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

23results about How to "Improve speech recognition performance" patented technology

Linear complexity model architecture for speech recognition

The invention discloses and introduces a linear complexity model architecture for speech recognition in the technical field of speech recognition, an AMLP branch uses an MLP to replace an attention mechanism, an attention average pooling layer is added on the basis of the MLP, uniform distribution of attention weights is ensured while the linear complexity is kept, comprehensive global features are obtained, and the accuracy of speech recognition is improved. According to the convolution branch, an enhanced local feature relationship is captured by using a convolution space gating unit, local features and global features are mixed through a channel interacting information with the AMLP branch, and the local features are supplemented for the global features. Advanced fusion is properly carried out during local feature and global feature extraction processing, so that the problem of real-time mutual influence of the global features and the local features is solved.
Owner:CHANGCHUN UNIV OF SCI & TECH

Agricultural disease and pest dialect voice intelligent recognition method based on deep learning technology

The invention discloses an agricultural disease and pest dialect speech intelligent recognition method based on a deep learning technology, and the method comprises the steps: combining a Mel-frequency cepstral coefficient with a convolutional neural network, and dividing a whole process into two stages, the pre-training stage comprises the steps of recording and storing a long voice file, extracting the characteristics of voice signals in the file and training a neural network model, and the retraining stage comprises the steps of recording and storing a short voice file, extracting the characteristics of the voice signals in the file, verifying a test result, adjusting model parameters and storing an optimal model; the dialect voice information reported by monitoring personnel in an agricultural field is intelligently recognized by considering accent of people in different regions, so that the recognition accuracy of complex dialect voice signals is effectively improved, and the recognition method is particularly suitable for understanding related terms of agricultural diseases and insect pests.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Speech recognition method and related device

ActiveCN119400181AImprove speech recognition performanceSpeech recognitionSpeech soundVoice data
The invention discloses a voice recognition method and a related device, and relates to the technical field of voice recognition, and the voice recognition method comprises the steps: obtaining target voice data; the method comprises the following steps: performing preliminary voice recognition on target voice data to obtain word-level acoustic information of the target voice data and candidate voice recognition results; projecting the word-level acoustic information of the target voice data into a representation space of the large language model to obtain target acoustic features of the target voice data; and processing the target acoustic features of the target voice data into a character sequence by using a large language model and assisted by the candidate voice recognition result of the target voice data, and obtaining a voice recognition result of the target voice data. The speech recognition method disclosed by the invention has a relatively good recognition effect.
Owner:IFLYTEK CO LTD

Portable ear electroencephalogram system for objective evaluation of auditory function and working method of portable ear electroencephalogram system

InactiveCN118986370Ashort incubation periodImprove speech recognition performanceHealth-index calculationAudiometeringAuditory functionsElectroencephalogram electrode
The invention discloses a portable auditory function objective evaluation-oriented ear electroencephalogram system and a working method thereof. The system comprises an ear electroencephalogram acquisition unit, an ear electroencephalogram electrode fixing unit and an auditory function objective evaluation unit, the ear electroencephalogram acquisition unit is used for acquiring ear electroencephalogram signals and transmitting the ear electroencephalogram signals to the auditory function objective evaluation unit; the ear electroencephalogram electrode fixing unit is used for fixing an electrode unit in the ear electroencephalogram acquisition unit to a temporal region and placing the ear electroencephalogram acquisition unit; and the auditory function objective evaluation unit is used for displaying the ear electroencephalogram signals in real time, marking the ear electroencephalogram signals according to the standard stimulation and the deviation stimulation and evaluating the auditory function according to the ERP waveform. According to the invention, the collection and transmission of the ear electroencephalogram signals are realized, and the ERP waveform is analyzed, so that the auditory function is objectively evaluated.
Owner:TIANJIN UNIV

Classroom intelligent terminal integrated with micro host, network access and audio acquisition

The invention relates to the technical field of classroom intelligent terminals, in particular to a classroom intelligent terminal integrating a micro host, network access and audio acquisition. According to the technical scheme, the classroom intelligent terminal integrating a micro host, network access and audio acquisition is provided. Comprising a main control unit, an acoustic array device, a network interface device, a deep learning audio processing unit, a multi-mode interaction device, an adaptive network technology component, an edge computing unit, a virtual reality and augmented reality device, a block chain module and a voice synthesis and emotion recognition module. The system provides more advanced, intelligent and interactive rich education experience, is expected to improve the learning effect and teaching efficiency, has potential revolutionary influence in the education field, and provides a more flexible, personalized and efficient learning environment.
Owner:NANJING JINSHENG YURUN SCI & EDUCATION EQUIP CO LTD

Acoustic model construction method and system, speech recognition method, device and medium

ActiveCN114446281BImprove training effectImprove speech recognition performanceSpeech recognitionAcoustic modelSpeech sound
An acoustic model construction method and system, a speech recognition method, a device and a storage medium, wherein the construction method comprises: obtaining unlabeled training data and labeled training data; constructing an acoustic model, the acoustic model being used to obtain conditional probabilities corresponding to phonemes; the acoustic model comprising an audio representation model, the audio representation model being used to obtain representation vectors based on input speech; using a training speech set, pre-training the audio representation model based on the correlation between frames; after pre-training the audio representation model, using labeled training data, training the acoustic model based on annotated text, the correlation between words in the annotated text, and the correlation between the representation vectors corresponding to the words and speech data. The embodiments of the present invention improve the training effect of the acoustic model.
Owner:SHANGHAI LIULISHUO INFORMATION TECH CO LTD

Domain adaptive speech recognition method and related device

PendingCN119673151AImprove speech recognition performanceInternal combustion piston enginesSpeech recognitionA domainSelf adaptive
The invention discloses a domain adaptive speech recognition method and a related device, and relates to the technical field of speech processing, and the method comprises the steps: obtaining a domain adaptive speech recognition model through the training of target domain unsupervised data in advance, and obtaining a target domain dictionary when the to-be-recognized target domain speech needs to be recognized, the target domain voice and the target domain dictionary are input into the domain self-adaptive voice recognition model, the domain self-adaptive voice recognition model recognizes the target domain voice based on the target domain dictionary, and a recognition result is obtained. According to the scheme, the target domain unsupervised data is utilized in the training stage, the target domain dictionary is utilized in the prediction stage, and the recognition efficiency is improved. Therefore, the speech recognition effect of the target field can be improved.
Owner:XIAN XUNFEI SUPER BRAIN INFORMATION TECH CO LTD

Intelligent magic mirror interaction method and system based on voice recognition

InactiveCN119339721AImprove voice receptionefficient collectionSpeech recognitionNoiseEngineering
The invention relates to the technical field of bioinformatics, and discloses an intelligent magic mirror interaction method and system based on voice recognition, and the method comprises the steps: collecting a voice signal of an intelligent magic mirror through a target multi-microphone module, carrying out the noise suppression of the voice signal, and obtaining a noise-suppressed voice signal, extracting a voice signal voiceprint of the noise suppression voice signal, determining a target voice signal and a target voice user of the intelligent magic mirror, calculating a user position of the target voice user, recognizing a user intention of the target voice signal by using a multi-language intention recognition model, calculating an intention priority of the user intention, and obtaining an intention priority of the user intention; determining a sequence intention task of the target voice user; constructing a mirror surface interaction instruction of the intelligent magic mirror, and defining a voice interaction instruction of the intelligent magic mirror; and determining an interaction behavior in the process of executing the sequence intention task, and constructing an interaction page of the target voice user and an interaction mirror surface in the intelligent magic mirror. The interaction effect of the intelligent magic mirror can be improved.
Owner:GUANGDONG DAVID INTELLIGENT TECH CO LTD

A speech recognition data enhancement method based on feature clipping and translation

ActiveCN114171012Bavoid wastingImprove speech recognition performanceSpeech recognition
The present invention relates to a speech recognition data enhancement method based on feature clipping and translation, and belongs to the field of speech recognition processing technology. The method clips and translates the audio signal features in the time dimension and the frequency dimension respectively. Among them, in the time dimension, the feature value of a certain time period is randomly selected, the feature of the time period is clipped, and then the unclipped feature value is translated along the time dimension direction; in the frequency dimension direction, the feature value of a certain frequency segment is randomly selected, and then the feature of the frequency segment is clipped, and the unclipped feature value is translated along the frequency direction. The method does not need to regenerate the audio signal or extract features, which avoids the waste of storage space and running time. It has better data enhancement effect than the existing data enhancement technology and effectively improves the speech recognition effect.
Owner:BEIJING INST OF TECH

Speech recognition method and device based on multi-view lip movement image

PendingCN119400177Acapture comprehensiveImprove speech recognition performanceInternal combustion piston enginesBiological modelsPattern recognitionSpeech recognition performance
The invention discloses a speech recognition method and device based on a multi-view lip movement image. The method comprises the following steps: acquiring to-be-processed image information and angle information; the to-be-processed image information comprises M pieces of lip movement image information; the angle information comprises N lip angles; performing fusion processing on the to-be-processed image information and the angle information to obtain target image result information; the target image result information comprises L pieces of lip movement image result information; l is a positive integer greater than or equal to 1 and less than or equal to N; and based on the target image result information, determining voice recognition result information. Therefore, the voice information can be captured more comprehensively, so that the voice recognition performance in a real scene is improved.
Owner:NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI

Air conditioner, voice recognition method thereof, terminal server and readable storage medium

ActiveCN118031371BImprove speech recognition performanceReduce working noise
The application discloses a voice recognition method of an air conditioner, the air conditioner and a computer readable storage medium, and comprises the following steps: a terminal server receives voice information uploaded by a master machine; the type of the voice information is recognized; when it is recognized that the type of the voice information is a wake-up voice, adjustment information is sent to a slave machine, so that the slave machine adjusts its operation parameters according to the adjustment information, or reduces the working noise of the slave machine after adjusting its working mode. The embodiment of the application improves the voice recognition effect of the slave machine of the air conditioner in a noisy environment and improves the use effect of the air conditioner.
Owner:GD MIDEA AIR CONDITIONING EQUIP CO LTD

Speaker and microphone structure

The present invention belongs to the technical field of sound boxes, and aims to provide a sound box and its microphone structure, including at least two microphone units, wherein the lateral center distance between two adjacent microphone units is 80 mm-120 mm; the microphone unit includes a bottom cover, an upper cover and a sound signal conversion component, wherein the top of the bottom cover is provided with a first groove, and the side wall is provided with a connecting hole communicating with the first groove; the bottom end of the upper cover is provided with a second groove, and the top end is provided with a first sound hole communicating with the second groove, and when the upper cover is covered on the bottom cover, the second groove and the first groove jointly form a closed cavity; one end of the sound signal conversion component is gap-set in the first groove, and the other end is sealed in the second groove, and the distance between the sound signal conversion component and the bottom cover can be adaptively adjusted according to the vibration frequency of the sound wave received by the first sound hole. The sound box and its microphone structure reduce echo and improve speech recognition ability by adopting an array-type speech recognition structure and a sealed cavity structure.
Owner:SHENZHEN GRANDSUN ELECTRONICS CO LTD

Automatic analysis device and automatic analysis system

Provided is an automatic analysis device in which safety is ensured, and operability is improved. The present invention is an automatic analysis device 100 comprising: an operation unit 102 that receives voice input from a microphone 103 or a mobile device 107; and a measurement unit 101 that analyzes a sample. The operation unit has: an equipment state acquisition unit 213 that acquires equipment state data for the measurement unit; a voice detection / recognition unit 211 that acquires voice data and converts the voice data into voice instruction text; and a unit for determining device operability 214 that, in cases in which the voice instruction text includes operation instructions for the measurement unit, determines the executability of the operation instructions included in the voice instruction text, on the basis of the equipment state data for the measurement unit acquired by the equipment state acquisition unit, and on the basis of the accuracy of the voice instruction text.
Owner:HITACHI HIGH TECH CORP

Speech recognition method, device, equipment, medium and product

PendingCN119400158AImprove speech recognition performanceSpeech recognitionText recognitionEngineering
The invention provides a speech recognition method and device, equipment, a medium and a product, and the method comprises the steps: obtaining a first prediction result and a second prediction result of a to-be-recognized speech, the first prediction result comprises a prediction result obtained based on a candidate text recognition result of the to-be-recognized speech, and the second prediction result comprises a prediction result obtained based on a candidate text recognition result of the to-be-recognized speech; the second prediction result comprises a prediction result obtained based on the to-be-recognized voice; determining a first weight corresponding to the first prediction result, and determining a second weight corresponding to the second prediction result; and performing feature fusion on the first prediction result and the second prediction result based on the first weight and the second weight, and determining a recognition result of the to-be-recognized voice based on the obtained fusion feature. The voice recognition effect can be improved.
Owner:HEFEI IFLY DIGITAL TECH CO LTD

Multilingual real-time speech recognition system and method based on deep learning

The invention relates to the technical field of speech recognition, in particular to a multilingual real-time speech recognition system and method based on deep learning. The method comprises the following steps: inputting a voice signal to be recognized into a Wiener filtering model, and outputting an enhanced voice signal; processing the discrete energy spectrum by using a group of triangular band-pass filters which are uniformly distributed on frequency to obtain corresponding output, performing logarithmic operation on the output of all the filters to obtain a logarithmic power spectrum, and obtaining characteristic parameters of the voice signal based on discrete cosine transform of the logarithmic power spectrum; extracting voice signal feature vectors based on the feature parameters; and inputting the voice signal characteristic vector into a vector quantizer, outputting a code vector label formed by quantization, inputting the code vector label into the HMM voice recognition model, and outputting a recognition result. According to the invention, the accuracy of speech recognition can be improved, and the stability of real-time speech recognition service is improved.
Owner:GUANGZHOU SIZHENG ELECTRONIC TECH CO LTD

Noise robust acoustic feature extraction method based on gamma channel scaled basis vector

ActiveCN115662408BGuaranteed carrying capacityImprove speech recognition performanceSpeech recognitionFrequency spectrumFeature extraction
The application discloses a noise-robust acoustic feature extraction method based on a gamma pass scaling basis vector. The noise-robust acoustic feature extraction method based on the gamma pass scaling basis vector comprises the following steps: performing pre-emphasis processing on a speech signal; performing frame processing on the speech signal after the pre-emphasis processing; performing Fourier transform on the speech signal after the frame processing; calculating a scaling coefficient according to the spectral distribution characteristics of a gamma pass filter bank, and optimizing a basis vector based on the scaling coefficient; and performing discrete cosine transform on the speech signal after the Fourier transform and the optimized basis vector to extract noise-robust acoustic features from the speech signal. According to the application, the scaling coefficient is calculated based on the frequency domain distribution characteristics of the gamma pass filter bank, and is directly applied to the basis vector for generating acoustic features, so that the original details of the speech signal are retained to the greatest extent, the information carrying capacity of the acoustic features under the interference of noise signals is ensured, and the speech recognition effect can be effectively improved.
Owner:INFORMATION SCI RES INST OF CETC +1

Speech recognition method and system in specific scene

The invention discloses a speech recognition method and system in a specific scene, and the method comprises the steps: a training stage: carrying out the recognition through a Bilstm + WFST model and an ED model based on a collected data set, carrying out the data processing of the recognition results, obtaining a high-quality pseudo-tag data set, and carrying out the recognition through a Bilstm + WFST model and an ED model, and carrying out the recognition through a Bilstm + WFST model; iteratively training the Bilstm model and the ED model in the Bilstm + WFST model by adopting the high-quality pseudo tag data set to obtain an optimal Bilstm + WFST model and an optimal ED model; in the recognition stage, recognition is conducted through the optimal Bilstm + WFST model and the ED model, the recognition results of the two models are scored, and the recognition result text corresponding to the smaller score serves as the final recognition result of continuous speech recognition. According to the invention, the voice recognition effect under the specific scene can be improved by using the non-annotated data of the specific scene.
Owner:杭州智元研究院有限公司

Language similarity evaluation method based on forced decoding, speech recognition method and related equipment

PendingCN119252226AImprove speech recognition performanceSpeech recognitionSpeech inputLanguage speech
The invention provides a language similarity evaluation method based on forced decoding, a speech recognition method and related equipment. The language similarity evaluation method based on forced decoding comprises the following steps: S101, selecting a multi-language voice model, and appointing a target language of the multi-language voice model; the multi-language speech model is used for decoding an input source language speech into a target language text; s102, inputting a source language voice into the multi-language voice model so as to forcibly decode the source language voice into a target language text, and obtaining a normalized posterior probability of the target language text; and S103, calculating a language similarity score between the source language and the target language based on the normalized posterior probability. Based on the method, the invention also provides a speech recognition method based on language similarity and related equipment. The source language speech is compulsively decoded into the target language text, the similarity of cross-language intrinsic representation is implicitly calculated, and speech recognition is performed based on the similarity score, so that the recognition performance is improved.
Owner:Chinese People's Liberation Army Cyberspace Force Information Engineering University

Intelligent risk control voice monitoring method and system based on multi-modal algorithm

The invention relates to the technical field of intelligent decision, and discloses an intelligent risk control voice monitoring method and system based on a multi-modal algorithm, and the method comprises the steps: carrying out the feature extraction of training voice, constructing a pre-trained text recognition model of voice features, and carrying out the model training of the pre-trained text recognition model through the voice features and a training text; dividing digital information and text information in the training text, and performing model training on a pre-trained word vector model by utilizing the preprocessed text and the training word vector; carrying out vector fusion on the training word vector, the digital information and the rule text data, and carrying out semantic association analysis on the training text and the rule text data; and generating a feature vector corresponding to the context vector and the semantic association graph, constructing a pre-trained risk discrimination model of the feature vector, and performing model training on the pre-trained risk discrimination model by using the feature vector and the training category. According to the invention, risk control voice monitoring intelligence can be improved.
Owner:WESHARE TECH SERVICES (SHENZHEN) LTD

A speech data training method and recognition method based on distributed array

The present invention discloses a speech data training method and recognition method based on a distributed array, wherein the training method includes: determining each microphone array speech data and its optimal microphone array label signal; inputting each microphone array speech data and the optimal microphone array label signal into a neural network model for training, extracting microphone phase features of two different channels and energy features of microphone speech data of any channel for splicing; and gradually optimizing the neural network model until it outputs the optimal speech signal. The present invention uses a distributed array speech data training method, utilizes a neural network model to train and output the optimal speech signal of the distributed microphone array speech data, can accurately identify the speech signal of the optimal sound source, and recognizes the training results based on a multi-channel attention feature fusion network model, significantly improves the speech recognition performance, and ultimately ensures the accuracy of speech recognition, meeting the speech recognition requirements in a far-field sound pickup environment.
Owner:SHENZHEN UNIV

True wireless stereo loudspeaker

ActiveCN222089761UImprove speech recognition performanceboost audioIntra aural earpiecesTransducer casings/cabinets/supportsExternal Auditory CanalsEngineering
The utility model provides a true wireless stereo loudspeaker, the appearance of the loudspeaker is formed by a shell, the interior of the shell is divided into an upper space and a lower space by a support which is arranged transversely in the length direction of the shell, a driver is arranged on one side of the lower space, and a loudspeaker is arranged on the other side of the lower space. A sound release part which is communicated with the driver and extends forward in a manner of facing the external auditory canal of the user is provided, a microphone is mounted on one side with an inlet of the sound release part as a reference in a space facing the front of the driver, and the sound release part is partitioned by a partition plate; the diaphragm extends so as to constitute the boundary of the space formed by the sound release part, and provides a microphone sound inflow part which is formed in a channel shape for transmitting the speaker's voice to the microphone, and which is independent of the sound release part. Thus, the ventilation flow of external sound can be opened and closed by means of the ventilation volume adjusting valve device, and the opening volume can be finely adjusted.
Owner:BUJEON

Training methods, devices, equipment, and storage media for speech recognition models

This application discloses a training method, apparatus, device, and storage medium for a speech recognition model, belonging to the field of artificial intelligence. The method includes: acquiring a sample audio set, the sample audio set including multiple sample audios; filtering candidate sample audios from the sample audio set based on an initial speech recognition model; extracting audio segments from the candidate sample audios; wherein the audio segments include audios aligned with consecutive identical text units from the candidate sample audios; and the initial speech recognition model, when performing speech recognition on the candidate sample audios, failed to correctly recognize the consecutive identical text units; and retraining the initial speech recognition model based on the audio segments to obtain a target speech recognition model. This application can improve speech recognition quality, particularly improving the accuracy of recognizing consecutive identical text units.
Owner:SOUNDAI TECH CO LTD

Speech recognition data enhancement method based on pseudo labeling and course learning, speech recognition method and related equipment

PendingCN119068867Aenhanced implementationSolve the scarcitySpeech recognitionSpeech recognition performanceCoursework
The invention provides a speech recognition data enhancement method based on pseudo labeling and course learning, a speech recognition method and related equipment. According to the method, the false annotation technology is utilized to generate the false annotation of the unannotated voice data, and the confidence score is calculated based on the posterior probability during decoding of the false annotation, so that the confidence score is regarded as the difficulty level standard for measuring the data in course learning, organic combination of the false annotation and the confidence score and further mining of the capability of the false annotation are realized, and the accuracy of course learning is improved. Therefore, the purpose of enhancing the speech recognition data is achieved, and on the basis, the purpose of optimizing the speech recognition performance is further achieved.
Owner:Chinese People's Liberation Army Cyberspace Force Information Engineering University