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

84 results about "Speech training" patented technology

Speech recognition model optimization method and device based on reinforcement learning, equipment and medium

The invention discloses a voice recognition model optimization method and device based on reinforcement learning, equipment and a medium, and relates to the technical field of voice recognition, and the method comprises the steps: determining a current optimization strategy of a current time step; randomly selecting one piece of enhanced speech training data and corresponding real text training data from the data training set as target training data, and inputting the target training data into the current automatic speech recognition model for prediction to obtain a plurality of prediction texts output by the current automatic speech recognition model; determining a text matching degree and a semantic similarity between each prediction text and real text training data to obtain a group of target reward values, updating an optimization strategy at the current moment based on the target reward values, and skipping to execute the step of determining the current optimization strategy of the current time step to obtain a target reward value; and outputting the corresponding optimized automatic speech recognition model until the current automatic speech recognition model meets the optimization ending condition. And reasonable optimization of the automatic speech recognition model is realized.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

AI-driven personalized voice training and pronunciation correction system

The invention provides an AI-driven personalized voice training and pronunciation correction system. The system firstly collects original voice data of a user in a voice training process, and extracts multi-dimensional voice feature vectors including pitch, speed, intonation, formant parameters and corresponding texts; based on the feature vector, recognizing a context tag where the current voice is located, and constructing a pronunciation feature vector of the user; the system further calls a standard pronunciation database according to the context tag, generates a target pronunciation feature vector under the corresponding context, and performs multi-dimensional comparison on the user pronunciation and the target pronunciation to obtain a difference parameter set containing pronunciation parts, speed and emotional differences; finally, the system generates correction suggestions including pronunciation action guidance, intonation adjustment prompts and semantic emotion enhancement instructions, and receives user feedback information to improve the personalized training effect; according to the invention, accurate pronunciation correction under context perception can be realized, and the personalized and intelligent level of voice training is enhanced.
Owner:GUANGZHOU SENJI SOFTWARE TECH CO LTD

Speech recognition model training method and device, equipment and storage medium

The invention discloses a voice recognition model training method and device, equipment and a storage medium, and relates to the technical field of voice recognition, and the method comprises the steps: processing an initial audio signal through employing a preset audio processing mode, processing the obtained target feature sequence based on an acoustic feature consistency constraint condition, an identification accuracy constraint condition and a teacher-student comparison constraint condition to obtain initial voice training data; processing the initial voice training data by using a voice synthesis center, and processing the obtained to-be-processed voice training data by using a preset acoustic scene simulation system to obtain to-be-enhanced voice training data; and processing the to-be-enhanced speech training data based on the word level by using an attention enhancement mechanism to obtain word enhanced speech training data, processing the word enhanced speech training data based on the sentence level by using a contrast learning framework, and training the initial speech recognition model by using the obtained target speech training data to obtain a target speech recognition model. Therefore, the efficiency of training the speech recognition model can be improved.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

Speech training method and system based on artificial intelligence and application

The invention discloses a speech training method and system based on artificial intelligence and application, and relates to the field of speech training, and the method comprises the steps: obtaining multi-modal data in real time when a user reads each training statement in each speech training process; obtaining a real-time multi-dimensional speech evaluation result according to the multi-modal data, and judging whether a next training statement exists in a speech training scheme in each speech training process or not; if not, generating a multi-dimensional speech evaluation result of each speech training process; if yes, the difficulty of the next training statement in the speech training scheme is adaptively and dynamically adjusted according to the real-time multi-dimensional speech evaluation result; and outputting the next training statement according to the adjusted speech training scheme, and repeating the steps until the next training statement does not exist in each speech training. The speech training scheme can be adaptively adjusted in real time in the speech training process, and the user experience, the participation degree and the training effect are remarkably improved.
Owner:CHANGSHA LIANYU TECHNOLOGY CO LTD

Synthetically generating inner speech training data

Methods and systems are disclosed for synthetically generating inner speech training data. The methods and systems access a collection of overt speech signals representing phonemes, phoneme sounds, words or phrases spoken at least partially using overt speech. The methods and systems transform the collection of overt speech signals into inner speech training data comprising electromyograph (EMG) data representing inner speech corresponding to the phonemes, phoneme sounds, words or phrases spoken at least partially using the overt speech. The methods and systems train a machine learning model to decode inner speech signals into a set of corresponding phonemes, phoneme sounds, words or phrases based on the inner speech training data.
Owner:SNAP INC

Keyword data augmentation tool for natural language processing

Techniques for keyword data augmentation for training chatbot systems in natural language processing. In one particular aspect, a method is provided that includes receiving a training set of utterances for training a machine-learning model to identify one or more intents for one or more utterances, augmenting the training set of utterances with out-of-domain (OOD) examples. The augmenting includes: identifying keywords within utterances of the training set of utterances, generating a set of OOD examples with the identified keywords, filtering out OOD examples from the set of OOD examples that have a context substantially similar to context of the utterances of the training set of utterances, and incorporating the set of OOD examples without the filtered OOD examples into the training set of utterances to generate an augmented training set of utterances. Thereafter, the machine-learning model is trained using the augmented training set of utterances.
Owner:ORACLE INT CORP

Phoneme alignment model training and speech synthesis method and device, equipment and medium

The invention relates to the technical field of speech synthesis, in particular to a phoneme alignment model training and speech synthesis method and device, equipment and a medium. The method comprises the following steps: performing convolution attention alignment on spectrum feature information and text feature information obtained according to voice training data to obtain a first alignment matrix; monotonic alignment search is executed based on the first alignment matrix to generate a second alignment matrix, wherein the second alignment matrix is a binary hard attention matrix; calculating relative entropy loss according to the first alignment matrix and the second alignment matrix; expanding the text feature information to a Mel spectrum frame length according to the second alignment matrix, and performing linear transformation on the expanded text feature information to generate a predicted Mel spectrum; calculating Mel loss according to the spectrum feature information and the predicted Mel spectrum; and training the phoneme alignment model according to the relative entropy loss and the Mel loss until a preset convergence condition is met. By adopting the method, the phoneme alignment accuracy can be improved, and the speech synthesis accuracy is further improved.
Owner:SHANGHAI PAIDI INTELLIGENT TECH CO LTD

Language training hearing aid system carrying AI speech anomaly evaluation algorithm

The invention discloses a speech training hearing aid system carrying an AI speech anomaly assessment algorithm, and relates to the AI speech anomaly assessment algorithm, which is characterized in that comprehensive hearing assessment is carried out by collecting a composite signal and formulating an age adaptation rule base, hearing threshold dispersion and signal-to-noise ratio attenuation are obtained, and then a hearing level assessment coefficient is obtained; daily speech evaluation is carried out by collecting speech feature data and formulating a standard speech comparison library, a daily speech anomaly evaluation model is constructed by using a convolutional neural network learning model, and then a daily speech evaluation coefficient is obtained; by collecting multi-dimensional data, professional speech evaluation is carried out, and then a professional speech evaluation coefficient is obtained; and according to the hearing level evaluation coefficient, the daily speech evaluation coefficient and the professional speech evaluation coefficient, analysis is performed to obtain an analysis result, and a comprehensive analysis scheme is formulated, so that the accuracy is greatly improved.
Owner:HANGZHOU HUIER HEARING INSTR & TECH CO LTD

Noise robustness streaming speech recognition method and model fused with speech enhancement front end

ActiveCN119601017AGood noise robustnessremove distortion effectsSpeech recognitionSpeech trainingText recognition
The invention provides a noise robustness streaming speech recognition method and model fused with a speech enhancement front end. The training method of the model comprises the following steps: acquiring a speech recognition training set; processing the speech training sample by using a causal speech enhancement network to obtain target filter bank features containing global information; processing the voice training sample by using a feature extraction method based on a filter bank to obtain original filter bank features; performing dynamic weighted fusion processing on the target filter bank features and the original filter bank features by using an attention mechanism network to obtain target fusion features containing supplementary information in the voice training sample; processing the target fusion feature by using an initial speech recognition network to obtain training text recognition information; generating a target loss result according to the target filter bank features, the training text identification information and the identification text label; and iteratively adjusting network parameters of the initial speech recognition model according to the target loss result to obtain a speech enhancement recognition model.
Owner:UNIV OF SCI & TECH OF CHINA

Speech recognition model acquisition method and device, computer equipment, readable storage medium and program product

The invention relates to a voice recognition model acquisition method and device, computer equipment, a computer readable storage medium and a computer program product, relates to the technical field of voice recognition, and can improve the training precision of a voice recognition model and the generalization ability of the model in an unlabeled application scene. The method comprises the following steps: acquiring unmarked voice training data; performing data cleaning on the voice training data to obtain cleaned voice training data; obtaining a pre-training voice recognition model, and performing pseudo-tag prediction on the cleaned voice training data through the model to obtain first voice training data with a tag; performing text error correction on a pseudo tag in the first voice training data with the tag, and performing voice correction on voice training data in the first voice training data with the tag to obtain second voice training data with the tag; and adjusting the pre-trained speech recognition model according to the second speech training data with the label to obtain a target speech recognition model.
Owner:GUANGZHOU QUYAN NETWORK TECH CO LTD

Voice training data acquisition method and device, equipment and medium

The invention discloses a voice training data acquisition method and device, equipment and a medium, and relates to the technical field of intelligent voice, and the method comprises the steps: splitting a multi-channel audio into single channels; background music and background noise are removed; splitting the multi-person dialogue audio into single speaker segments; punctuation adding; and the audio with the poor quality score is subjected to tone quality enhancement, so that voice training data with corpus quality can be obtained.
Owner:BEIJING YUNSHANG TECH CO LTD

Speaker verification based adaptive margin optimization method, system, and electronic device

This invention provides an adaptive margin optimization method, system, and electronic device based on speaker verification. The method includes: inputting speech training data including various speech durations into a speaker verification model; determining the loss function of the speaker verification model; adaptively optimizing the margin parameters of the loss function based on the speech durations in the speech training data and a preset target margin for each speech duration; and training the speaker verification model using the margin parameters of the adaptively optimized loss function to determine the acceptable training difficulty of the speaker verification model. This invention utilizes training speech of varying lengths to better simulate real-life scenarios. Through adaptive optimization and fine-tuning of the margin, adjusting the margin according to the duration and similarity of each speech, this method achieves good speaker verification performance for speech of different durations in real-world scenarios.
Owner:AISPEECH CO LTD

Adversarial training of keyword spotting to minimize TTS data overfitting

A method includes receiving training utterances that include non-synthetic speech training utterances and synthetic speech utterances. For each training utterance, the method includes processing, using a memorized neural network, a corresponding sequence of input audio frames to generate a hotword detection output indicating a likelihood the training utterance includes a hotword, determining a first loss based on the hotword detection output, obtaining a hidden layer feature vector for each corresponding input audio frame; processing, using a speech classification model, the hidden layer feature vectors to predict a classification output for the training utterance; and determining an adversarial loss based on the classification output predicted for the training utterance. The method also includes training the memorized neural network on the first losses and the adversarial losses to teach the memorized neural network to learn how to detect the hotword in audio and prevent overfitting of the synthetic speech training utterances.
Owner:GDM HOLDING LLC

Haptic and visual communication system for the hearing impaired

A communication method for hearing impaired communication comprising: providing a speech training device to a hearing impaired user, the speech training device configured to teach the hearing impaired user how to determine non-speech sounds. The method further includes providing a haptic output device to a hearing impaired user where the haptic output device is configured to be relasably coupled to the hearing impaired user. The haptic output device receives, a sound input signal comprising a non-speech sound and provides the haptic output signal to an actuator which is in electrical communication with the haptic output device. The actuator actuates in response to the haptic output signal and provides a haptic sensation to the hearing impaired user.
Owner:STEVENS PETER

Method for training a speech recognition model and method for speech recognition

This application relates to a method for training a speech recognition model comprising: providing a speech training data set comprising a plurality of speech data items and corresponding speech tags; providing a speech recognition model to be trained comprising a convolution neural network, a first fully connected network, a recurrent neural network and a second fully connected network which are cascade coupled together, wherein each of the networks comprises one or more network layers each having a parameter matrix; and the speech recognition model processing speech data items to generate corresponding speech recognition results; and using the speech training data set to train the speech recognition model such that the parameter matrices of at least two adjacent network layers satisfies a predetermined constraint condition; and the speech recognition model trained using at least one loss function can generate speech recognition results at an accuracy satisfying a predetermined recognition target.
Owner:MONTAGE TECH CHENGDU CO LTD

An active five-tone speech therapy system

This invention discloses an active five-tone speech therapy system, primarily targeting individuals with speech dysfunction after stroke. Its core active five-tone speech therapy has been proven in clinical trials to effectively improve spontaneous speech, auditory comprehension, repetition, and naming functions in patients with subacute and chronic aphasia following stroke. Building upon this therapy, this invention adds a module for collecting and differentiating the patient's five internal organ syndrome elements, creating a novel, online, therapist-free remote diagnosis and treatment software that integrates "patient symptom and sign information collection – five internal organ syndrome element assessment – ​​five-tone repertoire recommendation – active five-tone speech therapy – speech collection during training, accuracy and pronunciation standard assessment, training difficulty adjustment, scale evaluation, and training efficacy feedback." This invention can improve the applicability of Western classical melodic intonation therapy to Chinese aphasia patients, mobilize patients' subjective initiative, provide precise five-tone music recommendations and individualized treatment for patients with different syndrome types, enhance the rehabilitation effect and efficiency of existing speech training, reduce the workload of therapists, alleviate the medical and economic burden on patients, and lay the foundation for the development of subsequent active five-tone speech therapy remote diagnosis and treatment equipment.
Owner:FUJIAN UNIV OF TRADITIONAL CHINESE MEDICINE

An immersive eloquence expression training system based on brain-computer interface technology

The present invention provides an immersive eloquence expression training system based on brain-computer interface technology, which relates to the field of eloquence expression training, including: a multi-mode game mode creation module for creating different types of speech training games; a comprehensive evaluation and feedback module for monitoring the performance data of users in different types of speech training games, generating personalized evaluation and feedback results, and sending them to a brain science guidance and optimization module; the performance data includes voice, speech speed, intonation, body language and emotional expression; the brain science guidance and optimization module is used to monitor the user's electroencephalogram (EEG) signals, emotional state data and physiological indicators in real time through an EEG interface and an emotional sensor, and based on the personalized evaluation and feedback results, analyze the user's eloquence expression process according to the EEG signals, the emotional state data and the physiological indicators, and conduct long-term progress tracking. The present invention can effectively improve the user's eloquence expression ability.
Owner:CHINA NEW LINE EDUCATION TECH CO LTD

Speech communication aid trainer

ActiveCN309803572SSpeech trainingAcoustics
1. The name of the design product: speech communication auxiliary training device. 2. The use of the design product: for speech training or auxiliary communication for people with language barriers. 3. The design points of the design product: in shape. 4. The picture or photo that best shows the design points: perspective view 1.
Owner:谭文斯

A voice fraud detection method based on feature fusion and single classification

The present invention discloses a voice fraud detection method based on feature fusion and single classification, and the method comprises the following steps: S1: constructing an enhanced voice training set; S2: extracting the Log-Mel spectrum of the voice to be detected, using TRawNet to extract the time domain features of the voice to be detected, and fusing the two features; S3: sending the fused features to a graph attention network, modeling the information in different time domains and frequency domains, and training the entire network with a single classification loss function. The method uses a feature fusion method based on a graph attention network to combine the time domain features and frequency domain features of the voice, and models the relationship between different segments to extract more discriminative features; the proposed single classification loss function not only retains the acoustic diversity of the real voice, but also solves the problem of decreased detection capability caused by the channel effect, so that the generalization ability of the model is further enhanced.
Owner:HARBIN ENG UNIV

A speech training hearing aid system equipped with an AI speech anomaly assessment algorithm

The present invention discloses a speech training hearing aid system equipped with an AI speech anomaly evaluation algorithm, which relates to the AI speech anomaly evaluation algorithm. By collecting composite signals and formulating an age-adapted rule base, comprehensive hearing evaluation is carried out to obtain the hearing threshold dispersion and the signal-to-noise ratio attenuation amount, and then the hearing level evaluation coefficient is obtained; by collecting speech feature data and formulating a standard speech comparison library, daily speech evaluation is carried out, and a daily speech anomaly evaluation model is constructed using a convolutional neural network learning model, and then the daily speech evaluation coefficient is obtained; by collecting multi-dimensional data, professional speech evaluation is carried out, and then the professional speech evaluation coefficient is obtained; according to the hearing level evaluation coefficient, the daily speech evaluation coefficient and the professional speech evaluation coefficient, analysis is carried out to obtain the analysis result, and a comprehensive analysis plan is formulated, greatly improving the accuracy.
Owner:HANGZHOU HUIER HEARING INSTR & TECH CO LTD

A teacher classroom instruction recognition method and system based on classifier integration

The present invention discloses a method and system for identifying teacher's classroom instructions based on classifier integration, which obtains the teacher's speech to be identified during classroom teaching, pre-processes the acquired speech to be identified to obtain an audio segment set, then performs content recognition on the audio segment set to obtain a text set, extracts content attributes from the text set to obtain a feature vector set, and finally inputs the feature vector set into a preset integrated classifier to obtain the instruction classification result corresponding to the speech to be identified, wherein the preset integrated classifier is integrated by multiple base classifiers, and is trained with the feature vector set of speech training data as training samples and the instruction classification result corresponding to the speech training data as sample labels. The present application can realize accurate recognition of teacher's voice instructions in the classroom, which is helpful to better evaluate the teaching effect of teachers in the classroom, and measure the teacher's control over the classroom and the classroom atmosphere of the teacher.
Owner:STATE GRID JIANGSU ELECTRIC POWER CO LTD RESEARCH INSTITUTE +1

Voice large model reasoning method and device for long voice

The invention provides a large model reasoning method and device for long voices, and the method comprises the steps: obtaining a voice training signal marked with a training label, carrying out the coding of the voice training signal through an information extraction module, obtaining the original voice representation of the voice training signal, and carrying out the coding of the voice training signal according to the text content and inter-frame similarity of the original voice representation. Performing compression combination on the original voice representation to obtain compressed voice representation; inputting the compressed voice representation into a large language model, executing a reasoning task to obtain a reasoning result corresponding to the voice training signal, and constructing a loss function training information extraction module according to the reasoning result and a training label; and inputting the long voice signal into the trained information extraction module to obtain a compressed voice representation of the long voice signal, and inputting the compressed voice representation into the large language model to obtain a reasoning result corresponding to the long voice signal. According to the method, the long speech understanding capability is enhanced, and the reasoning cost and the reasoning time are greatly reduced while the high generation quality is ensured.
Owner:INST OF COMPUTING TECH CHINESE ACAD OF SCI

Speech recognition method based on bimodal mixed contrast enhancement, electronic device, chip, storage medium and program product

The application provides a speech recognition method based on bimodal mixed contrast enhancement, an electronic device, a chip, a storage medium and a program product; the method comprises the following steps: acquiring multi-modal speech training data; a bimodal mixed contrast learning model is constructed and trained, wherein samples with the same emotional label under the same mode are taken as positive sample pairs, samples with different emotional labels are taken as negative sample pairs, intra-modal contrast loss is calculated to enhance the ability of the bimodal mixed contrast learning model to distinguish intra-modal fine-grained emotional features; samples with the same emotional label under different modes are taken as positive sample pairs, samples with different emotional labels under different modes are taken as negative sample pairs, inter-modal contrast loss is calculated to realize the alignment and complementarity of different modal feature spaces; the intra-modal contrast loss and the inter-modal contrast loss are fused to obtain multi-modal mixed contrast loss, and the model parameters of the bimodal mixed contrast learning model are optimized; based on the features extracted by the bimodal mixed contrast learning model, a downstream speech recognition task is trained.
Owner:CHINA MOBILE (SUZHOU) SOFTWARE TECH CO LTD +1

Multi-dimensional AI platform intelligent voice response system using voice synthesis technology

The invention relates to the technical field of voice synthesis, in particular to a multi-dimensional AI platform intelligent voice response system using the voice synthesis technology, which screens out matched historical user question voices according to text semantic similarity corresponding to current user question voices and historical user question voices, and sends the matched historical user question voices to a user terminal. Obtaining a voice training set and the weight of each element in the voice training set according to the voice feature similarity between the question voice of the current user and the question voice of the matched historical user in combination with the user score value of the manual reply voice, training an acoustic model, obtaining a reply text corresponding to the question voice of the current user, and obtaining the question voice of the current user; and inputting into the trained acoustic model, generating a reply voice signal, and then outputting to the current user. According to the method, the voice training set is screened and constructed from historical manual reply voices, so that an acoustic model can learn a more natural and smooth voice synthesis mode, and the reply voice signal contains rich voice features and expression modes.
Owner:ROPEOK TECHNOLOGY GROUP CO LTD

Verbal communication aid training device

ActiveCN309812665SSpeech trainingEngineering
1. Name of the product in this design: Speech Communication Assistive Training Device. 2. Purpose of this design: To provide speech training or assist communication for people with language impairments. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.
Owner:谭文斯

A method, apparatus, device and medium for training a speech generation model

The application belongs to the field of artificial intelligence, and relates to a training method of a speech generation model, comprising the following steps: obtaining reference timbre spectrum, phoneme information and speech spectrum of a target object; training a preset initial speech generation model based on the reference timbre spectrum, the phoneme information and the speech spectrum to obtain model parameters; and adjusting parameters of a multi-timbre feature extraction network, a phoneme feature extraction network, a prosody feature discretization network, a time sequence alignment module, an attention fusion module and a speech reconstruction decoding network of the initial speech generation model based on the model parameters to construct the speech generation model. The application also provides an apparatus, a device and a medium. In addition, the application also relates to blockchain technology, and speech training data and model parameters can be stored in a blockchain. The application can realize decoupling of timbre and prosody information, and flexibly adjust the timbre and prosody information to generate synthesized speech with diversity and flexibility.
Owner:PING AN TECH (SHENZHEN) CO LTD

Synthetically generating inner speech training data

Methods and systems are disclosed for synthetically generating inner speech training data. The methods and systems access a collection of overt speech signals representing phonemes, phoneme sounds, words or phrases spoken at least partially using overt speech. The methods and systems transform the collection of overt speech signals into inner speech training data comprising electromyograph (EMG) data representing inner speech corresponding to the phonemes, phoneme sounds, words or phrases spoken at least partially using the overt speech. The methods and systems train a machine learning model to decode inner speech signals into a set of corresponding phonemes, phoneme sounds, words or phrases based on the inner speech training data.
Owner:SNAP INC

Speech and singing synthesis method, training method and device, model

The present application discloses a speech and singing synthesis method, a training method and device, and a model. The training method includes: obtaining speech training data; obtaining singing training data; converting text data into text embedding codes, converting speech data into speech embedding codes; splicing text embedding codes and speech embedding codes into speech training code data; dividing lyrics data into sentences and converting the sentences into sentence embedding codes, dividing singing data into singing segments corresponding to the sentences and converting the singing segments into singing segment embedding codes, extracting pitch sequences corresponding to the sentences and / or singing segments from the music score data and converting the pitch sequences into pitch embedding codes; splicing the sentence embedding codes, singing segment embedding codes, and pitch embedding codes into singing training code data; inputting the speech training code data and singing training code data into the speech and singing synthesis module of the initial model for training to obtain a trained target model.
Owner:SHANGHAI XIYU JIZHI TECH CO LTD

Speech enhancement method and device based on time-frequency domain feature fusion, and electronic equipment

The invention discloses a speech enhancement method and device based on time-frequency domain feature fusion and electronic equipment, and the method comprises the steps: carrying out the preprocessing of an initial speech training data set, and obtaining a target speech training data set; performing feature extraction on the target voice training data set to obtain candidate voice features; normalizing the candidate voice features to obtain target voice features; performing feature fusion on the target time domain feature and the target frequency domain feature to generate candidate fusion features; inputting the candidate fusion features into a multi-scale convolution feature enhancement module for feature enhancement, and generating to-be-trained fusion features; inputting the to-be-trained fusion features into the initial speech enhancement model for training to obtain a target speech enhancement model; and inputting the target fusion feature of the to-be-enhanced noisy speech into the target speech enhancement model to generate a target enhanced speech. The method can suppress noise interference, improves the speech enhancement effect in a complex noise scene, and can be widely applied to the technical field of speech enhancement.
Owner:GUANGDONG POLYTECHNIC NORMAL UNIV

Explanatable speech emotion recognition algorithm based on multilevel feature deentanglement

The embodiment of the invention relates to the field of speech emotion recognition, in particular to an interpretable speech emotion recognition method based on multilevel feature deentanglement. A specific embodiment of the method comprises the following steps: acquiring a voice training sample set; constructing an initial interpretable speech emotion recognition model; for a target voice training sample, executing the following training steps: inputting sample voice information into the initial feature extraction network model; inputting the initial general emotion feature information into the initial fusion multi-level emotion feature hybrid self-encoding network model; inputting the initial multi-level emotion feature information into an initial multi-level perception classification model; determining a difference value between the initial emotion label and a sample emotion label included in the target training sample; determining the initial interpretable speech emotion recognition model as a trained interpretable speech emotion recognition model; and inputting the target voice information into the interpretable voice emotion recognition model. According to the embodiment, the accuracy of speech emotion recognition can be improved.
Owner:HENAN UNIVERSITY OF TECHNOLOGY