124 results about "Voice Training" patented technology

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.

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.

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.

The invention belongs to the technical field of finance, medical treatment and artificial intelligence, and discloses a voice recognition model training method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining specific task voice training data, defining a specific task input instruction according to a specific scene of voice recognition, adjusting an input format of a prior text sequence of the pre-trained speech recognition model; inputting the prior text sequence with the adjusted input format and the audio coding vector into a decoder of a pre-training speech recognition model for decoding, and predicting a character sequence output by the pre-training speech recognition model according to a decoding result; defining a monotonicity limitation loss function according to the predicted character sequence, and constructing a target loss function based on the defined monotonicity limitation loss function; and updating the voice recognition model during training based on the target loss function to obtain a trained voice recognition model. According to the invention, the speech recognition accuracy of the speech recognition model in a specific scene is improved.

The invention relates to the technical field of rehabilitation training, in particular to a multi-logic interaction system for speech disorder rehabilitation training, which comprises a voice accuracy analysis module, a voice mouth shape comparison module, a training item distribution module, a training difficulty adjustment module and a review interval optimization module. By capturing and analyzing the pronunciation information of the user in real time, pronunciation errors can be accurately recognized and corrected, the pertinence and efficiency of voice training are enhanced, a patient can visualize the pronunciation errors by combining voice data with a mouth shape image, and meanwhile, by comparing standard pronunciation images, the pronunciation errors can be accurately recognized and corrected. According to the method, integration of voice and visual information is enhanced, each patient can obtain a rehabilitation scheme meeting target requirements and ability through intelligent distribution of training content and time and dynamic adjustment of training difficulty, training distribution and difficulty adjustment are optimized, a user can train in a proper rhythm, and the training efficiency is improved. And the individuation level and the overall effect of speech disorder rehabilitation training are improved.

The invention belongs to the technical field of electronic teaching aids, and discloses a voice training system and a data training method after complete denture repair, and the system comprises a feedback analysis and decision device which is used for carrying out the error classification of a used object, and obtaining the type of a high-frequency problem through a clustering algorithm; the dynamic content generation engine is used for recording a historical error pattern of the use object, presetting pronunciation training logic and generating personalized training content; the intelligent difficulty adjusting device is used for adopting a dynamic difficulty algorithm: scoring according to a result of a use object, and automatically adjusting the level difficulty; and the adaptive content generator is used for analyzing the pronunciation content of the use object, identifying wrong phonemes or grammar problems, and generating training content according with difficulty in real time according to the current level and error type of the use object. The method can help a user to recover clear voice as soon as possible, improves the use enthusiasm, and can solve the problems that personalized training is not available, real-time monitoring and feedback cannot be performed, and pronunciation cannot be corrected in time.

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.

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.

The invention provides a voice training scheme generation method and system. The method is applied to the technical field of voice training, and comprises the following steps: acquiring voice data, voice signals and physiological feature data related to voice generation, and performing preprocessing; extracting time domain and frequency domain features from the preprocessed data, wherein the time domain features comprise fundamental frequency, peak amplitude, signal energy and the like; the frequency domain characteristics comprise a harmonic noise ratio, a fast Fourier transform median, energy distribution of a voice signal in each frequency band, a frequency spectrum centroid, a width of the frequency spectrum centroid and the like; screening high-discrimination features from the initially extracted time domain features and frequency domain features through backward / forward sequence feature selection to construct an optimized feature set, and inputting the optimized feature set into an improved S4 neural network model for training; and analyzing the voice type based on the trained model, dynamically generating a personalized voice training scheme, and performing dynamic adjustment. According to the invention, the accuracy, adaptability and robustness of the voice training scheme are improved.

The invention discloses a training method and system and an application method and system of a voice conversion model based on data distillation. The method comprises the following steps: establishing a voice training data set, and training an original voice conversion model by using the voice training data set to obtain an initial voice conversion model; establishing a voice evaluation data set, and inputting the voice evaluation data set into the initial voice conversion model to obtain conversion voice data of each corresponding speaker; calculating a voice conversion score of each speaker; judging whether the voice conversion score of each speaker reaches a preset condition or not; if not, removing the voice data corresponding to the speaker from the voice training data set, and taking the remaining voice data as a voice database; repeatedly training; and taking the initial voice conversion model and the voice database as a trained voice conversion model and a final voice database respectively. The voice conversion model and the voice database obtained through training of the method can support conversion of various timbres, and the voice conversion effect is good.

A speech recognition module receives training data of speech and creates a representation for individual words, non-words, phonemes, and any combination. A set of speech processing detectors analyze the training data of speech from humans communicating. The set of speech processing detectors detect speech parameters that are indicative of paralinguistic effects on top of enunciated words, phonemes, and non-words in the audio stream. One or more machine learning models undergo supervised machine learning on their neural network to train on how to associate one or more mark-up markers with a textual representation, for each individual word, individual non-word, individual phoneme, and any combinations of these, that was enunciated with a particular paralinguistic effect. Each mark-up marker can correspond to its own paralinguistic effect.

An endoscope with voice control. A data processor for the endoscope obtains voice training data for a specific surgeon, and / or information indicating spoken utterances associated with a surgical procedure for which the endoscope is to be used. Voice utterances signals are received from a surgeon during the surgery. Speech recognition technology decodes the voice utterance signals into commands to control the endoscope, based at least in part on the data obtained from the database, and control commands are issued to implement the decoded voice utterances. Concurrently with the accepting and decoding of voice utterances, the processor accepts and decodes control signals from at least one other input device. The processor issues control commands to components of the endoscope to implement the decoded other input control signals. The voice utterances are accepted, decoded, and executed concurrently with the other input control signals.

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.

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.

The invention discloses a voice clone model generation method and device, a storage medium and computer equipment, relates to the technical field of voice synthesis and medical treatment, and mainly aims at solving the problems that a voice clone model trained by an existing method is relatively weak in noisy voice recognition capability and insufficient in robustness. The method mainly comprises the steps of obtaining a voice training sample set; a training model of the voice cloning model is constructed, and the training model of the voice cloning model comprises an initial speaker encoder, a self-supervised voice representation learning model and an initial voice synthesizer; training an initial speaker encoder and an initial voice synthesizer by using a natural voice training sample and a recognition result of a self-supervised voice representation learning model on the natural voice training sample; and extracting a speaker encoder and a voice synthesizer in the training model of the voice clone model, and generating the voice clone model according to the speaker encoder, the voice synthesizer and the text encoder. The method is mainly used for training a speech clone model.

The invention provides a voice activity detection method and system, a terminal and a storage medium, and relates to the technical field of voice data processing, in particular to a voice activity detection method, which comprises the following steps: acquiring a voice training sample carrying a voice tag; performing feature extraction according to the voice training sample to obtain a root sign amplitude spectrum feature sample and an Fbank feature sample; a voice activity detection model is constructed, and the voice activity detection model is used for carrying out feature fusion on root number amplitude spectrum features and Fbank features obtained by carrying out feature extraction on the voice data to obtain fusion features, and outputting a probability value of a voice signal existing in each frame of the voice data based on the fusion features; training a voice activity detection model by using the root sign amplitude spectrum feature sample and the Fbank feature sample to obtain a trained voice activity detection model; and performing voice activity detection by using the trained voice activity detection model. According to the invention, the accuracy of voice activity detection can be improved.

The invention provides a speech enhancement method based on BGRU and reference noise, which comprises the following network structures: during reasoning, receiving two paths of input: reference noise and noisy speech, inputting the two paths of noise into an enhancement network module through a short-time Fourier transform encoder respectively to obtain noise estimation and speech estimation, performing inverse short-time Fourier transform on the voice estimation to obtain voice after noise reduction; during training, four paths of input including reference noise, noisy voice, noise truth value and voice truth value are received, the four paths of noise respectively pass through the short-time Fourier transform encoder, and the encoded reference noise and noisy voice are calculated through the enhancement network module to obtain noise estimation and voice estimation; and the encoded voice truth value, noise truth value, noise estimation and voice estimation are all sent to a 3CL loss module, loss is calculated and fed back to the enhanced network module, parameters are adjusted, and the performance of the enhanced network module is improved. According to the invention, the voice quality and intelligibility can be improved under the condition of extremely low signal-to-noise ratio.

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.

The embodiment of the invention discloses a voice partner training method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a universal cue word of voice partner training and a current cue word corresponding to a current round of dialogue in a simulation service scene in a current dial test; the current broadcast text is accurately and conveniently generated based on the general prompt word, the current prompt word and the preset text generation model, so that the generation efficiency of the current broadcast text is improved; if it is detected that the current broadcast text does not contain the last sentence identifier, determining a current broadcast voice corresponding to the current round of dialogue based on the current broadcast text, the current prompt word and a preset voice generation model; the current broadcast voice is the voice with emotions, so that the emotional effect of voice broadcast is realized; determining a current response text corresponding to the current round of dialogue based on the received current response voice of the user and a preset voice recognition model; and based on the current broadcast text, the current response text and the current cue word, determining a next cue word corresponding to the next round of dialogue.

A system for translating speech from at least two source languages into another target language provides direct speech to target language translation. The target text is converted to speech in the target language through a TTS system. The system simplifies speech recognition and translation process by providing direct translation, includes mechanisms described herein that facilitate mixed language source speech translation, and punctuating output text streams in the target language. It also in some embodiments allows translation of speech into the target language to reflect the voice of the speaker of the source speech based on characteristics of the source language speech and speaker's voice and to produce subtitled data in the target language corresponding to the source speech. The system uses models having been trained using (i) encoder-decoder architectures with attention mechanisms and training data using TTS and (ii) parallel text training data in more than two different languages.

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.

The invention discloses a speech recognition model training method and device, equipment and a readable storage medium, and relates to the technical field of artificial intelligence. Comprising the following steps: firstly, acquiring voice training data and annotation data corresponding to the voice training data; the annotation data comprises text annotation data and intention annotation data; fuzzy processing is carried out on the text labeling data, and voice features of the voice training data are extracted; and training a speech recognition model based on the speech features, the text annotation data and the intention annotation data until the speech recognition model converges. According to the method, the text annotation data is fuzzified, some characters which are not concerned about intention classification are ignored, the speech recognition model is more focused on keywords, intention classification information is introduced in the training process, and the accuracy of the recognition result generated by the speech recognition model for intention classification is improved.

1. Name of the designed product: voice training bottle (all-voice). 2. Use of the designed product: the designed product is all-voice voice training bottle. 3. Design points of the designed product: combination of shape and pattern. 4. Picture or photo best indicating the design points: perspective view.

Aspects of the subject disclosure may include, for example, generating a natural language processing model by training an automatic speech recognition (ASR) encoder with manual transcription. The training is performed by correcting and adjusting relevant factors of the ASR encoder based on determined triplet loss, classification loss and Kullback-Leibler divergence loss. In response to an ASR utterance, the trained natural language processing model generates a predicted intent associated with the ASR utterance with improved accuracy. Other embodiments are disclosed.

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.

The embodiment of the invention provides a speaker recognition method and device, equipment and a storage medium, and the method comprises the steps: obtaining a to-be-tested voice and a sample voice, and the sample voice comprises a registration voice, a training voice and a test voice; extracting a plurality of target speaker embedding vectors from the to-be-tested voice and the registered voice, and generating a target speaker embedding vector pair set; calculating a voice similarity score according to the target speaker embedded vector pair set; and recognizing a speaker corresponding to the voice to be detected according to the voice similarity score. According to the method, speaker recognition in a complex acoustic scene can be realized under the condition that a large number of computing resources are not consumed.

1. The name of this design product: Graphical user interface for voice training of electronic devices. 2. Purpose of this design product: for use in an electronic device. 3. The key design feature of this design product lies in the graphical user interface displayed on the electronic device. 4. The picture or photo that best illustrates the key points of the design: Main view of Design 1. 5. Designate Design 1 as the base design. 6. Purpose of the Graphical User Interface: This graphical user interface is used for voice training, and it can provide visual feedback of voice tone and emotions through virtual avatars. The main view of Design 1 is the initial interface of voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change the corresponding expression according to the tone and emotion of the uploaded voice, as shown in the interface change status diagram of Design 1; The main view of Design 2 is the initial interface of voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change the corresponding expression according to the tone and emotion of the uploaded voice, as shown in the interface change status diagram of Design 2; The main view of Design 3 is the initial interface of voice training. Users can upload voice by clicking the record button at the bottom of the interface. The interface The virtual avatar in the lower left corner will change its expression according to the tone and emotion of the uploaded voice, as shown in the interface change state diagram of Design 3; the main view of Design 4 is the initial interface of voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change its expression according to the tone and emotion of the uploaded voice, as shown in the interface change state diagram of Design 4; the main view of Design 5 is the initial interface of voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change its expression according to the tone and emotion of the uploaded voice, as shown in the interface change state diagram of Design 5 ; The main view of Design 6 is the initial interface of voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change the corresponding expression according to the tone and emotion of the uploaded voice, as shown in the design 6 interface change state diagram; The main view of Design 7 is the initial interface of voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change the corresponding expression according to the tone and emotion of the voice, as shown in the design 7 interface change state diagram; The main view of Design 8 is the initial interface of voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change the corresponding expression according to the tone and emotion of the voice, as shown in the design 7 interface change state diagram; The virtual avatar will change its expression according to the tone and emotion of the uploaded voice, as shown in the interface change status diagram of Design 8; the main view of Design 9 is the initial interface for voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change its expression according to the tone and emotion of the uploaded voice, as shown in the interface change status diagram of Design 9; the main view of Design 10 is the initial interface for voice training. Users can upload voice by clicking the record button at the bottom of the interface. The virtual avatar in the lower left corner of the interface will change its expression according to the tone and emotion of the uploaded voice, as shown in the interface change status diagram of Design 10.

The invention discloses a custom voice instruction recognition method and device based on a twin network and electronic equipment. Preprocessing the collected voice instruction data to obtain a voice training data set; constructing a twin network architecture; performing end-to-end joint training on the identification model and the discrimination model; deploying the trained identification model and discrimination model to the electronic equipment; performing feature extraction on the voice data, inputting the extracted features into the recognition model, and calculating to obtain a reference space vector; collecting a to-be-recognized voice signal in real time, and inputting the extracted voice features into the recognition model to calculate and obtain a detection space vector; and jointly inputting the detection space vector and the reference space vector into a discrimination model, calculating to obtain a discrimination value, comparing the discrimination value with a preset threshold value, and judging whether a target voice instruction is recognized or not according to a comparison result. The user-defined voice recognition instruction can be newly added on the basis of the preset voice instruction, the voice recognition effect is optimized, and the user interaction experience is improved.

The utility model relates to a blowpipe device for assisting in voice training, which aims to solve the technical problems that in the conventional voice blowpipe training, water is easy to choke and accurate measurement cannot be realized, and adopts the technical scheme that the blowpipe device comprises a bottle body, a bottle cap and a suction pipe, bottle body scale marks are arranged on the bottle body, a suction pipe insertion hole is formed in the middle of the bottle cap, and a through groove is formed in the side wall of the suction pipe insertion hole; the suction tube comprises a suction tube body, a clamping block and a blocking piece, the clamping block is fixedly arranged on the side wall of the suction tube body, the clamping block is matched with the through groove, the suction tube is provided with suction tube scale marks, the suction tube scale marks correspond to the clamping block in position, the lower end of the suction tube body is an oblique notch, and the blocking piece is hinged to the oblique notch through a connecting rod. When the blocking piece is completely opened, the included angle between the blocking piece and the oblique notch is an acute angle. The scale marks are arranged on the bottle body and the suction tube, so that training is quantized, and accurate measurement and recording are facilitated; the lower end of the suction tube is provided with a baffle to prevent the patient from bucking in the training process.

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.