Analyzing the sound source data

[0955] After receiving the uploaded audio data, the server analyzes the musical features using music analysis libraries such as LibROSA and pydub. Specifically, it performs frequency spectrum analysis (FFT), pitch tracking, beat detection, and tempo estimation. The input is the audio data stored on the server, and the output is JSON-formatted data containing the musical features.

[0956] Step 3: Generate the staff notation

[0957] The server generates a staff using ABC notation or MusicXML based on the analyzed musical feature data. Specifically, it converts the extracted pitch information into musical notes on a staff, and visually arranges the rhythm information as rhythm symbols. The generated staff is converted into an image file (PNG or SVG format) and sent to the device. The input is JSON data containing the musical features, and the output is an image file of the generated staff.

[0958] Step 4: Emotion Recognition with the Emotion Engine

[0959] The device uses a built-in emotion engine to analyze the user's emotions in real time. This emotion engine uses a camera and microphone to capture the user's facial expressions and voice, and recognizes emotions using a machine learning model. Specifically, it uses OpenCV for facial expression recognition and a general speech recognition API for voice analysis. The input is the user's facial expression and voice data, and the output is recognized emotional information.

[0960] Step 5: Adjusting the staff according to your emotions

[0961] The server receives the emotion information sent from the device and adjusts the generated staff based on it. Specifically, it changes the tempo (for example, slowing down the tempo for sadness) or the pitch (for example, raising the pitch for joy). The input is an image file of the staff and the emotion information, and the output is an image file of the adjusted staff.

[0962] Step 6: Converting the music score format and final output

[0963] The user selects the desired music notation format (e.g., tablature, chord notation), and this information is sent to the server. The server converts the staff notation into the desired format and generates the final music notation. The generated music notation is again sent to the terminal as an image file, which the user can download and use to play an instrument, etc. The input is an image file of the adjusted music notation and the user's selection information, and the output is an image file of the music notation converted into the desired format.

[0964] (Application example 2)

[0965] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0966] Conventional audio data analysis systems have the ability to extract musical features and convert music into staff notation or other notation formats, but they are unable to adjust the music to reflect the user's emotions, making it difficult to provide emotional resonance with the user. Furthermore, in the case of advertising music, the effectiveness of advertising is limited because it is unable to generate optimal music based on the user's emotions. A system that can solve these problems and generate music based on the user's emotions is needed.

[0967] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0968] In this invention, the server includes means for receiving sound source data, means for analyzing the received sound source data and extracting musical features, means for generating staff notation based on the extracted musical features, means for converting the generated staff notation into a plurality of different musical notation formats, means for recognizing a user's emotion and adjusting the staff notation or other musical notation format based on the recognized emotion, and means for generating and providing the adjusted staff notation or other musical notation format as advertising music. This makes it possible to generate music that reflects the user's emotion, and to provide music that is optimal for advertising.

[0969] "Audio data" refers to digital data containing recorded music or audio, such as MP3 or WAV files.

[0970] "Musical features" are elements that represent the structure of music, and include information such as frequency, pitch, rhythm, and tempo.

[0971] A "staff" is a musical notation used to visually record music, and is used to express musical melodies and chords by arranging notes on five horizontal lines (staff).

[0972] A "music format" is a particular format or method for recording music, including, for example, staff notation, string notation, cultural notation, tablature, chord notation, etc.

[0973] "Emotion recognition" refers to determining a person's emotional state by analyzing their facial expressions, tone of voice, movements, or interaction data.

[0974] "Advertising music" is music created specifically for use in advertising, with the purpose of amplifying the appeal of a brand or product.

[0975] A "system" is an integrated framework that includes multiple components or modules that work in conjunction with each other to achieve a specific purpose.

[0976] The present invention is composed of a system that analyzes audio source data, generates musical notation, and converts it into multiple different musical notation formats, and adds an emotion engine that recognizes user emotions. This system is particularly useful in the advertising field, and can automatically generate advertising music that reflects the user's emotions.

[0977] Receiving and analyzing sound source data

[0978] A user selects audio data (e.g., MP3 or WAV files) using a terminal and uploads it to the server. The server receives the audio data and analyzes its musical characteristics (frequency, pitch, rhythm, tempo, etc.) using a library such as LibROSA.

[0979] Staff generation

[0980] The server generates a staff notation using the MusicXML format based on the extracted musical feature data, and the generated staff notation is sent to the terminal as an image file.

[0981] Recognizing user emotions with an emotion engine

[0982] The device uses an emotion engine to recognize the user's emotions. This emotion engine analyzes the user's facial expressions and tone of voice via a camera and microphone to determine emotions such as joy, sadness, and surprise.

[0983] Adjusting staff notation and music notation format according to emotions

[0984] The server receives the recognized user's emotion information and adjusts the generated staff notation or other musical notation format (e.g., string notation, cultural notation, tablature, chord notation, etc.) For example, if the user expresses joy, the tempo is increased and the pitch is increased.

[0985] Conversion and final output

[0986] The user selects the desired music notation format. Based on the selection and the recognized emotion information, the server converts the staff notation into another music notation format. The converted music notation is sent to the terminal again as an image file, and the user can view it and download it as needed. The converted music notation is used as advertising music.

[0987] Specific examples

[0988] When a user uploads an MP3 file of a piano performance to the server, the server analyzes the audio data and determines that it is in the key of C major and in 4 / 4 time. The generated staff is then sent to the device. The user reviews the staff, and the emotion engine recognizes the user's emotion (e.g., joy). Based on this emotion, the staff is adjusted to increase the tempo and pitch. The user selects conversion to tablature, and this information is sent to the server, and the converted tablature is sent to the device. Finally, the user can download the tablature and use it as advertising music.

[0989] Prompt Sentence Examples

[0990] "Analyze the following audio data, generate a musical score, and create advertising music tailored to the user's emotion, 'joy.' [Audio data file path: path_to_audio_file.mp3]"

[0991] The system of the present invention can analyze musical characteristics and convert music into various musical notation formats that take emotions into account efficiently and automatically, making it possible to provide music optimized for user emotions in the advertising field.

[0992] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0993] Step 1:

[0994] The user selects audio data using the device and uploads it to the server. To do this, the user selects the recorded MP3 or WAV file and presses the "Upload" button. The audio data file is the input, which is transferred to the server. The audio data is stored on the server as the output.

[0995] Step 2:

[0996] The audio data received by the server is analyzed using the LibROSA library. Specifically, the audio data is loaded and musical features such as frequency, pitch, rhythm, and tempo are extracted. In this process, the audio data is read using LibROSA's load function, and various features are extracted using the beat_track and piptrack functions. The audio data is input, and musical feature data (tempo, beat, pitch, etc.) is obtained as output.

[0997] Step 3:

[0998] The server generates a staff notation in MusicXML format based on the extracted musical feature data. Specifically, it uses the Music21 library to convert musical features (e.g., pitch and beat) into a staff notation. This process uses Music21's stream.Stream and note.Note to generate the staff notation. The input is musical feature data, and the output is staff notation data in MusicXML format.

[0999] Step 4:

[1000] The server sends the generated staff data to the device as an image file. Specifically, it converts the MusicXML format staff data into an image format (PNG or PDF) and transfers that file to the device. The staff data is input, and the image file is transferred to the device as output.

[1001] Step 5:

[1002] The device uses an emotion engine to recognize the user's emotions. Specifically, it uses a camera and microphone to analyze the user's facial expressions and voice in real time to identify emotions. In this process, an emotion recognition algorithm is used to analyze input audio and video data and output emotions such as joy, sadness, and surprise. The input is the user's audio and video data, and the output is recognized emotional data.

[1003] Step 6:

[1004] The server receives the recognized emotion information and adjusts the generated staff or other notation format. Specifically, it changes the tempo and adjusts the pitch based on the recognized emotion. This process uses an algorithm that changes the tempo and pitch of the staff based on the emotion data. The inputs are the recognized emotion data and staff data, and the output is the adjusted notation data.

[1005] Step 7:

[1006] The user selects the desired music notation format, and the server converts the staff notation into another music notation format based on the selection information and the recognized emotion information. Specifically, it converts it into the desired format (e.g., TAB notation, chord notation). In this process, the staff notation is converted using a music notation format conversion algorithm. The inputs are the staff notation data and the selection information, and the converted music notation data is obtained as the output.

[1007] Step 8:

[1008] The server then sends the converted music score data back to the terminal as an image file, which the user can then check and download. Specifically, the generated music score is converted into an image format and transferred to the terminal. The converted music score data is the input, and the image file is transferred to the terminal as the output.

[1009] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1010] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1011] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1012] [Fourth embodiment]

[1013] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1014] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1015] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1016] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1017] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1018] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1019] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1020] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1021] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1022] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1023] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1024] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1025] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1026] The system of this invention automates the process of receiving and analyzing audio data, generating musical notation based on its musical characteristics, and then converting the notation into multiple different notation formats. This system is primarily composed of three entities: a server, a terminal, and a user.

[1027] overview

[1028] A specific embodiment of the present invention will be described below. This system can be used in a variety of fields, including music education, music score production, and music analysis.

[1029] Receiving audio data

[1030] The user selects audio data (MP3, WAV, etc.) using their own device. This audio data is selected from the device's file system and uploaded to the server via the Internet. The server receives and stores this audio data, and then proceeds to the next analysis process.

[1031] Analysis of sound source data

[1032] To analyze the audio data inside the server, algorithms are used to extract musical features. Specific libraries include LibROSA and pydub. These libraries are used to extract musical features such as frequency, pitch, rhythm, and tempo from the audio data. These feature data are temporarily stored in memory or a database.

[1033] Staff generation

[1034] Based on the extracted musical feature data, the server generates a musical staff. In this process, pitch and rhythm information is arranged as staff data in a visually easy-to-understand format. Standard formats such as ABC notation or MusicXML format are commonly used. The generated musical staff is then sent to the terminal as an image file (e.g., PNG or SVG).

[1035] Selecting the music format

[1036] The user checks the staff notation displayed on the terminal and selects the desired notation format (string notation, bunka notation, tablature, chord notation). The selection information is sent from the terminal to the server.

[1037] Conversion to music notation format

[1038] Based on the selection information received from the user, the server converts the staff notation into other notation formats using corresponding algorithms, for example, conversion to tablature applies logic that maps pitch information to guitar frets and strings.

[1039] Providing converted scores

[1040] The converted music score is then sent to the device as an image file, where the user can view the converted music score on the device and download it if necessary.

[1041] Specific examples

[1042] For example, a user uploads an MP3 file recording of a piano performance to a server. The server analyzes the audio data and extracts that it is in the key of C major and in 4 / 4 time. Next, a musical staff is generated based on this information and sent to the device. The user confirms this and chooses to convert it to tablature. This information is sent to the server, and the musical staff is converted into tablature and sent to the device. The user can finally download this tablature and use it to play the instrument.

[1043] As described above, the system of the present invention efficiently and automatically converts sound source data into a variety of musical score formats.

[1044] The processing flow will be explained below.

[1045] Step 1:

[1046] The user selects the audio data (MP3, WAV, etc.) on the device. The user selects the audio file using the file selection dialog and presses the upload button.

[1047] Step 2:

[1048] The device uploads the selected audio data to the server. The audio file selected by the user is sent to the server via an HTTP request. The server receives it and stores it in a database or temporary storage.

[1049] Step 3:

[1050] The server reads the received audio data and begins analysis to extract musical characteristics. Specifically, the server uses music analysis libraries such as LibROSA and pydub to obtain data such as frequency, pitch, rhythm, and tempo.

[1051] Step 4:

[1052] The server generates a staff notation based on the extracted musical feature data. In this process, ABC notation or MusicXML format is used to visually arrange the scale and rhythm information as staff notation data. The generated staff notation data is temporarily saved in an internal format (such as JSON or XML).

[1053] Step 5:

[1054] The server converts the generated music sheet into an image file (such as PNG or SVG), which is then sent to the device as an HTTP response.

[1055] Step 6:

[1056] The terminal displays the image of the musical staff received from the server on the screen, and provides a user interface for the user to check the musical staff and select the desired musical notation format (string notation, Bunka notation, TAB notation, chord notation).

[1057] Step 7:

[1058] The user selects the desired music score format and sends the selected information to the server by pressing the send button on the terminal.

[1059] Step 8:

[1060] The terminal sends the user's selection information to the server. The information on the selected musical score format is sent to the server as an HTTP request.

[1061] Step 9:

[1062] The server converts the staff notation into a different notation format based on the selection information received from the user. In this process, the corresponding algorithm (e.g., staff notation to tablature conversion logic) is applied.

[1063] Step 10:

[1064] The server generates the converted score as an image file again, and sends the converted score image file to the terminal as an HTTP response.

[1065] Step 11:

[1066] The terminal displays the converted music score image received from the server on the screen, and the user is given the option to check it and download the image if necessary.

[1067] Step 12:

[1068] Users can download the converted music sheet images and use them for their own purposes.

[1069] Example 1

[1070] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1071] Conventional music data analysis and score generation systems do not automate the entire process, from analyzing audio data to converting it into multiple notation formats, and require the use of multiple software programs in combination. This forces users to perform complex operations, hindering efficient workflow. Furthermore, the accuracy of conversion between different notation formats is low, making it difficult to accurately reproduce musical nuances.

[1072] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1073] In this invention, the server includes means for receiving audio data, means for analyzing the received audio data and extracting musical features, means for generating staff notation based on the extracted musical features, means for converting the generated staff notation into a plurality of different musical notation formats, means for a user to use a terminal to select audio data and upload it to the server via the Internet, means for the server to save the audio data and extract musical features using a library, means for the server to generate staff notation based on the extracted musical features and send it to the terminal as an image file, means for a user to check the staff notation on the terminal and select a desired musical notation format, means for the server to receive the selection information and convert the staff notation into a different musical notation format, and means for sending the converted musical notation to the terminal as an image file. This makes it possible to centrally and automatically perform the entire process from receiving audio data to analyzing it, generating staff notation, converting it into a different musical notation format, and providing it to the terminal.

[1074] "Sound source data" refers to data that records music or audio information in digital or analog format.

[1075] The "receiving means" is a device or module for receiving sound source data from the outside.

[1076] "Analyzing means" refers to devices or software that perform processing to extract musical characteristics from sound source data.

[1077] "Musical features" are elements such as frequency, pitch, rhythm, and tempo contained in the sound source data.

[1078] "Extraction means" refers to devices or software that identify musical characteristics from sound source data and extract them as data.

[1079] "Staff notation" is a form of notation that visually represents musical features.

[1080] A "generating means" is a device or software for constructing a musical staff based on musical characteristics.

[1081] "Music formats" are different notation formats for musical instrument performance, including staff notation, tablature, cultural notation, string notation, chord notation, etc.

[1082] A "converting means" is a device or software that converts the original staff notation into another notation format.

[1083] A "terminal" is a device used by a user, such as a computer, smartphone, or tablet.

[1084] A "library" is a collection of existing programming tools and algorithms used for analysis and transformation.

[1085] A "user" is someone who uses this system to upload audio data and obtain the converted sheet music.

[1086] The "server" is a central control device that analyzes received sound source data, generates musical staves, and performs conversion processing.

[1087] MODE FOR CARRYING OUT THE INVENTION

[1088] The system of this invention automates the process of receiving and analyzing audio data, generating musical notation based on its musical characteristics, and then converting the notation into multiple different notation formats. This system is primarily composed of three entities: a server, a terminal, and a user.

[1089] Receiving audio data

[1090] The user selects audio data (MP3, WAV, etc.) using their own device. This is done by selecting an audio file from the device's file system. The selected audio data is then uploaded from the device to a server via the Internet, using a communication protocol such as an HTTP POST request. The server receives the audio data and saves it in a specified directory on the server.

[1091] Analysis of sound source data

[1092] The server analyzes the received audio data. This analysis uses libraries such as LibROSA and pydub to extract musical features. Specifically, the server loads the audio data into memory and uses LibROSA to extract musical features such as frequency, pitch, rhythm, and tempo. The extracted feature data is temporarily stored in the server's memory or database.

[1093] Staff generation

[1094] The server generates a musical staff based on the extracted musical feature data. In this process, the staff data is constructed using a standard format such as ABC notation or MusicXML format. The generated staff is exported to a visually easy-to-understand format and sent to the terminal as an image file (such as PNG or SVG).

[1095] Selecting the music format

[1096] The user checks the staff notation displayed on the terminal and selects the desired notation format (string notation, bunka notation, tablature, chord notation). The selected information is sent from the terminal to the server via an HTTP request.

[1097] Conversion to music notation format

[1098] The server converts the staff notation into other notation formats based on the user's selections (for example, tablature, which uses an algorithm to map pitch information to guitar frets and strings), and the converted notation is again generated as an image file.

[1099] Providing converted scores

[1100] The server sends the converted music score image file to the terminal, where the user can check the converted music score on the terminal and download it as needed.

[1101] Specific examples

[1102] For example, a user uploads an MP3 file recording a piano performance to a server. The server analyzes the audio data and determines that it is in the key of C major and in 4 / 4 time. Next, a musical staff is generated based on this information and sent to the device. The user confirms this and chooses to convert it to tablature. This information is sent to the server, and the musical staff is converted to tablature and sent to the device. The user can then download the tablature and use it to play their instrument.

[1103] Prompt Sentence Examples

[1104] The user uploads an MP3 file of their piano performance to the server, which analyzes the audio data to generate a 4 / 4 staff in the key of C major and converts it into tablature format.

[1105] As described above, the system of the present invention can centrally and automatically perform all processes from receiving sound source data to analyzing it, generating staff notation, and converting it into different musical notation formats and providing it.

[1106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1107] Step 1: Select and upload audio data

[1108] Input: The user selects audio data (MP3, WAV, etc.) using their own device (computer, smartphone, etc.).

[1109] Specific operation: The user opens a file selection dialog on the device and selects an audio file.

[1110] Output: The selected audio data is stored in the specified file path on the device.

[1111] Next process: The audio data is uploaded to the server.

[1112] Step 2: Upload the audio data

[1113] Input: User selected audio data.

[1114] What happens: The user clicks the upload button in their browser or application.

[1115] Output: The audio data is sent to the server via an HTTP POST request.

[1116] Next process: The server receives and stores the audio data.

[1117] Step 3: Receiving and saving audio data

[1118] Input: Audio data uploaded by users to the server.

[1119] Specific operation: The server receives an HTTP request and saves the audio data in a specific directory.

[1120] Output: Audio data stored in the file system.

[1121] Next process: The server prepares to analyze the sound source data.

[1122] Step 4: Loading the sound source data

[1123] Input: Audio data stored in the server's file system.

[1124] Specific operation: The server uses libraries such as LibROSA and pydub to load the audio data into memory.

[1125] Output: Sound source data loaded into memory.

[1126] Next process: Analyze the sound source data.

[1127] Step 5: Analyzing the sound source data

[1128] Input: Sound source data loaded into memory.

[1129] Specific operation: The server uses LibROSA to extract musical features such as frequency, pitch, rhythm, and tempo.

[1130] Output: Extracted musical feature data.

[1131] Next process: Save musical feature data and prepare for staff generation.

[1132] Step 6: Saving musical feature data

[1133] Input: Extracted musical feature data.

[1134] Specific operation: The server temporarily stores the feature data in memory or a database.

[1135] Output: Saved musical feature data.

[1136] Next step: Start the staff generation process.

[1137] Step 7: Generate the staff notation

[1138] Input: Stored musical feature data.

[1139] Specific operation: The server constructs staff data based on the musical feature data using a standard format such as ABC notation or MusicXML format.

[1140] Output: The generated musical staff.

[1141] Next process: Export the generated staff as an image file and send it to the user's device.

[1142] Step 8: Send and review the score

[1143] Input: The generated musical staff.

[1144] Specific operation: The server converts the generated staff into an image file in PNG or SVG format and sends it to the user's device as an HTTP response. The user then checks the staff on their device.

[1145] Output: A staff image displayed on the user's device.

[1146] Next process: The user selects the desired musical score format.

[1147] Step 9: Select the desired music format

[1148] Input: The staff displayed by the user.

[1149] Specific operation: The user selects the desired music notation format (e.g., tablature, bunka notation, string notation, chord notation) on the terminal using a pull-down menu or radio buttons.

[1150] Output: Selected music notation format information.

[1151] Next process: The selection information is sent from the terminal to the server.

[1152] Step 10: Converting the music format

[1153] Input: Selection information of musical score format received by the server.

[1154] What it does: The server uses the corresponding algorithm to convert the musical staff into the format of your choice, for example, to tablature, mapping pitch information to guitar frets and strings.

[1155] Output: The converted score.

[1156] Next process: Send the converted score to the user's terminal.

[1157] Step 11: Providing the converted score

[1158] Input: The converted score.

[1159] Specific operation: The server converts the converted score into an image file in PNG or SVG format and sends it to the user's device as an HTTP response. The user can check the converted score on their device and download it if necessary.

[1160] Output: The converted music score image displayed on the user's device.

[1161] Next process: The user downloads and uses the converted musical score.

[1162] (Application example 1)

[1163] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1164] In recent years, there has been a growing need in music education and music notation production to quickly and accurately convert audio files into sheet music. Furthermore, while it is necessary to provide different notation formats for different instruments and purposes, the reality is that this conversion process takes a great deal of time and effort. Furthermore, there is a need for on-site visual confirmation of sheet music and real-time conversion into different notation formats, but current systems face challenges that make this difficult.

[1165] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1166] In this invention, the server includes means for receiving audio data, means for analyzing the audio data and extracting musical features, means for generating musical notation based on the extracted musical features, means for converting the generated musical notation into a plurality of different musical notation formats, means for displaying the generated musical notation on a visual device in real time, and means for allowing a user to select a desired musical notation format and for instantly converting and displaying the musical notation into a different musical notation format based on the user's selection. This automates the generation of musical notation from audio data and the conversion into different musical notation formats, making it possible to check and operate the musical notation in real time through the visual device.

[1167] "Audio data" refers to information that records music or sound in digital or analog format.

[1168] "Musical features" are musical components such as frequency, pitch, rhythm, and tempo extracted from sound source data.

[1169] A musical staff is a sheet of music consisting of five lines used to write musical melodies and chords.

[1170] "Music format" refers to different notation methods for writing musical scores, such as staff notation, tablature, and cultural notation.

[1171] A "visual device" is a device that allows users to visually confirm information, and specifically includes smart glasses and head-mounted displays.

[1172] "Real-time display" is a function that displays the results of data processing immediately after it is performed.

[1173] The "selection means" is a means by which a user selects a desired option from multiple options.

[1174] "Instant conversion" refers to the rapid conversion of data formats based on user instructions or selections, without delay.

[1175] A specific embodiment of the present invention will be described below. The system has the functions of receiving and analyzing audio source data, generating musical staves, instantly converting them into different musical notation formats, and displaying them on a visual device in real time.

[1176] Receiving audio data

[1177] The user selects audio data (MP3, WAV, etc.) using their own device. The audio data is selected from the device's file system and uploaded to the server via the Internet. The server receives and stores this audio data and proceeds to the next analysis process.

[1178] Analysis of sound source data

[1179] To analyze the audio data inside the server, algorithms are used to extract musical features. Specific libraries include LibROSA and pydub. These libraries are used to extract musical features such as frequency, pitch, rhythm, and tempo from the audio data. These feature data are temporarily stored in memory or a database.

[1180] Staff generation

[1181] The server generates a staff based on the extracted musical feature data. In this process, pitch and rhythm information is arranged as staff data in a visually easy-to-understand format. Standard formats such as ABC notation or MusicXML are commonly used. The generated staff is then sent to the terminal as an image file (e.g., PNG or SVG).

[1182] Selecting and converting music notation formats

[1183] The user checks the staff notation displayed on the device and selects the desired notation format (e.g., tablature). The selection information is sent from the device to the server. The server converts the staff notation into another notation format based on the selection information received from the user. This process uses corresponding algorithms. For example, conversion to tablature applies logic that maps pitch information to guitar frets and strings.

[1184] Real-time display of generated music scores

[1185] The generated score is displayed in real time on a visual device (e.g., smart glasses or a head-mounted display), allowing the user to check the score and continue playing as needed.

[1186] Specific examples

[1187] For example, a user uploads audio data of a performance on an electronic piano. The audio data is analyzed by the server and determined to be in the key of C major and in 4 / 4 time. A staff notation is then generated based on this information and displayed on the user's visual device. If the user selects conversion to tablature, the information is sent to the server, and the staff notation is converted to tablature and displayed instantly on the visual device. The user can then continue playing the instrument using the tablature.

[1188] Prompt Sentence Examples

[1189] "Please receive audio played on an electronic piano via the Internet, analyze it in real time, and display it as musical notation. Furthermore, please create a system that can convert and display the music notation on the spot when the user selects a desired notation format (e.g., tablature)."

[1190] In this way, the system of the present invention efficiently and automatically converts audio data into various musical score formats, and realizes real-time display through a visual device.

[1191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1192] Step 1: Receiving audio data

[1193] A user selects audio data (MP3, WAV, etc.) using their own device. The selected audio data is uploaded to a server via the Internet. The server receives and stores this audio data. The input is the audio data file, and the output is the audio data stored on the server.

[1194] Step 2: Analyzing the sound source data

[1195] The server analyzes the received audio data. Using libraries such as LibROSA or pydub, it extracts musical features such as frequency, pitch, rhythm, and tempo from the audio data. The extracted feature data is temporarily stored in memory or a database. The input is the audio data, and the output is musical feature data.

[1196] Step 3: Generate the staff notation

[1197] The server generates a staff notation based on the analyzed musical feature data. Using a library such as Music21, pitch and rhythm information is arranged as staff notation data in a visually easy-to-understand format. The generated staff notation data is output as an image file (such as PNG or SVG). The input is musical feature data, and the output is an image file of the staff notation.

[1198] Step 4: Select the music format

[1199] The user checks the staff displayed on the terminal and selects the desired music notation format. This selection information is sent from the user to the server via the terminal. The input is the staff image file and the user's selection information, and the output is the selection information sent to the server.

[1200] Step 5: Converting to music notation format

[1201] The server converts the staff notation into other notation formats based on the selections received from the user. For conversion to tablature and other notation formats, logic is applied to map the pitch information to the appropriate instrument frets and strings. The input is an image file of the staff notation and the selections, and the output is an image file of the different notation formats.

[1202] Step 6: Real-time display

[1203] The server displays the generated musical score in real time on a visual device (such as smart glasses or a head-mounted display). The user can check the score through this device and continue playing if necessary. The input is image files in different musical score formats, and the output is the musical score displayed on the visual device.

[1204] This allows users to generate sheet music from audio data, convert it into the desired notation format, and check it in real time. Through the specific operations and data flow, users can clearly understand how the entire system works.

[1205] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1206] This invention combines a system that analyzes audio data to generate musical notation and converts the notation into multiple different musical notation formats with an emotion engine that recognizes the user's emotions. This system can provide musical notation that reflects the user's emotions in music education, music notation production, and music analysis.

[1207] overview

[1208] A specific embodiment of the present invention will be described below. This system is configured by adding an emotion engine to three main entities: a server, a terminal, and a user.

[1209] Receiving and analyzing sound source data

[1210] The user selects audio data (MP3, WAV, etc.) using a device. This audio data is selected on the device and uploaded to a server via the Internet. Once the server receives the audio data, it begins processing to analyze its musical features. This analysis uses libraries such as LibROSA and pydub to extract musical features such as frequency, pitch, rhythm, and tempo.

[1211] Staff generation

[1212] The server generates a musical staff based on the extracted musical feature data. It uses ABC notation or MusicXML format to visually arrange pitch and rhythm information. The generated musical staff is sent to the device as an image file.

[1213] Recognizing user emotions with an emotion engine

[1214] The device recognizes the user's emotions using an emotion engine. This emotion engine includes algorithms that analyze emotions from the user's voice, facial expressions, input content, etc. For example, it can recognize emotions such as joy, sadness, and surprise by analyzing the user's facial expressions and tone of voice through a camera or microphone.

[1215] Adjusting staff notation and music notation format according to emotions

[1216] The server receives the recognized user emotion information and adjusts the generated staff notation or any other notation format (string notation, music notation, tablature, chord notation), including changing the pitch and tempo, for example, if the user expresses sadness, slow down the tempo and change to a lower pitch.

[1217] Conversion and final output

[1218] The user selects the desired music notation format, and the server converts the staff notation into another music notation format based on the user's selection and the recognized emotion information. The converted music notation is then sent to the terminal as an image file, where the user can view it and download it if necessary.

[1219] Specific examples

[1220] For example, a user uploads an MP3 file recording a piano performance to the server. The server analyzes this audio data and extracts that it is in the key of C major and in 4 / 4 time. The generated staff is then sent to the device. The user reviews this staff, and the emotion engine recognizes the user's emotion (e.g., joy). Based on this emotion, the staff is adjusted to increase the tempo and pitch. The user then selects conversion to TAB notation, and this information is sent to the server, and the converted TAB is sent to the device. Finally, the user can download this TAB and use it to play an instrument.

[1221] As described above, the system of the present invention efficiently and automatically converts sound source data into a variety of musical score formats that take emotion into consideration.

[1222] The processing flow will be explained below.

[1223] Step 1:

[1224] The user selects the audio data (MP3, WAV, etc.) on the device. The user selects the audio file using the file selection dialog and presses the upload button.

[1225] Step 2:

[1226] The device uploads the selected audio data to the server. The audio file selected by the user is sent to the server via an HTTP request. The server receives it and stores it in a database or temporary storage.

[1227] Step 3:

[1228] The server reads the received audio data and begins analysis to extract musical characteristics. Specifically, the server uses music analysis libraries such as LibROSA and pydub to obtain data such as frequency, pitch, rhythm, and tempo.

[1229] Step 4:

[1230] The server generates a staff notation based on the extracted musical feature data. In this process, ABC notation or MusicXML format is used to visually arrange the scale and rhythm information as staff notation data. The generated staff notation data is temporarily stored in memory or a database.

[1231] Step 5:

[1232] The server converts the generated music sheet into an image file (such as PNG or SVG), which is then sent to the device as an HTTP response.

[1233] Step 6:

[1234] The device displays the image of the musical staff received from the server on the screen. The user confirms it, and the emotion engine begins preparations to recognize the user's emotions.

[1235] Step 7:

[1236] To recognize the user's emotions, the device uses a camera and microphone to collect the user's facial expressions and voice. The emotion engine analyzes this data and recognizes the user's emotions.

[1237] Step 8:

[1238] The device sends the recognized emotion information to the server, which is then sent as an HTTP request.

[1239] Step 9:

[1240] The server receives the emotion information and makes adjustments to the generated musical staff or other notation format, for example, lowering the pitch and slowing the tempo if sadness is recognized.

[1241] Step 10:

[1242] The user selects the desired music notation format, and the selected information and adjusted staff data are sent to the server.

[1243] Step 11:

[1244] Based on the selected notation format, the server converts the adjusted staff notation into other different notation formats (string notation, bunka notation, tablature, chord notation), using corresponding algorithms in this process.

[1245] Step 12:

[1246] The server generates the converted music score as an image file and sends it to the terminal as an HTTP response.

[1247] Step 13:

[1248] The terminal displays the converted music score image received from the server on the screen, and provides the user with the option to check it and download the image if necessary.

[1249] Step 14:

[1250] Users can download the converted music sheet images and use them for their own purposes.

[1251] Example 2

[1252] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1253] While existing audio data analysis systems can extract musical features and generate musical scores, they lack the ability to adjust the scores to reflect the user's emotions, making it difficult to improve the emotional expressiveness of the scores and the satisfaction of the score users. For this reason, there is a demand for systems with more advanced functions that reflect the user's emotions in the fields of music education, sheet music production, and music analysis.

[1254] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1255] In this invention, the server includes means for receiving sound source data, means for analyzing the received sound source data and extracting musical features, means for generating a staff based on the extracted musical features, means for adjusting the staff generated by the staff generating means based on user emotion information, means for converting the adjusted staff into a plurality of different music notation formats, and means for transmitting the output from the means for converting into a plurality of different music notation formats to a user terminal. This makes it possible to reflect the user's emotions in the musical score generated from the sound source data and provide more expressive music notation.

[1256] "Audio data" refers to music or audio data recorded in digital or analog format.

[1257] "Means for receiving" refers to a mechanism, method, or technology for capturing audio source data into a particular location or system.

[1258] "Means for analyzing and extracting musical features" refers to methods and techniques for identifying and extracting specific musical elements such as frequency, pitch, rhythm, and tempo from audio source data.

[1259] "Means for generating musical staff notation" refers to a method or technology for converting extracted musical features into a musical staff notation format to visually represent the musical pitch, rhythm, and tempo.

[1260] "Emotional information" refers to data on the user's emotional state analyzed from their voice, facial expressions, input, etc.

[1261] "Adjustment means" refers to techniques or methods for changing the pitch, tempo, rhythm, etc. of an existing musical staff based on recognized emotional information.

[1262] "Means for converting into multiple different notation formats" refers to techniques and methods for converting staff notation format data into other formats (e.g., string notation, bunka notation, tablature, chord notation).

[1263] "Transmission means" refers to the method or technology for transferring the generated or converted music score data to the user's terminal.

[1264] "Terminal" means a computer system or device operated by a user to select and upload audio data or to receive final score data.

[1265] This invention combines a system that analyzes audio data to generate musical notation and converts the musical notation into multiple different notation formats with an emotion engine that recognizes the user's emotions. This system can provide musical notation that reflects the user's emotions in music education, music notation production, and music analysis.

[1266] The system's components mainly include a server, a terminal, a user, and an emotion engine. A specific embodiment of this system will be described in detail below.

[1267] Selecting and uploading audio data

[1268] The user selects audio data (MP3 or WAV format) from the local disk using the device's file selection function. The selected audio data is then uploaded to the server via the Internet using an HTTP POST request.

[1269] Analysis of sound source data

[1270] After receiving the uploaded audio data, the server analyzes the musical characteristics using music analysis libraries such as LibROSA and pydub. Specifically, it performs frequency spectrum analysis, pitch detection, rhythm extraction, and tempo calculation. The analysis results are saved in JSON format and used in the next step.

[1271] Staff generation

[1272] The server generates a musical staff using ABC notation or MusicXML based on the analyzed musical feature data. At this stage, pitch and rhythm information is converted into visual symbols and expressed as musical notation. The generated musical staff is converted into an image file (PNG or SVG format) and sent to the device.

[1273] Emotion recognition by emotion engine

[1274] The device uses a built-in emotion engine to analyze the user's emotions in real time. This emotion engine uses a camera and microphone to capture the user's facial expressions and voice, and then uses machine learning models to recognize emotions. OpenCV is used for facial recognition, and a general speech recognition API is used for voice analysis.

[1275] Emotional adjustment of the musical staff

[1276] The server receives the emotion information sent from the device and adjusts the music score accordingly. For example, if the user expresses sadness, the server slows down the tempo and lowers the pitch.

[1277] Musical score format conversion and final output

[1278] The user selects the desired music notation format (e.g., tablature, chord notation), and the information is sent to the server. The server converts the staff notation into the desired format and generates the final music notation. The converted music notation is then resent to the device as an image file, which the user can download and use to play the instrument.

[1279] Specific examples

[1280] For example, a user uploads an MP3 file recording of themselves playing the piano to a server. The server analyzes this audio data and extracts that it is in the key of C major and in 4 / 4 time. The generated staff is sent to the device, where the user can review it. The emotion engine recognizes the user's emotion (e.g., joy), and adjusts the staff to speed up the tempo and raise the pitch based on this emotion. The user selects conversion to tablature, and this information is sent to the server, and the converted tablature is sent to the device. Finally, the user can download the tablature and use it to play an instrument.

[1281] In this way, the present invention can reflect the user's emotions in the musical score generated from the sound source data, thereby providing a more expressive score.

[1282] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1283] Step 1: Select and upload audio data

[1284] The user uses the file selection function of the device to select audio data (MP3 or WAV format) from the local disk. After this audio data is selected, it is uploaded to the server using an HTTP POST request. Specifically, the selected file is attached to the submission form and the audio data is sent to the server by clicking the submit button. The input is the file path of the audio data, and the output is the audio data saved on the server.

[1285] Step 2: Analyzing the sound source data

[1286] After receiving the uploaded audio data, the server analyzes the musical features using music analysis libraries such as LibROSA and pydub. Specifically, it performs frequency spectrum analysis (FFT), pitch tracking, beat detection, and tempo estimation. The input is the audio data stored on the server, and the output is JSON-formatted data containing the musical features.

[1287] Step 3: Generate the staff notation

[1288] The server generates a staff using ABC notation or MusicXML based on the analyzed musical feature data. Specifically, it converts the extracted pitch information into musical notes on a staff, and visually arranges the rhythm information as rhythm symbols. The generated staff is converted into an image file (PNG or SVG format) and sent to the device. The input is JSON data containing the musical features, and the output is an image file of the generated staff.

[1289] Step 4: Emotion Recognition with the Emotion Engine

[1290] The device uses a built-in emotion engine to analyze the user's emotions in real time. This emotion engine uses a camera and microphone to capture the user's facial expressions and voice, and recognizes emotions using a machine learning model. Specifically, it uses OpenCV for facial expression recognition and a general speech recognition API for voice analysis. The input is the user's facial expression and voice data, and the output is recognized emotional information.

[1291] Step 5: Adjusting the staff according to your emotions

[1292] The server receives the emotion information sent from the device and adjusts the generated staff based on it. Specifically, it changes the tempo (for example, slowing down the tempo for sadness) or the pitch (for example, raising the pitch for joy). The input is an image file of the staff and the emotion information, and the output is an image file of the adjusted staff.

[1293] Step 6: Converting the music score format and final output

[1294] The user selects the desired music notation format (e.g., tablature, chord notation), and this information is sent to the server. The server converts the staff notation into the desired format and generates the final music notation. The generated music notation is again sent to the terminal as an image file, which the user can download and use to play an instrument, etc. The input is an image file of the adjusted music notation and the user's selection information, and the output is an image file of the music notation converted into the desired format.

[1295] (Application example 2)

[1296] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1297] Conventional audio data analysis systems have the ability to extract musical features and convert music into staff notation or other notation formats, but they are unable to adjust the music to reflect the user's emotions, making it difficult to provide emotional resonance with the user. Furthermore, in the case of advertising music, the effectiveness of advertising is limited because it is unable to generate optimal music based on the user's emotions. A system that can solve these problems and generate music based on the user's emotions is needed.

[1298] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1299] In this invention, the server includes means for receiving sound source data, means for analyzing the received sound source data and extracting musical features, means for generating staff notation based on the extracted musical features, means for converting the generated staff notation into a plurality of different musical notation formats, means for recognizing a user's emotion and adjusting the staff notation or other musical notation format based on the recognized emotion, and means for generating and providing the adjusted staff notation or other musical notation format as advertising music. This makes it possible to generate music that reflects the user's emotion, and to provide music that is optimal for advertising.

[1300] "Audio data" refers to digital data containing recorded music or audio, such as MP3 or WAV files.

[1301] "Musical features" are elements that represent the structure of music, and include information such as frequency, pitch, rhythm, and tempo.

[1302] A "staff" is a musical notation used to visually record music, and is used to express musical melodies and chords by arranging notes on five horizontal lines (staff).

[1303] A "music format" is a particular format or method for recording music, including, for example, staff notation, string notation, cultural notation, tablature, chord notation, etc.

[1304] "Emotion recognition" refers to determining a person's emotional state by analyzing their facial expressions, tone of voice, movements, or interaction data.

[1305] "Advertising music" is music created specifically for use in advertising, with the purpose of amplifying the appeal of a brand or product.

[1306] A "system" is an integrated framework that includes multiple components or modules that work in conjunction with each other to achieve a specific purpose.

[1307] The present invention is composed of a system that analyzes audio source data, generates musical notation, and converts it into multiple different musical notation formats, and adds an emotion engine that recognizes user emotions. This system is particularly useful in the advertising field, and can automatically generate advertising music that reflects the user's emotions.

[1308] Receiving and analyzing sound source data

[1309] A user selects audio data (e.g., MP3 or WAV files) using a terminal and uploads it to the server. The server receives the audio data and analyzes its musical characteristics (frequency, pitch, rhythm, tempo, etc.) using a library such as LibROSA.

[1310] Staff generation

[1311] The server generates a staff notation using the MusicXML format based on the extracted musical feature data, and the generated staff notation is sent to the terminal as an image file.

[1312] Recognizing user emotions with an emotion engine

[1313] The device uses an emotion engine to recognize the user's emotions. This emotion engine analyzes the user's facial expressions and tone of voice via a camera and microphone to determine emotions such as joy, sadness, and surprise.

[1314] Adjusting staff notation and music notation format according to emotions

[1315] The server receives the recognized user's emotion information and adjusts the generated staff notation or other musical notation format (e.g., string notation, cultural notation, tablature, chord notation, etc.) For example, if the user expresses joy, the tempo is increased and the pitch is increased.

[1316] Conversion and final output

[1317] The user selects the desired music notation format. Based on the selection and the recognized emotion information, the server converts the staff notation into another music notation format. The converted music notation is sent to the terminal again as an image file, and the user can view it and download it as needed. The converted music notation is used as advertising music.

[1318] Specific examples

[1319] When a user uploads an MP3 file of a piano performance to the server, the server analyzes the audio data and determines that it is in the key of C major and in 4 / 4 time. The generated staff is then sent to the device. The user reviews the staff, and the emotion engine recognizes the user's emotion (e.g., joy). Based on this emotion, the staff is adjusted to increase the tempo and pitch. The user selects conversion to tablature, and this information is sent to the server, and the converted tablature is sent to the device. Finally, the user can download the tablature and use it as advertising music.

[1320] Prompt Sentence Examples

[1321] "Analyze the following audio data, generate a musical score, and create advertising music tailored to the user's emotion, 'joy.' [Audio data file path: path_to_audio_file.mp3]"

[1322] The system of the present invention can analyze musical characteristics and convert music into various musical notation formats that take emotions into account efficiently and automatically, making it possible to provide music optimized for user emotions in the advertising field.

[1323] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1324] Step 1:

[1325] The user selects audio data using the device and uploads it to the server. To do this, the user selects the recorded MP3 or WAV file and presses the "Upload" button. The audio data file is the input, which is transferred to the server. The audio data is stored on the server as the output.

[1326] Step 2:

[1327] The audio data received by the server is analyzed using the LibROSA library. Specifically, the audio data is loaded and musical features such as frequency, pitch, rhythm, and tempo are extracted. In this process, the audio data is read using LibROSA's load function, and various features are extracted using the beat_track and piptrack functions. The audio data is input, and musical feature data (tempo, beat, pitch, etc.) is obtained as output.

[1328] Step 3:

[1329] The server generates a staff notation in MusicXML format based on the extracted musical feature data. Specifically, it uses the Music21 library to convert musical features (e.g., pitch and beat) into a staff notation. This process uses Music21's stream.Stream and note.Note to generate the staff notation. The input is musical feature data, and the output is staff notation data in MusicXML format.

[1330] Step 4:

[1331] The server sends the generated staff data to the device as an image file. Specifically, it converts the MusicXML format staff data into an image format (PNG or PDF) and transfers that file to the device. The staff data is input, and the image file is transferred to the device as output.

[1332] Step 5:

[1333] The device uses an emotion engine to recognize the user's emotions. Specifically, it uses a camera and microphone to analyze the user's facial expressions and voice in real time to identify emotions. In this process, an emotion recognition algorithm is used to analyze input audio and video data and output emotions such as joy, sadness, and surprise. The input is the user's audio and video data, and the output is recognized emotional data.

[1334] Step 6:

[1335] The server receives the recognized emotion information and adjusts the generated staff or other notation format. Specifically, it changes the tempo and adjusts the pitch based on the recognized emotion. This process uses an algorithm that changes the tempo and pitch of the staff based on the emotion data. The inputs are the recognized emotion data and staff data, and the output is the adjusted notation data.

[1336] Step 7:

[1337] The user selects the desired music notation format, and the server converts the staff notation into another music notation format based on the selection information and the recognized emotion information. Specifically, it converts it into the desired format (e.g., TAB notation, chord notation). In this process, the staff notation is converted using a music notation format conversion algorithm. The inputs are the staff notation data and the selection information, and the converted music notation data is obtained as the output.

[1338] Step 8:

[1339] The server then sends the converted music score data back to the terminal as an image file, which the user can then check and download. Specifically, the generated music score is converted into an image format and transferred to the terminal. The converted music score data is the input, and the image file is transferred to the terminal as the output.

[1340] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1341] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1342] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1343] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1344] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1345] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1346] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1347] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1348] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1349] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1350] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1351] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1352] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1353] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1354] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1355] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1356] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1357] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1358] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1359] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1360] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1361] The following is further disclosed regarding the above embodiment.

[1362] (Claim 1)

[1363] means for receiving sound source data;

[1364] means for analyzing the received sound source data and extracting musical features;

[1365] means for generating a musical staff based on the extracted musical features;

[1366] The system includes means for converting the generated musical staff into a number of different notation formats.

[1367] (Claim 2)

[1368] 10. The system of claim 1, wherein the means for analyzing the sound source data uses frequency spectrum analysis.

[1369] (Claim 3)

[1370] 2. The system of claim 1, wherein the plurality of different musical notation formats include string notation, cultural notation, tablature, and chord notation.

[1371] "Example 1"

[1372] (Claim 1)

[1373] means for receiving sound source data;

[1374] means for analyzing the received sound source data and extracting musical features;

[1375] means for generating a musical staff based on the extracted musical features;

[1376] a means for converting the generated staff notation into a plurality of different notation formats;

[1377] A means for a user to select sound source data using a terminal and upload the data to a server via the Internet;

[1378] a server storing the sound source data and extracting musical features using the library;

[1379] A means for the server to generate a staff notation based on the extracted musical features and transmit it to the terminal as an image file;

[1380] A means for the user to check the staff notation on the terminal and select the desired music notation format;

[1381] a server receiving the selection information and converting the staff notation into a different notation format;

[1382] A means to send the converted score to the device as an image file

[1383] A system including:

[1384] (Claim 2)

[1385] 10. The system of claim 1, wherein the means for analyzing the sound source data uses frequency spectrum analysis.

[1386] (Claim 3)

[1387] 2. The system of claim 1, wherein the plurality of different musical notation formats include string notation, cultural notation, tablature, and chord notation.

[1388] "Application Example 1"

[1389] (Claim 1)

[1390] means for receiving sound source data;

[1391] means for analyzing the received sound source data and extracting musical features;

[1392] means for generating a musical staff based on the extracted musical features;

[1393] a means for converting the generated staff notation into a plurality of different notation formats;

[1394] a means for displaying the generated musical score on a visual device in real time;

[1395] A system including a means for a user to select a desired musical notation format and instantly convert and display the musical notation format into a different musical notation format based on the selection.

[1396] (Claim 2)

[1397] 10. The system of claim 1, wherein the means for analyzing the sound source data uses frequency spectrum analysis.

[1398] (Claim 3)

[1399] 2. The system of claim 1, wherein the plurality of different musical notation formats include string notation, cultural notation, tablature, and chord notation.

[1400] "Example 2: Combining Emotion Engines"

[1401] (Claim 1)

[1402] means for receiving sound source data;

[1403] means for analyzing the received sound source data and extracting musical features;

[1404] means for generating a musical staff based on the extracted musical features;

[1405] A means for adjusting the staff notation generated by the means for generating the staff notation based on the emotional information of the user;

[1406] means for converting the adjusted staff into a plurality of different notation formats;

[1407] The system includes a means for transmitting the output from the means for converting into a plurality of different musical score formats to a user terminal.

[1408] (Claim 2)

[1409] 2. The system of claim 1, wherein the means for analyzing the sound source data and extracting musical features uses frequency spectrum analysis.

[1410] (Claim 3)

[1411] 2. The system of claim 1, wherein the means for converting the staff notation into a plurality of different notation formats includes string notation, cultural notation, tablature, and chord notation.

[1412] "Application example 2 when combining emotion engines"

[1413] (Claim 1)

[1414] means for receiving sound source data;

[1415] means for analyzing the received sound source data and extracting musical features;

[1416] means for generating a musical staff based on the extracted musical features;

[1417] a means for converting the generated staff notation into a plurality of different notation formats;

[1418] means for recognizing a user's emotion and adjusting the staff or other musical notation format based on the recognized emotion;

[1419] A system including means for generating and providing tuned musical staves or other musical notation formats as advertising music.

[1420] (Claim 2)

[1421] 10. The system of claim 1, wherein the means for analyzing the sound source data uses frequency spectrum analysis.

[1422] (Claim 3)

[1423] 2. The system of claim 1, wherein the plurality of different musical notation formats include string notation, cultural notation, tablature, and chord notation. [Explanation of symbols]

[1424] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving sound source data; means for analyzing the received sound source data and extracting musical features; means for generating a musical staff based on the extracted musical features; The system includes means for converting the generated musical staff into a number of different notation formats.

2. 2. The system of claim 1, wherein the means for analyzing the sound source data uses frequency spectrum analysis.

3. 2. The system of claim 1, wherein the plurality of different musical notation formats include string notation, cultural notation, tablature, and chord notation.

Images