65 results about "Speech classification" patented technology

Provided herein are systems and methods for providing instructions for speech based on speech classifications of verbal communications from users. Ae computing system can generate speech characteristics for a first verbal communication using a first audio sample from a user. The computing system can determine, from a plurality of speech classifications, a first speech classification for the first verbal communication based on the speech characteristics. The computing system can select, from a plurality of actions, an action comprising modifying one or more of the speech characteristics to define an utterance for the user based on the first speech classification. The computing system can provide an instruction presenting a message to prompt the user to perform the utterance defined by the action selected from the plurality of actions. The efficacy of the medication that the user is taking to address the condition may be increased.

The invention relates to a cross-domain voice classification method and device based on feature decoupling and multi-task learning. The method comprises the following steps: firstly, acquiring a multi-data-domain voice file, and preprocessing the multi-data-domain voice file to obtain a cross-domain voice classification data set; then, constructing a cross-domain voice classification model which comprises a voice feature encoder module, a data domain classification module, a supervised comparative learning module and a multi-task classification module; then, a joint optimization loss function is constructed based on data field classification loss, supervised contrast learning loss and task classification loss, and a gradient descent algorithm is adopted to train and optimize the cross-domain voice classification model based on the cross-domain voice classification data set and the joint optimization loss function; and finally, inputting to-be-classified voice into the trained cross-domain voice classification model to obtain a voice corresponding category. The discrimination ability and generalization ability of the model in a cross-domain scene are significantly improved, so that the model still maintains high classification precision in a complex multi-source voice environment.

The invention discloses a method and a device for identifying a risk voice call. The method comprises the following steps: acquiring a time domain signal of a voice call, and determining a first quantum state representation corresponding to the time domain signal; target features are extracted from the first quantum state representation, a self-attention matrix is constructed according to the target features, and the target features at least comprise a frequency spectrum feature, an energy feature and a fundamental frequency feature; performing weighting processing on the target features by using the self-attention matrix to obtain target quantum features; analyzing the target quantum features by using a long short-term memory network to obtain intermediate feature representation; and performing voice classification according to the intermediate feature representation to obtain a classification result, the classification result being used for reflecting whether the voice call is a risk voice call. The technical problem that a traditional voice recognition algorithm is difficult to efficiently and accurately recognize a risk voice call is solved.

A method for training a speech enhancement network, performed by an electronic device, includes: acquiring a first clean speech sample and a noise sample, and mixing them to generate a noisy speech sample; performing noise reduction on the noisy speech sample based on the speech enhancement network to obtain an enhanced speech sample; framing the enhanced speech sample into a plurality of enhanced speech frames, classifying speech effectiveness of the enhanced speech frames, and generating a first effectiveness distribution based on classification results of the enhanced speech frames; and determining a noise reduction accuracy based on the enhanced speech sample and the first clean speech sample, determining a speech classification accuracy based on the first effectiveness distribution, determining a speech enhancement accuracy based on the noise reduction accuracy and the speech classification accuracy, and training the speech enhancement network based on the speech enhancement accuracy.

The invention discloses a toxic speech detection method and system based on forgetting learning, and the method comprises the steps: firstly constructing a toxic speech classification model, dynamically tracking the classification state change of each sample in a training process, and carrying out the quantitative calculation of the total number of forgetting events; then sorting and analyzing the samples based on the forgetting frequency, and identifying and removing redundant samples which are difficult to forget so as to construct a high-quality simplified training set; and the model is retrained by using the simplified data set, the model parameters are optimized, and the detection efficiency is improved. The system comprises a data preprocessing module, a forgetting event calculation module, a sample screening module, a model training module and a detection generation module, and a complete toxicity speech detection and optimization process is formed. According to the method, a forgetting learning mechanism is introduced, so that the defects of training data redundancy, annotation noise interference and the like in a traditional method are effectively overcome, the model training speed and generalization performance are remarkably improved while the detection accuracy is ensured, and reliable technical support is provided for online content safety management and toxic speech real-time detection.

The invention discloses a method and device for improving speech recognition accuracy, computer equipment and a storage medium, and the method comprises the steps: obtaining to-be-recognized speech data, and extracting speech features corresponding to the to-be-recognized speech data; inputting the voice features into a pre-trained voice classification model to obtain human voice data; matching the human voice data with voiceprint features of a pre-registered user; and if the matching is successful, identifying to obtain a voice instruction corresponding to the human voice data, and executing a corresponding operation based on the voice instruction. The voice data and other interference sounds (such as song sounds, navigation broadcast sounds and engine noise sounds) can be accurately distinguished, so that pure voice data can be obtained. And interference factors in a complex voice environment are effectively filtered. And the unique voiceprint feature of the target user is utilized to identify and execute the voice instruction of the specific person, so that a more stable and accurate voice interaction service is provided for the user.

The invention relates to the technical field of data processing, and discloses a voice task scheduling method, device and system and a storage medium, which are applied to a terminal air conditioner, and the method comprises the following steps: carrying out audio classification on a received voice task to obtain a voice classification task; wherein the language classification task comprises a non-awakening task; performing networking classification on the non-awakening tasks to obtain offline interaction tasks and online interaction tasks; obtaining a network connection state and a terminal load state of the terminal air conditioner; and according to the network connection state and the terminal load state, the online interaction task or the offline interaction task is unloaded to the collaborative equipment end for task processing, or the terminal air conditioner locally carries out task processing. According to the method, flexible task scheduling is carried out on the voice task, and the requirements of voice low-delay wakeup and high-reliability voice execution are effectively met.

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.

The present application belongs to the technical field of intelligent teaching, and particularly relates to a teaching quality evaluation method and system based on deep learning. The method comprises extracting feature data to be evaluated from normal speech, evaluating the feature data to be evaluated by using a speech evaluation model to generate an evaluation result, and determining the quality grade of the normal speech according to the evaluation result, wherein the feature extraction from noise speech and noise speech comprises extracting amplitude information and frequency information from a sound production section. The present application performs screening on teaching speech to identify abnormal sound sections; through voiceprint comparison, the teaching speech in which the abnormal sound sections that can match the pre-stored voiceprint are classified as noise speech, and the teaching speech that cannot be matched is classified as noise speech, so as to distinguish the noise speech originating from the background environment from the noise speech originating from the teaching subject, overcome the evaluation error problem caused by regarding the two as noise without distinction, and lay a data foundation for subsequent evaluation.

The present application discloses a speech emotion recognition method implemented based on artificial intelligence technology. The present application includes obtaining a speech feature signal corresponding to the speech to be recognized; obtaining the text to be recognized according to the speech feature signal; obtaining a speech classification result through a speech classification model based on the speech feature signal; obtaining a text classification result through a text classification model based on the text to be recognized, wherein the text classification result represents the emotion type of the speech to be recognized; determining the emotion recognition result corresponding to the speech to be recognized according to the speech classification result and the text classification result. The present application also provides a speech emotion recognition application method, related device, equipment and storage medium. The present application can not only reduce the labeled data for emotion classification relying only on speech data, but also can improve the accuracy of emotion recognition even in the case of scarce training data.

The embodiment of the invention provides a voice classification method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring target voice data and a target text of the target voice data; performing feature extraction on the target voice data to obtain emotion feature information; performing feature extraction on the semantics of the target text to obtain intermediate feature information, and converting the intermediate feature information into graph structure feature information; and classifying the target voice data according to the emotion feature information and the graph structure feature information to obtain a classification result of the target voice data. Therefore, the accuracy of voice classification can be improved.

This application relates to an effective speech detection method and apparatus based on a feature-enhanced pre-trained model. The method includes: acquiring speech to be detected containing different types of noise; inputting the speech to be detected into a first pre-trained model, and extracting effective speech features from the speech to be detected through the first pre-trained model; the first training data used by the first pre-trained model is obtained by enhancing the data features of unlabeled sample speech; inputting the effective speech features into a second pre-trained model, and performing effective speech classification through the second pre-trained model to obtain a classification result sequence; and outputting effective speech segments of the speech to be detected based on the classification result sequence; the effective speech segments are speech segments from which noise has been removed. This method can adapt to more application scenarios and noise types, effectively improving the effective speech detection effect and performance, thereby enhancing the performance of the speech recognition system.

The embodiment of the invention discloses a voice quality detection method, and the method comprises the steps: determining a voice classification result of each frame through a preset voice activity detection algorithm, dividing audio data into a voice segment and a non-voice segment, taking each frame of audio of which the classification result is the voice data in the non-voice segment as an interference frame, and carrying out the elimination. And calculating a signal-to-noise ratio of the voice segment to determine a quality detection result. And the interference frame which is misjudged as voice is eliminated from the non-voice segment, and purer noise estimation is obtained. Based on the calculated signal-to-noise ratio, the voice signal quality can be reflected more truly, and the problems of noise power overestimation and signal-to-noise ratio underestimation caused by VAD false detection are effectively solved, so that the accuracy and reliability of voice quality detection are improved.

This application relates to the field of smart home appliance technology, and discloses a method for voice-controlled air conditioners. The method includes, when a voice module receives an externally input voice command, sending the voice command to a voice classification module to determine whether the voice command is an offline voice command; if the voice command is an offline voice command, feeding the voice command back to the voice module to control the air conditioner's operation; if the voice command is not an offline voice command, transmitting the voice command to the cloud for parsing and recognition before feeding it back to the voice module to control the air conditioner's operation. By first determining whether the user's voice command is an offline voice command, and then performing the corresponding offline or online control, this avoids using online cloud AI to parse and recognize the voice command at the initial stage, reducing the frequency of using online AI for voice-controlled air conditioners and saving system resources. This application also discloses a device, an air conditioner, and a storage medium for voice-controlled air conditioners.

A vehicle system for classifying spoken utterance within a vehicle cabin as one of system-directed and non-system directed, the system may include at least one microphone configured to detect at least one acoustic utterance from at least one occupant of a vehicle, at least one sensor to detect user behavior data indicative of user behavior, and a processor programmed to: receive the acoustic utterance, classify the acoustic utterance as one of a system-directed utterance and a non-system directed utterance, determine whether the acoustic utterance was properly classified based on user behavior observed via data received from the sensor after the classification, and apply a mitigating adjustment to classifications of subsequent acoustic utterances based on an improper classification.

Systems and methods for providing instructions for speech based on speech classification of a language communication from a user are provided herein. A computing system may generate verbal features for a first language communication using a first audio sample from a user. The computing system may determine a first speech classification for the first language communication from a plurality of speech classifications based on the speech features. The computing system may select, based on the first speech classification, an action from the plurality of actions that includes improving one or more of the speech features to define a utterance to the user. The computing system may provide instructions to present a message to prompt a user to perform a utterance defined by an action selected from the plurality of actions. The efficacy of a medicament taken by a user for solving the disease may be increased.

The invention discloses an English pronunciation error correction system and device based on artificial intelligence, and relates to the field of English pronunciation error correction. The system comprises a voice acquisition module, a voice recognition module, a voice program definition judgment module, a pronunciation evaluation module, a voice classification recognition module, an error classification module, a voice processing module, a voice processing module, a voice processing module and a voice processing module, wherein the voice of a user is input and recorded through an audio acquisition module; the voice program definition judgment module judges voice program definition through a definition comprehensive scoring formula; according to the English pronunciation training system, classified input voice features are compared with standard voice features to carry out detailed error evaluation, an error correction feedback module carries out multi-dimensional integrated error correction feedback through multi-dimensional vision, hearing and characters, and a user receiving module carries out evaluation and personalized practice on English pronunciation by setting an interactive interface. According to the system, errors caused by insufficient definition and error types of pronunciation of students are prevented, and the students are helped to find error sources better and faster and correct the error sources.

The present invention discloses a method and system for testing speech signals based on laryngeal vibration and electroencephalogram (EEG) electrical stimulation, which relates to the field of speech information classification and includes: determining whether to apply EEG electrical stimulation to a user during the speech preparation stage according to the basic EEG signal; acquiring the laryngeal vibration signal and EEG signal of the user synchronously collected during the speech execution stage and respectively performing data preprocessing on them to obtain the preprocessed laryngeal vibration signal and EEG signal; using the PageRank algorithm to perform channel selection on the preprocessed EEG signal to obtain the EEG signal after channel selection; respectively performing feature extraction and dimensionality reduction processing on the preprocessed laryngeal vibration signal and the EEG signal after channel selection to obtain the laryngeal vibration features after dimensionality reduction and the EEG features after dimensionality reduction, and inputting them into the dual-modal SPCA with L1 regularization to obtain sparse features and inputting them into the trained speech signal classification model to obtain the speech classification and recognition result. The present invention solves the problem of homophony but different meanings in the pronunciation of deaf-mute people.

Provided herein are systems and methods for providing instructions for speech based on speech classifications of verbal communications from users. A computing system can generate speech characteristics for a first verbal communication using a first audio sample from a user. The computing system can determine, from a plurality of speech classifications, a first speech classification for the first verbal communication based on the speech characteristics. The computing system can select, from a plurality of actions, an action comprising modifying one or more of the speech characteristics to define an utterance for the user based on the first speech classification. The computing system can provide an instruction presenting a message to prompt the user to perform the utterance defined by the action selected from the plurality of actions. The efficacy of the medication that the user is taking to address the condition may be increased.

The present invention discloses a method and system for imaginary speech classification based on an attention-guided tensor network. Obtain imaginary speech EEG data and its corresponding label; perform data enhancement on the imaginary speech EEG data to construct a training data set; construct an attention-guided tensor network, train using the data-enhanced training set in the data set, and test using the unenhanced test set in the data set; use the trained and verified attention-guided tensor network to implement EEG imaginary speech classification. The method of the present invention combines data enhancement with the tensor network technology guided by the classification identifier of the attention mechanism to achieve high-precision imaginary speech EEG classification performance.

The present disclosure relates to a method and system for performing speech classification on an audio signal. The method includes obtaining the audio signal including a sequence of audio frames and determining, for each audio frame, a first speech confidence metric using a first speech classifier. For each given audio frame in at least a subset of the sequence of audio frames, the method includes classifying each respective audio frame in a first context window associated with the given audio frame as a speech frame or a non-speech frame by comparing the first speech confidence metric of the given audio frame to a first predetermined threshold, determining an adaptive threshold based on a number of speech frames in the first context window, and determining a first binary speech classification indicator for the given audio frame based on the first speech confidence metric and the adaptive threshold.

A method for determining a vehicle domain includes: converting a user's speech into text; and classifying the user's speech into a vehicle domain or an external domain based on the text, wherein the classifying of the user's speech into the vehicle domain or the external domain includes classifying a domain of the user's speech based on previously stored keyword-related information and then classifying the domain of the user's speech based on previously stored keyword-related information and then classifying the domain of the user's speech based on a trained domain classification model.

The present invention provides a false voice detection method, a false voice detection model acquisition method, and related equipment. The false voice detection method comprises: acquiring a target speech; and detecting whether the target speech is false voice based on a pre-acquired target false voice detection model. The target false voice detection model is trained using training speech labeled with speech categories to construct a false voice detection model. The constructed false voice detection model includes a speech encoder, a speaker characterization module that acquires a speaker characterization based on the output of the speech encoder, a false voice characterization module that acquires a false voice characterization based on the output of the speech encoder, and a speech classification module that performs speech classification based on the outputs of the speaker characterization module and the false voice characterization module. The speaker characterization module is acquired by combining a speaker classification task with the training of the speech encoder, and the speech encoder is a pre-trained speech model obtained through pre-training. The false voice detection method provided by the present invention can accurately detect whether a speech is false voice.

The invention relates to a digital semantic communication method and system for voice reconstruction and classification, and the method comprises the steps: carrying out the preprocessing of voice data, and inputting the preprocessed data into a semantic encoder formed based on a double-attention residual mechanism network; after semantic features output by the semantic encoder are processed by the channel encoder, the semantic features are mapped into digital constellation symbols by a modulator adopting a soft quantization method; after transmission through the physical channel, the modulation symbols recover features by the soft decision demodulator, and signal distortion caused by the physical channel is eliminated through the channel decoder; and the demodulated semantic features are respectively input into a semantic decoder with a symmetric architecture to realize voice reconstruction, and input into a voice classifier consisting of a lightweight feature compression network and a classification head to realize voice classification. According to the method, the feature extraction integrity is improved through a double-attention architecture, the gradient fracture problem is solved through soft quantization and soft decision, and the channel robustness is enhanced in combination with progressive signal-to-noise ratio training.

A high-precision dynamic memristor model and an application method thereof are characterized in that the memristor model is established based on a Ta2O5 memristor, and the Ta2O5 memristor comprises a bottom electrode, a functional layer and a top electrode which are sequentially attached from bottom to top; the bottom electrode is platinum, the functional layer is tantalum pentoxide, and the top electrode comprises lower tantalum and upper platinum. The memristor model has the effects that the memristor model can fit experimental data of a Ta2O5-based multi-layer device, and 2.9% of relative root-mean-square error is realized in resistance state conversion. In a voice classification task, the training accuracy rate of the method reaches 99.4%, the test accuracy rate reaches 91.6%, and the potential of neural morphology calculation of the method is proved. According to the work, the accuracy of memristor modeling is improved, and application in intelligent computing and memory systems is supported.

The invention relates to automatically determining timing windows for speech captions in an audio stream. A content system inputs segments of an audio stream to a speech classifier for classification, the speech classifier generating raw scores for the segments of the audio stream that represent a likelihood that the respective segment of the audio stream includes the presence of speech sounds. The content system generates binary scores for the audio stream based on the set of raw scores, each binary score generated based on an aggregation of the raw scores from a contiguous series of segments of the audio stream. The content system generates one or more timing windows for speech sounds in the audio stream based on the binary scores, each timing window indicating an estimate of a start and end timestamp for one or more speech sounds in the audio stream.

The embodiment of the invention provides a multi-modal classification method and system for audio semantic understanding and rejection. The method comprises the following steps: receiving a collected original audio signal; acquiring a context historical memory of the original audio signal in voice interaction, and capturing multi-dimensional features related to semantic understanding and rejection from the original audio signal and the context historical memory; inputting the multi-dimensional features into a pre-trained multi-modal classification large model, wherein the multi-modal classification large model directly determines speech recognition content, semantic classification and rejection results of the original audio signals by using the multi-dimensional features; and determining a reply result for feeding back the original audio signal based on the speech recognition content, the semantic classification and the rejection result. According to the embodiment of the invention, end-to-end processing from audio to semantic understanding and rejection is realized. The speech recognition capability and the speech classification and rejection capability are unified in the multi-modal large model, so that the calculation resources are reduced, the overall system delay is greatly reduced, and the speech recognition accuracy is also improved.

The present invention discloses a deep fake audio detection and protection method based on a large-scale pre-trained model Whisper, comprising the steps of step S1: inputting the audio to be detected into the pre-trained model Whisper, and using the transcribed text of the entire audio as a prompt during the fine-tuning process of each audio segment, so that the model Whisper can utilize global text information; step S2: pre-processing the audio data to adapt to the model Whisper during training and decoding; step S3: evaluating the performance of the model Whisper during training by designing a detection cross-entropy loss function. The deep fake audio detection and protection method based on the large-scale pre-trained model Whisper disclosed by the present invention realizes audio authenticity identification through transfer learning. Different from existing speech classification or recognition tasks, the complete transcribed text of the audio is embedded in the decoder as prompt information through an innovative fine-tuning strategy, which overcomes the problem of single reliance on traditional acoustic features.

The invention discloses a forged voice detection method and system based on voiceprint driving. Relates to the technical field of artificial intelligence voice security. The method comprises the following steps: step 1, inputting voice information, preprocessing the voice information, and extracting LFCC features of the voice information; 2, constructing a voiceprint recognition model, extracting spectrum distribution features from the LFCC features, and generating voiceprint embedding vectors; 3, constructing a forged voice detection model, fusing the LFCC features and the voiceprint embedding vectors according to a preset proportion, inputting the fused LFCC features and the voiceprint embedding vectors into the forged voice detection model for recognition, and performing true and false voice classification; and step 4, optimizing the voiceprint recognition model and the forged voice detection model through multi-target joint learning. The invention aims to improve the robustness of a forged voice detection system to a forged voice sample and improve the correct detection rate of a model to forged voice.

The present invention provides a speech recognition and classification method and system based on machine learning, which is applied to the field of data processing technology. In this application, domain feature extraction is performed on the application scenario information of the target speech to generate a classification task impact factor; time-frequency analysis processing is performed on the target speech stream information to generate a standardized speech feature matrix; feature dimension screening is performed on the standardized speech feature matrix based on the classification requirement information of the target user to generate a target acoustic feature vector; signal characteristic analysis is performed on the acquisition device information of the target speech to generate a device compensation feature vector; transfer learning is performed on a preset speech classification model based on an acoustic training set to generate an adaptive speech classification model; the classification task impact factor, the target acoustic feature vector, and the device compensation feature vector are input into the adaptive speech classification model, and feature fusion is performed through an attention mechanism to generate speech classification result information with confidence.