Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

54 results about "Generative music" patented technology

Generative music is a term popularized by Brian Eno to describe music that is ever-different and changing, and that is created by a system.

Training program and music playlist generation for athletic training

Systems and techniques for generating an athletic training program and selecting music for playing during the training program are described. Based on specified parameters, a training program module may generate a customized training program intended to help an athlete reach a goal. In conjunction therewith or independently thereof, a music selection module may generate a music playlist for playing during a training program. Music selection parameters may include training intensity, user speed, user location, user mood, a user's currently performance (e.g., as compared to an expected performance) and the like. The music selection module may select songs from a personal library or a public database of music. Music selection may be made to maximize user motivation / inspiration.
Owner:NIKE INC

Computer network indicating relatedness of attributes of monitored terminals

Each terminal of a computer network can monitor the activities of the other terminals or associated equipment such as a telephone and display these activities in visual and / or audible form. The display may be represented as a “virtual world”, and / or a generative music system such as “Koan”. The nature of the activities performed by the terminal itself also control the display, for example giving greatest prominence to those terminals engaged in similar or related activities. A terminal may be configured to act as a specified user's “base” terminal, to display the activity of the specified user, by identifying whether the specified user's identity is being used on another terminal. The activity of this terminal can then be displayed on the “base” terminal. The base terminal can therefore indicate the absent user's availability, level of activity, etc. to colleagues working nearby.
Owner:BRITISH TELECOMM PLC

Automatic generation of musical scratching effects

The invention relates to a method for generating electrical sounds and to an interactive music player. According to the invention, an audio signal in digital format, which lasts for a predeterminable length of time, is used as the starting material. The reproduction position and / or the reproduction direction and / or the reproduction speed of said signal is / are modulated automatically with respect to the rhythm using control information in different predeterminable ways, based on information concerning the musical tempo.
Owner:NATIVE INSTR SOFTWARE SYNTHESIS

Music information retrieval

Embodiments of the present invention provide for the receipt of unprocessed audio. Musical information is retrieved or extracted from the same. This musical information may then be used to generate collaborative social co-creations of musical content, identify particular musical tastes, and search for content that corresponds to identified musical tastes.
Owner:HUMTAP INC

System and method of music generation

There is provided herein a system and method for generating music on multiple cell phones or other mobile computing devices, wherein two or more users (to include a user and a computer) acting together may create a joint musical work. The instant methods enable multiple users to create music in a synchronised fashion by using their cell phones or other portable electronic devices as musical instruments. The instant invention has been made possible because of the enhanced processor power within mobile electronic devices and has the potential to create added value in such devices by assisting users in exploiting multimedia features of their cell phones.
Owner:MAGIX

Generating music thumbnails and identifying related song structure

Provided are, among other things, systems, methods, software programs and techniques for generating an audio thumbnail for a musical piece, in which locations of different repeating segments within an input musical piece are identified. In addition, a singing segment within the musical piece is detected based on a calculated singing metric that indicates when singing is present. A thumbnail criterion that defines a location of an audio thumbnail by reference to generic musical structure is obtained, and a segment of the musical piece is selected as the audio thumbnail based on the thumbnail criterion, together with the location of at least one of the plural different repeating segments and a location of at least a portion of the singing segment. The audio thumbnail is then played and / or stored for future playing.
Owner:HEWLETT PACKARD DEV CO LP

Method for generating music by image on the basis of complex network

The invention discloses a method for generating music by an image on the basis of a complex network. The method comprises the following steps that: 1: extracting a gray code corresponding to a regionof interest of a gray image, and multiplying three continuously adjacent gray codes in a gray code array to obtain a gray product array; S2: according to a MIDI (Musical Instrument Digital Interface)pitch range, carrying out mold processing on elements in the gray product array, and obtaining a range interval and a pitch floating number so as to generate a pitch sequence; S3: taking the pitch, the length and the strength of notes in existing music as basic attributes to code note nodes, and forming a note network by the connecting edges of the note nodes; and S4: carrying out node migration on the pitch sequence generated by the image in the note network so as to generate the music. By use of the method for generating the music by the image, the complex network and knowledge rendered by amusic theory are applied to enable the music to be finger-popping and beautiful.
Owner:NORTHEASTERN UNIV

System for creating music publishing agreements from metadata of a digital audio workstation

Systems and methods relating to a platform for creating, monitoring, updating, and executing legal agreements for data files such as a collaborate digital media file using associated metadata. The platform enables music publishing agreements to be generated automatically by taking metadata from a DAW (digital audio workstation) that reflects the activity and contributions of each author associated with a file. Authorship metadata can be recorded on a ledger or blockchain by the platform. The platform enables calculation and disbursement of royalties to be automated by algorithmic determination of terms of an authenticated smart contract using authorship metadata for an associated media file generating the royalty. Authors may concurrently contribute from across a variety of different DAWs, local and remote, and computing resources may be distributed by the platform.
Owner:AURIGN INC

Generating music thumbnails and identifying related song structure

Provided are, among other things, systems, methods, software programs and techniques for generating an audio thumbnail for a musical piece, in which locations of different repeating segments within an input musical piece are identified. In addition, a singing segment within the musical piece is detected based on a calculated singing metric that indicates when singing is present. A thumbnail criterion that defines a location of an audio thumbnail by reference to generic musical structure is obtained, and a segment of the musical piece is selected as the audio thumbnail based on the thumbnail criterion, together with the location of at least one of the plural different repeating segments and a location of at least a portion of the singing segment. The audio thumbnail is then played and / or stored for future playing.
Owner:HEWLETT PACKARD DEV CO LP

Music classification method based on deep learning

The invention discloses a music classification method based on deep learning, and the method comprises the steps: converting an audio file of music into a Mel spectrogram, and generating a one-hot vector of a music label; respectively transmitting the Mel spectrogram of the music and the one-hot vector of the music label into a convolutional neural network and a recurrent neural network; obtainingfrequency domain and time domain feature vectors of music through a convolutional neural network, obtaining a music-label relationship vector through a recurrent neural network, mapping respective output vectors of the convolutional neural network and the recurrent neural network to the same dimension, and performing connecting and combining to form a music-label embedding vector; and transmitting the music-label embedding vector to a label prediction layer, wherein the output of the music-label embedding vector is the probability value of the music corresponding to each category label, and finally, selecting a plurality of category labels from all the category labels as the classification of the music according to the probability values. The invention belongs to the technical field of information, and can realize accurate prediction of music category labels based on numerous and staggered relationships of music categories.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Music synthesis method, device and equipment and computer readable medium

The embodiment of the invention discloses a music synthesis method and device, electronic equipment and a computer readable medium. One specific embodiment of the method comprises the steps of synthesizing lyrics based on a currently displayed lyric template and at least one word input by a user according to the lyric template; generating labels of music features and language features based on thelyrics and the melody of the preset background music; generating a target dry sound based on the labels of the music features and the language features; and synthesizing music based on the target drysound and the preset background music. According to the embodiment, the user can participate in lyric filling, and music is generated according to the lyric filled by the user.
Owner:BEIJING BYTEDANCE NETWORK TECH CO LTD

Recursive jump connection deep learning music automatic generation method based on layer standardization

PendingCN113707112AGenerate high qualityAdded recursive modeElectrophonic musical instrumentsNeural learning methodsDigital interfaceGenerative music
The invention discloses a recursive jump connection deep learning music automatic generation method based on layer standardization. The method comprises the steps of collecting musical instrument digital interface data, preprocessing a training set, constructing a music automatic generation network, training the music automatic generation network and automatically generating a music file. According to the method, on the basis of the structure of the Transformer-XL neural network, the layer-standardized recurrent neural network and the multi-expert layer are introduced, so that the overall neural network performance is optimized, the condition of recursion disappearance or explosion is relieved, the learning ability of the neural network is enhanced, and the quality of the generated music is higher and is closer to the type of a training set. The method can be applied to the technical field of automatic music generation.
Owner:SHAANXI NORMAL UNIV

Music generation method and training method of music generation model

The invention discloses a music generation method, which comprises the following steps: obtaining a chord comprising a plurality of chords, each chord having a specified duration and comprising a plurality of notes; respectively converting the plurality of chords of the chord into a plurality of first MIDI messages, wherein each first MIDI message comprises a chord feature representing the corresponding chord and a note feature representing the plurality of notes of the corresponding chord; determining a chord arrangement sequence of the plurality of chords performed by the chord; inputting the multiple first MIDI messages and the chord arrangement sequence into a music generation model based on a natural language neural network, and sequentially generating multiple second MIDI messages corresponding to the multiple first MIDI messages and mapping the chord arrangement sequence, wherein each second MIDI message comprises note features representing multiple generated notes, the plurality of generated notes generally have the specified duration; and splicing the plurality of second MIDI messages into a generated music MIDI message according to the generation sequence.
Owner:TENCENT MUSIC ENTERTAINMENT TECH SHENZHEN CO LTD

Washing machine capable of controlling water flow by music and control method

The invention discloses a washing machine capable of controlling water flow by music and a control method. The washing machine comprises a motor used for generating washing water flow; the motor is connected with a control device which is used for controlling the rotation-stop ratio and / or rotating speed of the motor; a storage device used for storing the music is arranged on the control device; the storage device is connected with an analysis device which is used for extracting, analyzing and processing music features; the analysis device is connected with a conversion device which is used for converting music signals into the rotation-stop ratio and / or rotating speed signals of the motor; the conversion device is connected with an execution device for controlling the rotating speed of the motor. The music is transmitted into the storage device; the analysis device extracts, analyzes and processes features of the music to generate music feature signals; the conversion device converts the music feature signals into the rotation-stop ratio and / or rotating speed of the motor; the corresponding rotation-stop ratio and / or rotating speed signal is transmitted to the motor when the music signals is transmitted to an audio output device.
Owner:QINGDAO HAIER WASHING MASCH CO LTD

Method of generating music data

A computer-implemented method of generating a piece of music is disclosed. The method comprises the steps of determining an initial sequence of notes for the piece of music; determining at least one probability distribution for selecting at least one subsequent note from a set of candidate notes; generating a biasing output based on data of the initial sequence of notes; and extending the initialsequence of notes with at least one subsequent note selected from the set of candidate notes according to the probability distribution and the biasing output, wherein the biasing output biases the selection so as to affect the likelihood of the selection resulting in a repeat of a musical element formed by the initial sequence of notes.
Owner:BYTEDANCE INC

Superposition enhancement neural modulation method and device based on music and energy wave function

The invention provides a superposition enhancement neural modulation method and a device based on music and an energy wave function. The method comprises the following steps: generating a music stimulation sequence; analyzing the music stimulation sequence to obtain a stimulation signal sequence corresponding to stimulation intensity and stimulation time; and performing stimulation output by a stimulation controller according to the stimulation signal sequence. According to the invention, the stimulation timestamp and the intensity of the stimulation controller are recoded by using the inherent rhythm and the energy wave function of the music to induce the superposition enhanced neural modulation effect, so that the method can be applied to various treatment and evaluation scenes, for example, post-stroke limb dyskinesia, cognitive impairment, aphasia, senile dementia, Parkinson's disease, spinal cord neural network excitability, disturbance of consciousness and the like.
Owner:浙江柔灵科技有限公司

Digital music management method, system and device and storage medium

The invention discloses a digital music management method, system and device and a storage medium. The digital music management method comprises the following steps: judging whether each block chain node participates in a transaction consensus, and if so, identifying the block chain node as an accounting node; acquiring digital music uploaded by a user; auditing the digital music; if the audit is passed, registering and storing the digital music through the bookkeeping node, and generating digital music information and a storing identifier; and generating NFT music according to the digital music information and the evidence storage identifier. According to the invention, by identifying each block chain node participating in the transaction consensus, the problems of poor data visibility and low security caused by a single storage node for digital music management are avoided; through registration and evidence storage of the digital music and generation of the NFT music, a data flow link of the digital music is transparent, the convenience of authorization management is improved, and the method and the device can be widely applied to the technical field of computers.
Owner:天翼爱音乐文化科技有限公司

Music comment generation method based on deep learning

A music comment generation method based on deep learning comprises the following steps: acquiring original music comments by using a web crawler technology, and constructing a music comment library; constructing a text abstract generation model based on the Bert model and the Transformer model, and inputting the lyric text of the to-be-commented music into the text abstract generation model to obtain a lyric abstract text; judging whether a music name or a singer name of the to-be-commented music exists in the original comments of all the music in the music comment library or not; if yes, selecting out the original comments with the music names or the singer names, and if not, calculating the text similarity between the lyric abstract text of the music to be commented and the original comments of each piece of music in the music comment library, and selecting out the original comment with the highest similarity; and constructing a replication generation model based on the VAE model, and inputting the selected original comments into the replication generation model to generate a new comment text. The invention belongs to the technical field of information, and can automatically generate a comment text of music and improve the accuracy, diversity and fluency of the text.
Owner:新讯数字科技(杭州)有限公司

Music generation method and device, electronic equipment and storage medium

The embodiment of the invention discloses a music generation method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining the original heart rate data of a fetus, and determining the audio parameters of to-be-generated music according to the original heart rate data; extracting a preset number of heart rate value points from the original heart rate data; traversing the heart rate value points in sequence, and determining a note corresponding to each heart rate value point according to a preset mapping relationship between heart rate values and notes; selecting target notes from the determined notes according to a preset melody generation rule, and forming a note melody according to the target notes; generating an accompaniment according to the rotation and rotation rule; and generating a stave according to the note melody and the accompaniment, and generating playable music in combination with the audio parameters according to the stave. According to the embodiment of the invention, the purpose of converting the fetal heart rate into the music and the stave is achieved.
Owner:SOUTH SUZHOU MEDICAL TECH CO LTD

National music generation method and device, equipment and storage medium

The invention relates to the field of artificial intelligence, and discloses a national music generation method and device, equipment and a storage medium. Multi-national style meditation music for meditation relaxation is generated, the method comprises the following steps: obtaining national music generation parameters input by a user, wherein the national music generation parameters comprise scene parameters, style parameters and time parameters; according to the scene parameters and the style parameters, determining musical instrument types, music score materials and a music material generation model, screening N pieces of music score data from the music score materials, inputting the N pieces of music score data into the music material generation model, and generating N pieces of music materials, wherein N is a natural number not less than 1; according to the musical instrument type, selecting a corresponding rendering rule from a preset rendering rule library, and performing tone rendering on the music material based on the rendering rule to obtain a finished product material; and performing audio processing on the finished product material, generating a music file and outputting the music file. In addition, the invention also relates to a block chain technology, and music score materials can be stored in a block chain.
Owner:PING AN TECH (SHENZHEN) CO LTD

Singing synthesis method and device, computer device and storage medium

The invention discloses a singing synthesis method and device, a computer device and a storage medium, and is applied to the technical field of computers. The method provided by the invention comprises the following steps of acquiring the music data of a target song, and encoding the music data through a preset encoder to generate the music encoded data; inputting the music encoded data into an attention mechanism network for coding, and generating the feature information; inputting the feature information into a singing synthesis model, and generating the first sound spectrum data; and decoding the first sound spectrum data to obtain the first linear spectrum data, and converting the first linear spectrum data into a target song audio in a Fourier transform mode. According to the present invention, the singing synthesis model is obtained through training a small amount of training data, the synthesis efficiency of the target song audio is improved, and meanwhile the synthesis effect of the target song audio is guaranteed.
Owner:PING AN TECH (SHENZHEN) CO LTD

Comparison Training for Music Generator

Techniques are disclosed relating to automatically generating new music content based on image representations of audio files. A music generation system includes a music generation subsystem and a music classification subsystem. The music generation subsystem may generate output music content according to music parameters that define policy for generating music. The classification subsystem may be used to classify whether music is generated by the music generation subsystem or is professionally produced music content. The music generation subsystem may implement an algorithm that is reinforced by prediction output from the music classification subsystem. Reinforcement may include tuning the music parameters to generate more human-like music content.
Owner:AIMI INC

Automatic electronic music score playing method, system and device, equipment and storage medium

PendingCN112652279AOvercome the inconvenience of carryingOvercome the defect that users cannot modify electronic scoresElectrophonic musical instrumentsMusicGenerative musicEngineering
The invention discloses an automatic electronic music score playing method, system, device and equipment and a storage medium, and the method comprises the steps: recognizing an electronic music score file in a preset format, and generating a music standardized file; receiving a modification instruction based on the music standardized file; outputting the music standardized text modified according to the modification instruction as an MIDI file; and sending the MIDI file to a corresponding terminal. According to the invention, an electronic music score file can be automatically identified, so that the music standardized file is generated, the modification of the music standardized file actively by a user can be received, the formed MIDI file is sent to the terminal for playing, and the defects that a paper music score is inconvenient to carry and the user cannot modify the electronic music score in the prior art are overcome.
Owner:广东爱乐社教育科技有限公司

Systems, methods and apparatus for generating music recommendations based on combining song and user influencers with channel rule characterizations

Systems, methods and apparatus for generating music recommendations based on combining song and user influencers with channel rule characterizations are presented. Such systems and methods output a playlist, which may be delivered as an information stream of audio on a user or client device, such as a telephone or smartphone, tablet, computer or MP3 player, or any consumer device with audio play capabilities. The playlist may comprise various individual audio clips of one genre or type, such as songs, or of multiple types, such as music, talk, sports and comedy. The individual audio clips may be ordered by a sequencer, which, using large amounts of data, generates both (i) user independent and (i) user dependent influencer weightings for each clip, and then combines all of such influencer weightings into a combined play weighting W for a given audio clip, for a given user. Taking the various play weightings W(Ui, Sj), a set of rules may be applied to generate a set of candidates C(Ui, Sj, Tk) to play to User j in each of Time slots k through k+m. Real time playlists may then be generated from the m sets of candidates by application of a set of rules, which may be channel rules, for example. The data used to generate influencer weightings may include user-specific data including preferences and detailed listening history, audio clip specific data, and data gleaned from various Internet accessible sources, including social media. In some embodiments a feedback loop may be implemented to gauge the accuracy of the dynamically generated playlists and modify the influencer weightings in response.
Owner:SIRIUS XM RADIO INC

Method and Apparatus for the Composition of Music

PendingUS20220122569A1Electrophonic musical instrumentsEmotional tensionGenerative music
A system and method for making musical decisions is provided. The approach is based on algorithms which compose music driven by an input of desired emotional tension over time. A method for abstraction and quantification of musical structures is detailed, as well as the application of this method in a generative algorithm that produces musical sequences. The overall goal of this method is to use a set of abstractions and guidelines to generate emotionally appropriate new music in real time.
Owner:CAREN MATTHEW
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products