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

13results about How to "Improve Speech Recognition Efficiency" patented technology

Multi-model speech recognition method based on C-Adapter adapter

The invention provides a multi-model speech recognition method based on a C-Adapter adapter, and belongs to the technical field of speech recognition, and the method comprises the steps: carrying out the feature extraction of an original speech signal through an acoustic encoder, and obtaining the speech feature information; the C-Adapter adapter carries out processing according to the voice feature information, generates modal adaptation feature information and maps the modal adaptation feature information to a voice recognition space; mapping the voice recognition task characters to a voice recognition space through a text vector model, and constructing text task representation information; the modal adaptation feature information and the text task representation information in the speech recognition space are spliced, and speech information to be recognized is constructed; and recognizing the voice information to be recognized through the large language model to obtain a voice recognition result. According to the method, the combination of the speech recognition model and the large language model is realized, the accuracy of speech recognition is effectively improved, the speed of speech recognition is improved, and the requirement of converting speech into characters in real time is met while the speech recognition efficiency is improved.
Owner:BEIJING BAIGEFEICHI TECH LLC

Speech recognition method and device, storage medium and electronic equipment

PendingCN119600994AImprove experienceImprove Speech Recognition EfficiencySpeech recognitionText recognitionFeature extraction
The invention provides a voice recognition method and device, a storage medium and electronic equipment, and the method comprises the steps: calling a target pre-training model, carrying out the feature extraction of target voice data, and obtaining the voice feature of each target voice frame in the target voice data; based on the voice feature of each target voice frame, performing clustering processing on the target voice data to obtain a plurality of clustered voice features so as to determine at least one text recognition result; when the target voice data meets the streaming audio data recognition condition, determining audio data representation features under the target voice data based on the plurality of clustering voice features and the at least one text recognition result; and calling a target attention model, and determining a decoding feature of each text recognition result in the at least one text recognition result based on the audio data representation features under the target voice data, thereby determining a target voice recognition result of the target voice data. According to the embodiment of the invention, voice recognition can be quickly carried out on the target voice data.
Owner:DUXIAOMAN TECH (BEIJING) CO LTD

Artificial intelligence AI voice recognition system

InactiveCN119091871Aimprove continuityImprove Speech Recognition EfficiencySpeech recognitionData acquisitionSpeech sound
The invention discloses an artificial intelligence (AI) voice recognition system, and relates to the technical field of voice recognition. According to the artificial intelligence AI voice recognition system, when a plurality of voice questioning data are collected, the terminal analyzes the plurality of voice questioning data, and when a voice instruction is recognized and played, the terminal generates target data, and the voice questioning data can be played through the voice recognition unit. When other instructions enter, the continuity of AI voice recognition is effectively enhanced by reducing the playing sound and enhancing the recognition effect of other voice instructions, the voice answering data recognized again interferes with the playing process of the voice answering data, the voice answering data recognized wrongly can be interrupted in time, more time is saved, and the user experience is improved. The AI speech recognition efficiency is improved, the signal is enhanced, and the noise of the signal is eliminated, so that the AI speech recognition precision is remarkably improved.
Owner:DIGITAL (SHANGHAI) ENTERPRISE DEV CO LTD

Speech recognition method, apparatus, device, and storage medium

The present application relates to the field of artificial intelligence and the field of financial technology, and discloses a speech recognition method, device and equipment and a storage medium, the method comprising: splicing a first embedding vector and a second embedding vector to generate a third embedding vector, reconstructing the third embedding vector to generate a fourth embedding vector; obtaining a predicted speech recognition text output by a speech recognition model based on the fourth embedding vector, obtaining a first loss value and a second loss value between the predicted speech recognition text and a preset speech recognition text; generating a total loss value of the predicted speech recognition text according to the first loss value and the second loss value, training the speech recognition model based on the total loss value; obtaining a current speech and a current field label sent by a customer service system, inputting the current speech and the current field label into the trained speech recognition model, and obtaining a current speech recognition text output by the trained speech recognition model. The present application is beneficial to improving the efficiency of speech recognition.
Owner:PING AN TECH (SHENZHEN) CO LTD

Speech recognition method and device, electronic equipment and storage medium

ActiveCN117219063Breduce the number of elementsReduce the amount of decoding calculationsPrediction probabilitySpeech sound
Embodiments of the present application provide a speech recognition method and device, electronic equipment and storage medium, at least applied to the field of artificial intelligence and speech recognition, wherein the method comprises: performing vector coding processing on the audio feature vector of the speech to be recognized to obtain an audio coding vector; performing classification processing on the audio coding vector to obtain a prediction probability distribution of each predicted character in a preset vocabulary corresponding to each speech frame in the speech to be recognized; performing pruning processing on the audio coding vector based on the prediction probability distribution to obtain a pruned audio coding vector; and performing speech recognition on the speech to be recognized based on the pruned audio coding vector to obtain a speech recognition result. Through the present application, the decoding calculation amount in the speech recognition process can be reduced, the decoding efficiency can be improved, and thus the speech recognition efficiency can be improved.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD +1

Display device and voice pickup method

ActiveCN115334342BImprove Speech Recognition EfficiencySelective content distribution
The present application provides an embodiment, which belongs to the voice recognition technology, and provides a display device and a voice pickup method, wherein the display device includes a display; a controller connected to the display, and the controller is configured to: receive first indication information sent by the control device, the first indication information is used to indicate that the voice button of the control device is pressed for the first time; if a voice application is running in the foreground of the display device, send second indication information to the control device, the second indication information is used to instruct the control device to perform voice pickup under the first voice path, and the first voice path is used to carry the indication information of the display device; receive the first voice data picked up under the first voice path sent by the control device. Compared with the prior art, when a voice application is running in the foreground of the display device, the voice pickup can be controlled by the voice application on the display device, thereby avoiding the situation where the software and hardware trigger the voice pickup at the same time and receive invalid voice data.
Owner:VIDAA (NETHERLANDS) INT HLDG BV

Speech recognition method and device, electronic equipment and storage medium

The invention relates to the technical field of voice recognition, in particular to a voice recognition method and device, electronic equipment and a storage medium, and aims to improve the voice recognition efficiency. The method comprises the following steps: acquiring to-be-recognized voice, encoding the to-be-recognized voice through a target encoder, and acquiring candidate encoding features corresponding to the to-be-recognized voice; obtaining a blank frame probability corresponding to each voice frame in the to-be-recognized voice according to the frame distribution information of the to-be-recognized voice, and screening out at least one target frame from the to-be-recognized voice based on the obtained blank frame probability; the frame distribution information represents probability distribution of each voice frame in a dictionary space; screening out a target candidate coding feature corresponding to at least one target frame from the candidate coding features; and decoding based on the target candidate coding features to obtain a text recognition result corresponding to the to-be-recognized voice. According to the invention, the frame rate compression is carried out through the frame distribution information, only part of important frames are decoded, and the speech recognition efficiency can be effectively improved.
Owner:BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD

A speech recognition method and system for engineering project management based on artificial intelligence

The present invention relates to the technical field of project management, and in particular to an artificial intelligence-based engineering project management and control voice recognition method and system, the method comprising: a staff member sends voice information and positioning information to a processing end for the first time through a bound terminal; the artificial intelligence decomposes all management processes into minimum processes, marks the work location, working time period and a number of staff members allowed to access each minimum process to form a minimum access block; counts the number of times staff members allowed to access all minimum access blocks; the artificial intelligence determines the identity of the staff member through voice information; pushes in different ways according to the number of times the staff member is allowed to access; the present invention decomposes all management processes into minimum processes and forms minimum access blocks, that is, switches each minimum process into an independent calling process; directly predicts the minimum process that it can access through voice recognition, so as to greatly improve management efficiency and response speed.
Owner:XIAMEN LIANJIAN TECH CO LTD

Distributed voice processing system and method

PendingCN119028343AImprove recognition rateImprove recognition distanceSpeech recognitionEngineeringSpeech sound
The invention provides a distributed voice processing system and method. The system comprises a plurality of node devices, the plurality of node devices form a network, each node device comprises a processor, a memory, a communication module and a sound processing module, and at least one node device in the plurality of node devices comprises a sound acquisition module; wherein the sound acquisition module is configured to acquire an audio signal; the sound processing module is configured to pre-process the audio signal to obtain a first sound pre-processing result, wherein the pre-processing comprises extracting a sound characteristic value of the audio signal; wherein the communication module is further configured to receive one or more second sound pre-processing results from at least one other node device from the network; the sound processing module is further configured to execute speech recognition based on the first sound preprocessing result and / or the one or more second sound preprocessing results to obtain a first speech recognition result. According to the invention, the decentration design is realized, and the speech recognition efficiency, stability and robustness are improved.
Owner:ESPRESSIF SYST SHANGHAI

Fourier transform system and method based on neural network hardware system

The present invention discloses a Fourier transform system based on a neural network hardware system, and belongs to the field of neural network chip technology. It includes: arranging input data points into a set two-dimensional length. According to the input data points and the real part equation of the rotation factor, respectively obtain the corresponding first real matrix and second real matrix. Arrange the input data matrix into a two-dimensional first matrix corresponding to the number of rows and columns of the computing unit array. Obtain a fourth matrix according to the two-dimensional third matrix, the second real matrix and the second imaginary matrix. The fourth matrix is ​​obtained by operating the first fully connected layer computing unit with the first real matrix and the first imaginary matrix to obtain a fifth matrix. According to the fifth matrix, obtain output Fourier real data and output Fourier imaginary data. The present invention solves the problem that the prior art artificial intelligence chip has low performance and large area when calculating Fourier transform in application scenarios such as speech recognition and speech synthesis.
Owner:BEIJING TSINGMICRO INTELLIGENT TECH CO LTD

An online conference translation method and system

ActiveCN121480532BImprove Speech Recognition EfficiencyReduce identification uncertaintyNatural language translationSpeech recognitionLanguage speechSpeech sound
The application discloses an online conference translation method and system, and belongs to the technical field of speech recognition. The language space is constrained by the interactive side signal, and the recognition uncertainty is reduced. In the recording stage, a target language label generated by a sliding gesture is introduced. The label reflects the language of the speaker to whom the speech is directed. The language label of the speaker's mother tongue is combined, the candidate language set is optimally converged into a two-language set of "mother tongue + target language", and the search space of speech recognition in the language dimension is significantly reduced from the "complete language set of the conference" to the "two-language set". Based on this, the misrecognition probability caused by multi-language competition is reduced, especially the probability of misrecognizing foreign language terms as mother tongue homophonic words is reduced, and it can be quickly determined which languages are involved in each sentence of speech, so as to quickly determine which mixed language model is used for speech recognition, and the speech recognition efficiency of mixed language speech is improved.
Owner:QUEEN BEE NETWORK TECH (SHENZHEN) CO LTD

Speech recognition method and device, equipment and storage medium

The embodiment of the invention provides a speech recognition method and device, equipment and a storage medium. The method comprises the following steps: acquiring to-be-recognized voice data; performing feature extraction on the voice data to obtain a voice feature vector; the speech feature vector is converted through a target speech recognition model, a triple used for self-attention calculation is obtained, and the triple comprises a query vector, a key vector and a value vector; the query vector and the value vector are generated in the first layer of the target speech recognition model, and the key vector in the attention mechanism is generated in each layer of the target speech recognition model in an updating manner; and obtaining an attention calculation result of the target layer based on the query vector and the value vector generated by the first layer and the key vector of the target layer, and recognizing the voice data based on the attention calculation result to obtain a voice recognition result. The embodiment of the invention aims to reduce the memory requirement in voice recognition and improve the voice recognition efficiency.
Owner:PING AN TECH (SHENZHEN) CO LTD

Speech recognition method and device, equipment and storage medium

The invention relates to the field of artificial intelligence and financial science and technology, and discloses a speech recognition method, device and equipment and a storage medium, and the method comprises the steps: splicing a first embedded vector and a second embedded vector, generating a third embedded vector, reconstructing the third embedded vector, and generating a fourth embedded vector; obtaining a predicted speech recognition text output by the speech recognition model based on the fourth embedded vector, and obtaining a first loss value and a second loss value between the predicted speech recognition text and a preset speech recognition text; generating a total loss value of the predicted speech recognition text according to the first loss value and the second loss value, and training a speech recognition model based on the total loss value; and obtaining a current voice and a current domain label sent by the customer service system, inputting the current voice and the current domain label into the trained voice recognition model, and obtaining a current voice recognition text output by the trained voice recognition model. The voice recognition efficiency can be improved.
Owner:PING AN TECH (SHENZHEN) CO LTD