Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

149 results about "Musical composition" patented technology

Musical composition, music composition, or simply composition, can refer to an original piece or work of music , either vocal or instrumental, the structure of a musical piece, or to the process of creating or writing a new piece of music. People who create new compositions are called composers. Composers of primarily songs are usually called songwriters; with songs, the person who writes lyrics for a song is the lyricist. In many cultures, including Western classical music, the act of composing typically includes the creation of music notation, such as a sheet music "score," which is then performed by the composer or by other instrumental musicians or singers. In popular music and traditional music, songwriting may involve the creation of a basic outline of the song, called the lead sheet, which sets out the melody, lyrics and chord progression. In classical music, orchestration (choosing the instruments of a large music ensemble such as an orchestra which will play the different parts of music, such as the melody, accompaniment, countermelody, bassline and so on) is typically done by the composer, but in musical theatre and in pop music, songwriters may hire an arranger to do the orchestration. In some cases, a pop or traditional songwriter may not use written notation at all, and instead compose the song in their mind and then play, sing and/or record it from memory. In jazz and popular music, notable sound recordings by influential performers are given the weight that written or printed scores play in classical music.

Music generation method and device based on knowledge graph, equipment and medium

The invention relates to the technical field of natural language processing and medical treatment, can be applied to scenes of daily music creation, psychological medical treatment and the like, and discloses a knowledge graph-based music generation method, device and equipment and a medium, and the method comprises the steps: obtaining demand information, analyzing the demand information according to a preset knowledge graph to construct knowledge connotation mapping, generating a music constraint condition according to the knowledge connotation mapping; generating melody, rhythm and harmony based on the music constraint conditions; and performing music fusion on the melody, the rhythm and the harmony to generate a target music work. Music can be automatically generated, and the creation requirement of a user for a specific music type is met.
Owner:PING AN TECH (SHENZHEN) CO LTD

Artificial intelligence-powered music registry, collaboration, and workflow management system

An AI-powered music registry, collaboration, and workflow management platform that addresses the challenges faced by music industry participants in the digital age. The system comprises a segmentation and hashing subsystem for musical pieces, segments, and isolated elements, enabling the evaluation of uniqueness and the consideration of individual creators' contributions. An artificial intelligence (AI) and machine learning (ML) subsystem is employed for extracting and isolating individual instruments, vocals, and performer contributions, while a component-level tracking module enables enhanced crediting and royalty distribution.
Owner:QOMPLX INC

Real-time generation method and device for dance score

The embodiment of the invention provides a real-time generation method and device for dance score. The method comprises the following steps: capturing a real-time picture of a human body action, and analyzing dance visual information and scene information in the real-time picture of the human body action; performing human body action information extraction and facial expression analysis on the dance visual information to obtain human body posture characteristic parameters, and generating real-time music attribute information according to the human body posture characteristic parameters and scene information; and taking the music attribute information as node features in the music and / or graph, sampling the music and / or graph, and generating real-time dance score. According to the real-time generation method and device of the dance score, the score does not need to be generated according to a completed dance video, and music creation can be completed while a user dance, so that the user has double copyrights of the dance and music works.
Owner:BEIJING INSTITUTE FOR GENERAL ARTIFICIAL INTELLIGENCE

Machine-Learned Models for Generation of Musical Accompaniments Based on Input Vocals

Training data comprising a plurality of training pairs is obtained. Each training pair comprises instrumental audio data and vocal audio data separated from audio data of a musical work of a respective plurality of musical works. For one or more training pairs of the plurality of training pairs, the vocal audio data is processed with machine-learned model(s) of a machine-learned generative audio model grouping to obtain a vocal intermediate representation for the vocal audio data. The instrumental audio data is processed with a pre-trained encoding model to obtain an instrumental intermediate representation for the instrumental audio data. A loss function is evaluated that evaluates a difference between the vocal intermediate representation and the instrumental intermediate representation. Values of parameters of a machine-learned model of the machine-learned generative audio model grouping are modified based on the loss function.
Owner:GOOGLE LLC

Music work automatic classification method and system

The invention relates to the technical field of music information retrieval, in particular to an automatic classification method and system for music works, and the method comprises the following steps: based on the classification standard of music genre, analyzing the hierarchical node relationship of the music genre, extracting the corresponding hierarchical characteristics of the large class and the small class of the genre, identifying the association proportion between each hierarchy, and analyzing the hierarchical connection strength. And generating a music genre level weight table. According to the method, through deep analysis of a music genre hierarchical structure, finer and dynamic classification of music works is realized, the classification accuracy and flexibility are significantly improved, through extraction of hierarchical features and revelation of association between hierarchies, music classification not only breaks through limitation of simple labeling, but also can reflect hierarchical relationships between genre, and the classification efficiency is improved. The chord change rule and amplitude are extracted, the dynamic capture of music features is enhanced, the association of chord change and genre level features is matched, the classification weight is dynamically adjusted, genre features are accurately matched, and the diversity and complexity of music creation are better adapted.
Owner:HEBEI XIAOLONG TECH CO LTD

Music generation method and device, electronic equipment and storage medium

The invention provides a music generation method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring a lyric text to be converted and a reference audio; mapping the reference audio to a potential space from an original audio space to obtain a first audio feature; based on a diffusion model acting on the potential space, performing multi-step noise adding processing on the first audio feature to obtain a noise feature; under the condition that preconditions are given, multi-step denoising processing is carried out on the noise features based on a diffusion model, and second audio features are obtained; wherein the precondition is related to the total duration of the lyric text and the reference audio; and mapping the second audio feature from the potential space to the original audio space to obtain a music work for singing the lyric text. The user input in the music generation process is simplified, and the music generation efficiency is improved.
Owner:BEIJING DAJIA INTERNET INFORMATION TECH CO LTD

Song poem music restoration model construction method and device

The invention discloses a Song poem music restoration model construction method and device. The construction method comprises the following steps: constructing a Song poem music data set; the Song poem music restoration model comprises a lyric-to-melody generation module which is used for generating melody according to input Song poems; the melody-to-aclasas generation module is used for generating an aclasas according to the melody; the melody-to-accompaniment generation module is used for generating an accompaniment according to the melody; the merging and restoring module is used for merging the melody, the unsold singing and the accompaniment to generate a complete music work; and training the constructed Song poem music restoration model by using the Song poem music data set to obtain a trained Song poem music restoration model. Compared with the prior art, high-quality restoration of the Song poem music is realized.
Owner:WUHAN UNIV

Generating audio-based musical content and / or audio-visual-based musical content using generative model(s)

Implementations relate to utilizing generative model(s) (GM(s)) to generate musical content that includes at least lyrical content and music composition content. Processor(s) of a system can: receive user input associated with a client device of a user that includes a request for the musical content, generate the musical content, and cause the musical content to be audibly rendered at the client device. In some implementations, the processor(s) can cause a single GM to process GM input (including at least the user input) to generate GM output and can determine the lyrical content and the music composition content based on the GM output. In other implementations, the processor(s) can cause multiple GMs to process respective GM inputs (each including at least the user input) to generate respective GM outputs and can determine the lyrical content and the music composition content based on the respective GM outputs.
Owner:GOOGLE LLC

Method and system for ai-based song remixing

According to an embodiment, a trained AI is provided that automatically identifies stems of a music work and loops within the stems. Information about the stems, the cut points of loops, and the loop's fundamental parameters will be formed into an AI Song pack. The remixing step uses the AI Song pack as a starting point and a database of loops is searched to identify audio loops that can replace loops with similar sonic characteristics in the music work to create a remix. Once some number of candidate loops have been identified a final remixed audio track will be produced which is comprised of replaced loops from the database. Alternatively, replacement stems might be created by replacing all loops in each stem. Finally, effects might be applied to the audio material created by either approach.
Owner:BELLEVUE INVESTMENTS GMBH & CO

Artificial intelligence systems and methods for detecting musical infringement in symbolic music

The present disclosure relates to a system and method for detecting musical infringement in symbolic music. The system receives a first musical composition and, when provided as audio, converts it into a symbolic format using a transcription neural network trained to extract a main melody. It then generates k-mer sequences comprising consecutive notes, indexes these sequences in a data structure configured for dynamic conditioning, and compares them to reference musical compositions. Upon estimating a similarity measure that exceeds a threshold, the system performs a refined local sequence alignment adapted for music, accounting for key shifts, rests, and melodic or rhythmic variations. Based on this refined alignment, the system determines whether the first musical composition includes a musical fragment that infringes upon or regurgitates a portion of at least one reference composition.
Owner:SOUND PATROL INC

Ambient perception system for experiencing the environment through music

The present invention discloses an environment perception system, which includes a memory and a first module and a second module. The memory is configured to store environment data, one or more music work templates and one or more mappings, wherein the environment data indicates at least one of a state, condition or change in the environment in which the environment perception system is located. The first module is configured to receive the environment data and store the environment data in the memory. The second module is configured to: based on the one or more music work templates and the one or more mappings, convert the environment data into a music signal, including modifying variables in the one or more music work templates based on the environment data; and based on the music signal, play the music work via an audio system to audibly indicate at least one of a state, condition or change in the environment.
Owner:GENERAL MOTORS LLC

Audio processing method and device

The present application discloses an audio processing method and device, which relate to the field of audio processing technology. The method comprises obtaining an audio file to be processed and extracting key parameters from the audio file to be processed, wherein the key parameters include at least a beat list, a beat type and a beat number speed parameter. According to the beat type and the beat number speed parameter, the note duration range corresponding to the interval between each adjacent beat is calculated. When matching the note sample, the method searches for each candidate note in the note duration range that meets preset rules and matches the recording rhythm from the note sample library. The preset rules are determined by the beat list, the preset music parameters and the music theory constraints. The method searches for the optimal note sequence from each candidate note, and renders the optimal note sequence by a preset rendering method to obtain an audio signal, thereby completing the process of creating a musical work.
Owner:小芒电子商务有限责任公司

A method and system for automatically classifying music works

The present invention relates to the field of music information retrieval technology, specifically to a method and system for automatically classifying music works, comprising the following steps: based on the classification standard of music genres, analyzing the hierarchical node relationship of music genres, extracting the corresponding hierarchical characteristics of genre major categories and minor categories, identifying the correlation ratio between each level, analyzing the hierarchical connection strength, and generating a music genre hierarchical weight table. In the present invention, through the in-depth analysis of the hierarchical structure of music genres, a more refined and dynamic classification of music works is achieved, and the accuracy and flexibility of classification are significantly improved. By extracting hierarchical features and revealing the association between levels, music classification not only breaks through the limitations of simple labeling, but also reflects the hierarchical relationship between genres, extracts the law and amplitude of chord changes, enhances the dynamic capture of music features, matches the association between chord changes and genre hierarchical features, dynamically adjusts the classification weight, accurately matches genre characteristics, and better adapts to the diversity and complexity of music creation.
Owner:HEBEI XIAOLONG TECH CO LTD

Systems and methods for algorithmic generation of musical compositions

A computer-implemented method for algorithmic generation of musical compositions may include (i) receiving, as a first input set, a set of musical compositions composed by a composer, (ii) receiving, as a second input set, metadata related to at least one musical composition, (iii) training a generative machine learning model on the first input set and the second input set, and (iv) producing, by the generative machine learning model, a new musical composition that is based at least in part on the first input set and the second input set. Various other methods, systems, and computer-readable media are also disclosed.
Owner:SONGBIRD INC

Accompaniment generation method, accompaniment generation apparatus, and accompaniment generation system

To generate an added value which cannot be obtained only by referring to a musical score by giving additional information to a musical piece by interpreting the musical score.SOLUTION: The accompaniment generation method includes acquiring the musical score image data SD representing the musical score 5, analyzing the musical piece information included in the musical score 5 from the acquired musical score image data SD, and generating the accompaniment to be added to the musical piece represented by the musical score 5 based on the analysis result of the musical piece information. The accompaniment generation program executes the accompaniment generation method on a computer.SELECTED DRAWING: Figure 3
Owner:YAMAHA CORP

Audio system and method for a kitchen appliance

The present disclosure provides a method (200) performed by an audio system (5) of a kitchen appliance (10), wherein the audio system (5) comprises a passive buzzer (150) coupled to a controller (100) including a processor (110) and a memory (120) having stored therein executable instructions. Execution of the executable instructions by the processor (110) configures the controller (100) to generate a drive signal (1000) for driving the passive buzzer (150) to produce a sequence of musical notes (300) forming a musical composition, wherein the executable instructions configure the controller (100) to generate the drive signal (1000) according to one or more duty cycle parameters (330, 335, 340), one or more frequency parameters (310, 315, 320), and one or more temporal parameters (305, 325, 345) for each musical note (300). The controller (100) controls the passive buzzer (150) according to the drive signal (1000) to produce the sequence of musical notes (300), wherein during a duration (305) of each musical note (300) defined by the one or more temporal parameters (305, 325, 345), the drive signal (1000) controls a pitch of each musical note (300) based on the one or more frequency parameters (310, 315, 320) and a volume of each musical note (300) based on the one or more duty cycle parameters (330, 335, 340), wherein the pitch and volume of each musical note (300) are independently controllable such that the volume of a musical note (300) can be set independently of the pitch of that musical note (300).
Owner:BREVILLE HLDG PTY LTD

An audio processing method, an electronic device, and a readable storage medium

This application relates to the field of speech recognition, and particularly to an audio processing method, an electronic device, and a readable storage medium. The audio processing method includes: processing audio data input by a user in the form of reading aloud to obtain user feature parameters such as speech rate, pitch, and timbre; and based on multiple user feature parameters, using a pre-trained algorithm to obtain corresponding musical feature parameters of the audio data, such as musical emotion, musical style, musical rhythm, and musical tonality. Then, the aforementioned musical feature parameters and the corresponding audio text are input into an AI composition model for music composition, resulting in musical data corresponding to the audio data. Finally, speech synthesis technology is used to synthesize the user feature parameters such as timbre and pitch with the musical data obtained based on the AI ​​composition model to obtain a musical work simulating the user's timbre. In this way, music simulating the user's singing can be obtained based on the user's audio, providing a way for users to create personalized music.
Owner:HUAWEI TECH CO LTD

Data processing method of analysing musical data in the context of educational material data

A data processing method of generating a structured audio-visual presentation of educational material data, integrated with musical data, for output onto a display, comprising steps of: a) receiving a block of musical data representing a specific musical work; b) receiving a block of educational material data representing a specific educational material; c) processing the musical data to determine musical elements contained therein and the structure of the musical data, including notes played by a plurality of instruments and vocal sounds including words and syllables; d) processing the educational material data to determine the elements contained therein and thereby determine the structure of the educational material data, including text and diagrams associated with the text; and e) processing the musical elements and the educational material elements, to determine synchronized time pairings of specific individual musical elements with specific individual educational material elements, by using the determined structures where the determined synchronised time pairings are ordered sequentially for presentation onto the display as an audio-visual presentation.
Owner:THIIIA LTD

Method and system for AI-based song remixing

ActiveUS12784720B2EngineeringAudio frequency
According to an embodiment, a trained AI is provided that automatically identifies stems of a music work and loops within the stems. Information about the stems, the cut points of loops, and the loop's fundamental parameters will be formed into an AI Song pack. The remixing step uses the AI Song pack as a starting point and a database of loops is searched to identify audio loops that can replace loops with similar sonic characteristics in the music work to create a remix. Once some number of candidate loops have been identified a final remixed audio track will be produced which is comprised of replaced loops from the database. Alternatively, replacement stems might be created by replacing all loops in each stem. Finally, effects might be applied to the audio material created by either approach.
Owner:BELLEVUE INVESTMENTS GMBH & CO

Information processing device

This information processing device (3) comprises: a control information acquisition unit (366) that acquires a plurality of pieces of sound control information in which a plurality of sound control operations for a musical piece are recorded; a correction unit (370) that is able to correct each of the plurality of pieces of acquired sound control information; a playback unit (371) that plays back the musical piece; and a reproduction unit (372) that reproduces, in the played back musical piece, the plurality of sound control operations based on the corrected plurality of pieces of sound control information.
Owner:ALPHATHETA CORP

Musical performance correction method and musical performance correction device

A musical performance correction method executable by a computer, the musical performance correction method includes: estimating a playing position in a musical composition by analyzing musical performance data indicating a played pitch played by a user; and correcting the played pitch indicated by the musical performance data to a reference pitch, from among a plurality of reference pitches corresponding to the playing position in the musical composition, in a case where a difference between the played pitch and the reference pitch is less than a predetermined value.
Owner:YAMAHA CORP

Methods, devices, electronic devices, and storage media for invoking music playback functions

The embodiments of the present invention provide a method, device, electronic device and storage medium for calling a music playback function. The method for calling a music function provided by the embodiments of the present invention is that after the first APP obtains the trigger instruction of the music playback function, it can display the media information display page obtained from the server corresponding to the second APP, and then obtain the music playback instruction for the target music work sent by the media information display page, and based on the music playback instruction, start the second APP in the background to play the target music work. In the embodiments of the present invention, if the first APP wants to play music, it can obtain the media information display page from the server corresponding to the second APP for display, and open the second APP in the background to realize the music playback function. It is not necessary to develop a corresponding music playback page and interface specifically for the music playback interface provided by other application service providers when developing the first APP, which reduces the research and development cost of the APP that calls the music playback function.
Owner:GUANGZHOU KUGOU COMP TECH CO LTD

Music creation control cue word generation method, system and equipment and medium

The invention discloses a music creation control cue word generation method, system and device and a medium, and the method specifically comprises the steps: based on multi-mode creation demand data, determining a melody intention through analyzing voice humming, determining an emotion intensity parameter through analyzing voice intonation, and generating a cue word according to the emotion intensity parameter; extracting keywords of styles, themes and emotions in combination with a natural language processing technology to form multi-modal features; inputting the multi-modal features into a pre-constructed music knowledge graph for associated query and intention refining, and generating music control cues; distributing the music control prompt words to a multi-agent collaborative cluster to generate a music element set; and driving a music generation model to synthesize a music work according to the music element set, and dynamically adjusting an association weight of a music knowledge graph or a decision parameter of a multi-agent collaborative cluster in combination with user feedback data. According to the method and the device, accurate and personalized music creation control cue word generation is realized, and the quality of music creation and the user satisfaction are improved.
Owner:广州三七极耀网络科技有限公司

Systems and methods for algorithmic generation of musical compositions

A computer-implemented method for algorithmic generation of musical compositions may include (i) receiving a musical composition and listener preference data associated with at least one listener, (ii) extracting from the musical composition a first set of tracks and a second set of tracks, (iii) generating, by at least one generative machine learning model, based at least in part on the listener preference data, a new set of tracks, and (iv) combining, by a music production model, the first set of tracks extracted from the musical composition with the new set of tracks generated by the generative machine learning model to create a new musical composition based at least in part on the listener preference data. Various other methods, systems, and computer-readable media are also disclosed.
Owner:SONGBIRD INC

Music genre classification method based on knowledge graph and anti-factual attention mechanism

The invention discloses a music genre classification method based on a knowledge graph and an anti-factual attention mechanism, and the method comprises the steps: firstly obtaining music data and metadata, and constructing a music genre analysis data set; secondly, based on the metadata, music knowledge graph construction and embedded representation learning are carried out, and learning embedded representation is obtained; then, based on the music data, audio feature extraction capable of learning anti-factual attention is carried out, and audio feature embedding is obtained; and finally, on the basis of learning embedding representation and audio feature embedding, constructing a knowledge-guided feature fusion and music genre classification model to obtain a music genre classification result, and performing test evaluation. The method is used for improving the deep understanding and classification accuracy of the music audio content, and can more accurately and comprehensively understand the context background and the internal relation of the music work; and meanwhile, the classification robustness and accuracy in a complex acoustic environment are improved.
Owner:HANGZHOU DIANZI UNIV +2

Emotional care method based on audio and video combination in combination with essential oil sniffing

The invention discloses an emotion care method based on audio and video combination in combination with essential oil sniffing. The method comprises the following specific steps: S1, selecting an input instruction according to music of a user; s2, performing deep screening on the music works subjected to preliminary screening; s3, selecting an input instruction according to the picture of the user; s4, inputting an instruction according to the guide language of the user; matching the screened qualified music works, picture works and guidance language audio works; and according to the style of the mixed audio and video file, recommending and selecting essential oil types. The system provides high-quality music and videos, enables consumers to perceive more audio and video details, provides a'relaxed-calm-nice-pleasant-wide 'hierarchical music combination, enables the consumers to relax bodies, provides various music and video combinations, provides guide language audio, guides the consumers to suck essential oil for relaxation, and improves the quality of the consumers. Therefore, the actual emotion maintenance effect is improved, and consumers are helped to remove negative emotions such as anxiety and depression and keep physical and psychological health.
Owner:BEIJING LIULIXUELING TECHNOLOGY CO LTD

System and method for sharing musical compositions

A system for listing and radio broadcasting of musical compositions by new and independent artists. The method includes receiving musical compositions from the artists through an interface implemented on a user device. The system further receives playback schedules for the musical compositions from the artists. The system then broadcasts the musical compositions based on the respective playback schedule. The system allows listeners to vote for their favorite artists. Artists getting maximum votes in a predefined duration can be given cash prizes. Also, the system allows the artists to contract with external radio stations to play their musical compositions on these radio stations.
Owner:MORGAN LOIS NOEL +1