59 results about "Sequence (music)" patented technology

The invention provides a classical music cross-modal high-reliability experimental data set construction method for full-scene teaching application, and the method comprises the steps: constructing an original data set through collecting audio, video, music score and other multi-modal data, carrying out the standardization of each modal data through a preprocessing technology, and obtaining a multi-modal data set in a unified format; according to the semantic feature vectors, a knowledge graph is constructed, nodes represent semantic relations between music elements, edges represent semantic relations between the elements, a graph convolutional network is adopted to encode the knowledge graph, and semantic representation of the teaching content is obtained; a virtual reality rendering technology is adopted, multi-modal teaching resources are integrated into an immersive teaching scene, a content sequence is presented in real time, and dynamic teaching experience is obtained; and continuously collecting interaction data of the learner, updating the knowledge graph and the semantic feature vector, and optimizing the cross-modal fusion model by adopting an incremental learning algorithm to obtain a self-adaptive teaching data set.

The invention relates to the technical field of music score matching, in particular to an audio and music score matching method and system, and the method comprises the steps: providing a reference database of a music score, which comprises multiple segments of expected playing characteristics of a plurality of music units; acquiring first note data generated by playing of the user at first time; judging whether second note data generated at adjacent second time before the first time is successfully matched with the first target music unit or not; if yes, determining a first dynamic prediction sequence at the first time according to the first target music unit; judging whether the corresponding music unit obtained in the first dynamic prediction sequence is a second target music unit of the first note data or not; and if yes, marking the second target music unit as the current playing node. According to the music score matching technology, the matching time axis can be dynamically adjusted in combination with the playing state, and then positioning matching of the audio and the music score can be rapidly achieved through the limited matching calculation amount.

The invention relates to the field of intelligent creation of personalized music, and discloses an intelligent creation system of personalized music, comprising a non-residual music gene modeling module for constructing a structured feature tensor; the user state sensing and trajectory planning module is used for acquiring physiological state data of a user in real time and planning a target emotion parameter trajectory sequence for guiding the emotion state of the user; the constraint optimization generation module is used for generating an optimal music feature tensor sequence by solving a dynamic constraint optimization problem; and the multi-modal synthesis and presentation module synthesizes the music feature tensor sequence into audio synchronous with the virtual playing action and outputs the audio. According to the method, a scheme of combining user physiological state perception and predictive emotion trajectory planning is adopted, so that dynamic and prospective guidance of user emotion is realized; the music is converted into an active and personalized biological feedback tool from a passive listening medium, so that the effectiveness of the music in emotion regulation application is remarkably improved.

The invention discloses a music database retrieval method and system based on feature extraction, and relates to the technical field of data analysis, and the method comprises the steps: carrying out the preprocessing of an audio signal of a query track input by a user, dividing the audio into equal-length frame sequences, and generating three-channel spectrogram tensors, including a Mel spectrogram, a logarithmic amplitude spectrogram and a CQT spectrogram; extracting multi-modal features of the equal-length frame sequence, dividing melody motivation segments according to pitch change and stability of the audio signal, performing differential coding, generating a melody differential sequence, and modeling the melody differential sequence into a melody topological graph; and calculating the structural similarity between the melody topological graph and a database melody graph, screening a similar melody candidate set P, mapping a melody curve into a topological manifold through a topological data analysis method, extracting persistent homology features, and converting the persistent homology features into a persistent bar graph. According to the method, the retrieval precision and the matching credibility of the complex melody in the music database are remarkably improved.

The invention relates to a method and system for assisting clinical psychotherapy through traditional Chinese medicine music therapy. The method comprises the following steps: extracting five-tone frequency, rhythm and timbre characteristics of music, dynamically converting audio data into a dynamic image frame sequence in combination with a color mapping rule, and realizing multi-sensory real-time matching of the music and visual elements by utilizing a time synchronization algorithm and collaborative intensity calculation. And finally, dynamic collaborative stimulation is output through a streaming media transmission technology. Therefore, on the basis of retaining the kernel of the five-tone regulation theory in the traditional Chinese medicine, the problems of audio-visual splitting and difficulty in quantitative implementation of the theory in the traditional method are solved, and the multi-modal synergistic effect and clinical suitability of the music therapy in emotion and cognitive regulation are remarkably improved.

The application discloses a two-dimensional Root-MUSIC angle automatic pairing method and system based on signal receiving timing, and specific steps of the method are as follows: step 1, a Root-MUSIC algorithm mathematical model suitable for angle estimation of two orthogonal arrays of an L-shaped array is constructed, the Root-MUSIC algorithm is applied to the two orthogonal arrays respectively, and a set of azimuth angles and a set of elevation angles are estimated; step 2, timing detection and dynamic grouping are carried out based on signal arrival timing, and simultaneous multi-signal receiving processing is converted into a single-signal processing flow organized according to timing; the Root-MUSIC algorithm is executed on each group of signals, and pairing of the azimuth angles and the elevation angles is automatically completed; and step 3, the pairing result of step 2 is stored, and whether the pairing process is ended is judged, if yes, the angle pair is output in sequence. The application constructs a joint processing mechanism of timing detection-dynamic grouping-serial processing, converts traditional multi-dimensional matching calculation into a simple timing alignment operation, and makes angle pairing become a natural derivative result of the signal processing flow.

The invention discloses a music understanding model training method, an audio processing method, equipment and a medium, which are applied to the technical field of computers, and comprise the following steps: compressing a song audio through an initial music understanding model to obtain an audio compression representation; the audio compression representation comprises any one or more of timbre information, emotion information and semantic information; performing coding processing on the pitch sequence of the song audio through the initial music understanding model to obtain melody compression representation containing melody information; constructing a fusion compression representation based on the audio compression representation and the melody compression representation; and optimizing the initial music understanding model based on the fusion compression representation and the audio compression representation to obtain a music understanding model. According to the method, the pitch track of the melody is reserved through the pitch sequence, redundant information is directly stripped, semantic focusing of melody characteristics is achieved, melody compression representation is obtained based on the pitch sequence, the characteristic of strong association of the music before and after is reserved, and the method is more suitable for characteristic learning of the music melody.

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.

The disclosure relates to a computer-implemented method for audio generation. The method includes obtaining a first set of single-track audio data, wherein the single-track audio data is represented in a text-based single-track musical notation; obtaining a set of predefined character sequences, each predefined character sequence associated with a type of music elements in the single-track musical notation; tokenizing the first set of single-track audio data based on the set of predefined character sequences; and training a first audio generation model based at least in part on the tokenized first set of signal-track audio data. The disclosure further relates to corresponding apparatus, computer programs, and computer-readable storage media.

The application relates to the technical field of artificial intelligence-based music melody automatic generation systems, and particularly discloses an artificial intelligence-based music melody automatic generation system. The system comprises an intention analysis and feature mapping module, which is used for converting a user intention into a structured semantic feature; an emotion evolution state machine module, which is used for dynamically generating a time-series emotion state vector according to the semantic feature; a hierarchical controllable generation network module, which is used for generating a note sequence with specific styles, coherent emotions and diversity based on the semantic feature and the emotion state vector; and a post-processing and music theory constraint module, which is used for performing compliance correction and optimization on the note sequence. The application can generate a melody with coherent emotion evolution logic, high matching of a user intention, various styles and compliance with music theory.

The present application belongs to the field of program control, and particularly relates to a music fountain intelligent control method and system. The method comprises: obtaining real-time state data of a music fountain system and audio data of music to be played, framing the music audio data and extracting the composite acoustic characteristics of each frame to obtain future music characteristics in a target prediction time domain; at each control sampling time, calculating a target terminal state according to the beat strength and the harmonic feature of the future music characteristics, obtaining a terminal invariant set centered on the state as a terminal constraint; constructing a performance target function, combining the transient change rate of the future music characteristics and the harmonic entropy adjustment function to adjust the weights of the punishment water type change rate and the state deviation; online solving an optimal control problem of minimizing the target function under the terminal constraint to obtain a control sequence for driving the water pump and the valve. The present application can balance the smoothness and fluency of the waterscape and the dynamic expressiveness of the music, and improve the overall artistic effect of the music fountain.

The invention discloses a harmonic texture and sequence reasoning fused audio-to-MIDI method and system, and relates to the technical field of audio processing. Aiming at the problem of insufficient transcription accuracy of the existing polyphonic music, the method comprises the following steps: carrying out time-frequency transformation on the polyphonic music to generate a spectrogram; constructing a time-frequency target detection network, detecting notes based on harmonic comb texture features, and outputting a time-frequency bounding box; constructing a sequence inference network to extract time sequence context features; carrying out local alignment and weighted fusion on the time sequence context features by using a time-frequency bounding box by adopting an ROI-guided gating fusion mechanism; and inputting the fusion features into a decoder to generate an MIDI sequence, and correcting the note time value by using a time-frequency bounding box. According to the method, the visual texture features and the music sequence logic are effectively fused, and the time precision and robustness of polyphonic music transcription are remarkably improved.

The invention discloses a system and a method for driving hands and body postures of a human body through audio, and aims to solve the problems of difficulty in rhythm and semantic decoupling and lack of expressive force of actions in the prior art. The core of the scheme lies in a double-path parallel mapping module: one path is a rhythm-motion synchronization path which efficiently maps audio physical characteristics into a'dynamic envelope vector 'for controlling motion dynamics; the second path is an emotion-semantic coding path, and the audio content is coded into a posture prototype sequence representing a posture shape by using a depth model; and then, a cross-channel attention fusion module uses the dynamic envelope vector as a query to perform dynamic weighted fusion on the attitude prototype sequence to generate a structured attitude potential representation. Finally, the attitude decoder synthesizes the representation into a smooth, natural and highly synchronous three-dimensional human skeleton animation with the audio. According to the method, through a decoupling and cooperation mechanism, the music, diversity and reality sense of the generated attitude are remarkably improved.

The application relates to a user operation method and device by music rhythm recognition, electronic equipment and medium, and belongs to the technical field of information recognition. The method comprises the following steps: generating a demonstration melody by combination according to at least one first non-rhythm melody, a rhythm melody and at least one second non-rhythm melody arranged in sequence; generating an operation melody by combination according to the at least one first non-rhythm melody, a blank melody and the at least one second non-rhythm melody arranged in sequence, wherein the time length of the blank melody is equal to that of the rhythm melody; playing the demonstration melody and the operation melody in sequence, obtaining operation information of a blind user who imitates the rhythm melody when the blank melody is played; judging whether the operation information matches the rhythm melody, if yes, changing a parameter value of a target object; otherwise, determining that the operation information is wrong. The application has the effect that a blind user can accurately and quickly operate a target object.

This application discloses a method for generating musical audio, a computer device, and a computer storage medium. Based on a currently set musical scene, chord progressions and musical structures are generated. According to the musical characteristics represented by each melodic fragment, motivic melodic fragments are determined from each melodic fragment. These motivic melodic fragments serve as musical motifs corresponding to the musical scene. The motivic melodic fragments are arranged according to the musical structure to reproduce the motivic motif, resulting in a sequence of melodic fragments. At least one interpolated melodic fragment is added to the sequence of melodic fragments based on chord progressions to develop the motivic motif, resulting in a musical audio file that matches the musical scene. The arrangement of the music can be flexibly changed according to the user's listening scenario and needs. The user only needs to set the musical scene, without needing to change the music arrangement template or understand the technical terminology of music arrangement. This reduces the time spent on music generation and improves the efficiency of music generation.

The invention discloses a folk music style identification method and system and a storage medium. The folk music style identification is realized by analyzing an audio signal. Calculating a short-time energy envelope change rate to obtain a transient intensity factor, and weighting the periodic difference function by using the factor; cumulative mean normalization processing is carried out on the corrected difference function, and harmonic structure stability is calculated to screen fundamental frequency candidate points; global tonality probability distribution is calculated based on all candidate points, a state transition matrix considering a frequency difference value and tonality coordination degree is constructed, and an optimal fundamental frequency sequence is decoded; and dividing the sequence into a playing technique fragment and a melody stable fragment according to the transient intensity factor, extracting a feature subset to form a feature vector, and inputting a classification model to output a style identification result.

The invention relates to the technical field of intelligent music teaching, and discloses a music teaching system based on artificial intelligence, and the system comprises the steps: obtaining an audio recorded by a user through a dialect, extracting musical scales in the audio according to a time sequence, forming a musical scale sequence, constructing a plurality of musical scale segments, and grouping the musical scale segments according to segment lengths; comparing the musical scale fragments with the library musical scale sequences of the songs in the music library, counting the number of matching times, and calculating the matching degree of the songs in the music library in combination with the number of matching times and the fragment lengths of the musical scale fragments; monitoring the current last musical scale of the song created by the user, obtaining a historical musical scale sequence of the last musical scale according to a set repetition judgment threshold value, comparing the historical musical scale sequence with the target song, and prompting the repetition level to the user; and according to the repetition level of the created song, combining with a comparison result of the historical musical scale sequence and the target song, generating a subsequent musical scale for guiding a user to create, thereby realizing high-precision identification and personalized recommendation of the song melody.

The invention discloses a music score conversion method, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring a target song audio; performing lyric time value prediction on the target song audio to obtain a lyric word sequence and a time value corresponding to each lyric word in the lyric word sequence; performing pitch quantity prediction on the target song audio to obtain a pitch quantity corresponding to each lyric word in the lyric word sequence; determining a pitch value corresponding to each lyric word in the lyric word sequence based on the hour value and the pitch quantity corresponding to each lyric word; and generating a music score corresponding to the target song audio based on the lyric word sequence and the hour value and the pitch value corresponding to each lyric word in the lyric word sequence. According to the invention, the operation process of music spectrum conversion is simplified, and the accuracy of music spectrum conversion is improved.

The application discloses a kind of electronic organ dynamic music score generation and keyboard highlight guiding method and system, method includes receiving user input music and difficulty parameter, and pre-processing;Adopt the multi-audio track separation and chord inference algorithm based on deep learning, extract the music features including melody, chord and rhythm in pre-processed music;Adopt multi-modal Transformer model, generate dynamic electronic organ music score according to the music features and difficulty parameter, and adjust music score content according to note density and rhythm complexity;According to electronic organ music score, the keyboard that needs to be played is indicated using light system on electronic organ;Through the collection user's keying speed and accuracy, evaluate user skill level, and adjust electronic organ music score difficulty according to evaluation result in real time;Adopt music generation Transformer technology to generate accompaniment note sequence, and provide a variety of accompaniment instrument options and style adjustment options according to user preference.The application can realize full-process automation and personalized learning.

The application discloses a drama aria audio score recording method and system, electronic equipment and a storage medium, and relates to the field of voiceprint splicing. The method comprises the following steps: a multi-modal feature extraction step, an adversarial training score step, a hierarchical transfer learning adaptation step, a streaming processing and multi-modal verification step, and a symbol-parameter decoupling output step. The multi-modal feature extraction step comprises attention weighted fusion and dynamic adjustment of time-frequency feature contribution degree. The adversarial training score step comprises checking a symbol sequence in a score through a drama music knowledge graph. The hierarchical transfer learning adaptation step comprises adaptation training of different drama types. The streaming processing and multi-modal verification step comprises multi-modal alignment, and dynamic adjustment of the weight of model output and a rule template according to a voting result. The symbol-parameter decoupling output step comprises symbol-parameter decoupling, and output of score data in a target format.

The invention relates to the technical field of intelligent music, and discloses a piano melody deviation intelligent chord switching method for original melody of multi-style to-be-played music, and the method comprises the steps: converting to-be-played music input into a discrete note event sequence; inferring a core hypothesis including a style vector and an original melody parameter set based on the sequence, and generating a candidate accompaniment chord set; calculating a total acoustic roughness for quantifying acoustic conflicts between melody deviations caused by the original melody parameter set and standard twelve-average melody chords and adaptively selecting and outputting a final chord through a multi-objective utility function according to the total acoustic roughness and a style vector. According to the method, the acoustic conflict between the original melody deviation and the standard melody chord is quantified, and the style-adaptive decision model is applied, so that the accompaniment chord with acoustics coordination and style matching is intelligently switched out while the original melody characteristics of the melody are reserved, and the music, style adaptability and auditory sense coordination degree of automatic accompaniment can be improved.

The invention relates to a music generation method, a music generation device, electronic equipment and a storage medium. The music generation method comprises the steps that music structure information is acquired, the music structure information comprises the number of music bars of music, the number of notes included in each music bar and a chord mark corresponding to each music bar, and the chord marks represent chords corresponding to the corresponding music bars. According to the music structure information, a first music score sequence is obtained, the first music score sequence comprises a plurality of music bars, a plurality of notes included in each music bar and chord marks corresponding to each music bar, the number of the music bars is consistent with the number of the music bars, and the number of the notes corresponding to each music bar is consistent with the number of the notes; the plurality of notes corresponding to each music bar are consistent with the chords corresponding to the corresponding music bar in music expression. And converting the first music score sequence into target audio data. According to the invention, the music generation effect is more controllable.

The invention relates to the technical field of artificial intelligence, and discloses a music generation model training method, which comprises the following steps: S1, extracting harmony, rhythm and curve form theoretical characteristics of an input music sequence; s2, constructing a dynamic music theory constraint field, and fusing the spatio-temporal evolution law of the theoretical characteristics; s3, designing a gating constraint generator, and injecting the constraint field state into a music generation process; s4, establishing a dynamic optimization objective function containing theoretical constraint terms; s5, generating and screening a theoretical boundary sample through reverse disturbance; s6, implementing a double-loop iteration mechanism of generation training and theoretical evolution; s7, realizing generation capability migration of the cross-music theory system; the S1 comprises the following steps: extracting chord features by adopting a two-way circulation network; and coding the rhythm mode through depth separable convolution. According to the method, self-adaptive balance of theoretical guidance and artistic innovation is realized through a constraint field and chaotic scheduling, and the dual problems of stiff generated music and rule conflicts are solved.

The invention discloses a no-reference sound correction method based on a music score big language model, and relates to a mismatch song correction method in the technical field of intelligent audio processing. The objective of the invention is to solve the problems of poor pitch and rhythm collaborative correction effect, low note feature extraction precision and easy loss of emotional expression in a non-reference scene in the existing sound correction technology. The method comprises the following steps: S1, acquiring and preprocessing off-tune singing audio data; s2, carrying out note accurate segmentation on the preprocessed audio; s3, note level features are extracted, and Octuple-MIDI symbolization input is generated; s4, realizing non-reference pitch-rhythm joint error correction through a music score big language model, and outputting a standard MIDI sequence; s5, based on a standard MIDI sequence, completing cooperative accurate correction of the sound pitch and the rhythm of the song; and S6, outputting the natural corrected singing sound through a high-fidelity synthesis technology. The method is used in the field of off-tune singing processing such as karaoke entertainment, AI music creation, singing sound correction and the like.

The invention discloses an electronic organ dynamic music score generation and key highlight guiding method and system, and the method comprises the steps: receiving music and difficulty parameters inputted by a user, and carrying out the preprocessing; a multi-track separation and chord reasoning algorithm based on deep learning is adopted, and music features including melody, chord and rhythm in the preprocessed music are extracted; generating a dynamic electronic organ music score according to the music characteristics and the difficulty parameters by adopting a multi-mode Transform model, and adjusting the content of the music score according to the note density and the rhythm complexity; according to the electronic organ music score, a lighting system on the electronic organ is used for indicating keys needing to be played; the skill level of the user is evaluated by collecting the key pressing speed and accuracy of the user, and the electronic organ music score difficulty is adjusted in real time according to the evaluation result; a music generation Transform technology is adopted to generate an accompaniment note sequence, and various accompaniment instrument options and style adjustment options are provided according to user preferences. According to the invention, full-process automation and personalized learning can be realized.

The invention relates to the field of music artificial intelligence, and discloses an intelligent music generation algorithm dynamically adapting to environment emotions, which comprises the following steps: acquiring emotional state information of a user in a current environment, and constructing an emotional state function changing along with time for describing an emotional change trend of the user in continuous time; inputting the emotional state function into a pre-trained emotional mapping model to obtain a corresponding music control vector sequence, the control vector sequence being defined in a Lie algebra space of music control parameters; the invention also discloses an intelligent music generation system dynamically adapting to the environmental emotion. The system comprises an emotion recognition module; an emotion mapping module; a track embedding module; a music generation module; and a feedback control module. According to the method, the Lie group trajectory modeling and user emotion feedback fine tuning mechanism is introduced, so that the structural continuity of melody generation and dynamic self-adaption of emotion response are realized.

The present invention relates to a method for generating music data on the basis of text data, an apparatus for generating music data on the basis of text data, an electronic device, a computer-readable storage medium, and a computer program product. The method comprises: on the basis of text data for describing music information or a melody, determining information for describing musical symbols of music data to be generated, wherein the information for describing musical symbols of said music data comprises at least one of the following two: a music parameter set for describing attributes of the musical symbols of said music data, and a musical symbol sequence for describing melody characteristics of said music data; and on the basis of the information for describing the musical symbols of said music data, determining music data in the form of the musical symbol sequence.

The present invention discloses a method for synchronizing music score with audio and a computer-readable storage medium. The method comprises: extracting a main melody track of the audio to be synchronized; extracting the pitch based on the main melody track to obtain a note sequence and the start and end times of each group of main melody notes in the note sequence, wherein the start and end times of the same group of main melody notes are consistent; comparing the note sequence with the music score corresponding to the audio to be synchronized, determining the correspondence between each group of main melody notes in the note sequence and each group of music score notes in the music score, wherein the same group of music score notes are music score notes that need to be played at the same time; and when playing the audio to be synchronized, determining the music score notes corresponding to the current playback time based on the start and end times and the correspondence between each group of main melody notes, and highlighting the corresponding music score notes or the measure in which they are located in the music score. The present invention can achieve music score and audio synchronization.

The invention relates to the field of digital music scores, in particular to a finger score generation and display method, computer equipment and a storage medium. The method comprises the following steps: obtaining a music score to be converted, and extracting the pitch, time value and playing fingering of each note from the music score; the fingering is used for indicating hands and fingers for playing notes; dividing the keyboard into a plurality of sound groups, and allocating different first display features to different sound groups; and / or, different second display features are assigned to different hand parts; based on the first display feature and / or the second display feature, according to the pitch of each note and / or the allocated playing hand, generating a frame body corresponding to each note; according to the arrangement sequence and the beat positions of the notes in the stave, the frame bodies are spatially arranged in the stave; and displaying the first identifier and the second identifier in each frame in an overlapping manner to obtain a finger score corresponding to the music score to be converted. The visual and clear mapping relation among the score surface, the fingering and the keys is realized, and the learning and playing threshold is reduced.

A method, an apparatus, a device, and a storage medium for training a model are provided. First audio content associated with vocal content is extracted from a music sample. First annotation information is generated based on the first audio content, and the first annotation information includes text content corresponding to the first audio content and first melody information of the first audio content. A first training sequence is constructed based on the text content and the first melody information. The first training sequence is input to a music generation model to generate a first set of music encoded representations. The music generation model is trained based on the first set of music encoded representations and a second set of music encoded representations of the music sample.