26results about How to "Improve voice quality" patented technology

The invention discloses a voice noise reduction system in a multi-noise environment, and particularly relates to the technical field of voice noise reduction, which comprises a basic division module for dividing voice data into a plurality of basic voice segments with the same duration; the rationality analysis module judges whether segmentation points of adjacent fragments are reasonable or not, and if the segmentation points are not reasonable, the optimization marking module searches for new segmentation points for optimization; the loop module repeatedly verifies the optimization result until all the voice segments are reasonably segmented; the noise reduction module extracts voice and noise features, and performs noise reduction processing by using a noise reduction strategy selection model; the recombination module recombines the voice segments after noise reduction into complete voice output; according to the invention, the voice signal is divided into a plurality of segments, the most suitable noise reduction algorithm can be matched for each segment according to the noise feature of each segment, and the method can cope with a more complex and unstable noise environment through a dynamically adaptive noise reduction strategy, and guarantees that the voice quality is better improved in various scenes.

The invention relates to a voice processing method and device, electronic equipment and a storage medium. The method comprises the following steps: extracting voice features of a damaged voice signal to obtain damaged voice features; inputting the damaged voice features into a repaired voice generation network of a voice damage repair model to obtain generated repaired voice features; dividing the repaired voice features according to a plurality of preset sub-bands to obtain sub-repaired voice features corresponding to the sub-bands; inputting the sub-repaired speech features corresponding to the sub-bands into a multi-band speech enhancement network of a speech damage repair model, and performing speech enhancement processing on the corresponding sub-repaired speech features through speech enhancement sub-networks corresponding to the sub-bands in the multi-band speech enhancement network to obtain enhanced speech features of the sub-bands; and generating a deep repair voice signal corresponding to the damaged voice signal based on the enhanced voice feature of each sub-band. According to the invention, the voice quality and intelligibility can be remarkably improved in a scene in which multiple distortions exist at the same time.

The invention discloses an interphone implementation system based on voice automatic recognition, and relates to the technical field of voice recognition, and the system comprises the steps: collecting a voice signal of a user through an interphone microphone, and converting the voice signal into an analog electric signal; converting the analog electric signal into a digital audio signal by using an AAC audio coding algorithm, and carrying out coding processing; voice data packets lost in the transmission process are repaired in a data redundancy mode by using a forward error correction technology; framing the audio signal to be processed by using an overlapped sliding window method; detecting a voice area endpoint in the voice frame by using a double-threshold judgment method; training a speech recognition hidden Markov model through the speech area data and the corresponding statements in the information base; and obtaining statement information corresponding to the voice signal of the user by using a Viterbi algorithm. By arranging the audio repairing module, the endpoint detection module, the model training module and the voice recognition module, the voice quality is improved, the call distance is increased, and thus the working efficiency of a user is improved.

The invention discloses a Tibetan language Andole speech enhancement method suitable for specific noise and general noise, and relates to the technical field of low-resource language speech processing. The method specifically comprises the following steps: acquiring noisy voice information; preprocessing the noisy voice information, and dividing the processed data into a training set and a test set; a noise spectrum feature input by the noise classification module is optimized based on a weighted average method of a logarithmic power spectrum domain hard threshold; constructing a noise classification task and noise suppression task fused multi-target Tibetan speech enhancement model; training and testing the built speech enhancement model by using the training set and the test set to obtain a trained speech enhancement model; and inputting the actually collected noisy speech into the trained speech enhancement model to obtain an enhanced logarithmic power spectrum. Through effective fusion of the noise classification task and the suppression task, the quality and the intelligibility of the Tibetan language Andor dialect enhancement voice are improved, the human-computer interaction of the Tibetan language Andor dialect is more perfect, and the method has a positive effect on popularization of Tibetan language informatization.

This application provides a device control method, a recognition model training method, and related devices. The device control method includes: acquiring speech to be processed emitted by a target user; inputting the speech to be processed into a recognition model to obtain recognition information output by the recognition model, wherein the recognition information includes control speech and a target speech channel, or the recognition information includes control speech, a target speech channel, and a time-frequency masking code, wherein the target speech channel is a speech transmission channel with a signal-to-noise ratio greater than a signal-to-noise ratio threshold, and the time-frequency masking code is used for sound source localization of the target user; and waking up or controlling the device's functions based on the recognition information. This application improves the accuracy of recognizing control information in speech.

The invention discloses a speech noise reduction system in a multi-noise environment, and specifically relates to the technical field of speech noise reduction, comprising a basic division module that divides speech data into a plurality of basic speech segments of the same duration; a rationality analysis module that determines whether the segmentation points of adjacent segments are reasonable, and if not, an optimization marking module that finds new segmentation points for optimization; a loop module that repeatedly verifies the optimization result until all speech segments are segmented reasonably; a noise reduction module that extracts speech and noise features, and uses a noise reduction strategy to select a model for noise reduction processing; a reorganization module that reorganizes the noise-reduced speech segments into complete speech outputs; the invention divides a speech signal into a plurality of segments, and can match the most suitable noise reduction algorithm for each segment according to its noise features, and can cope with a more complex and unstable noise environment through a dynamically adapted noise reduction strategy, and ensure that the speech quality is well improved in various scenarios.

The invention discloses a speech enhancement method and a related device, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the enhancement of target speech data based on a speech enhancement model, and obtaining enhanced speech data, the speech enhancement model is constructed based on a U-shaped network added with a joint attention mechanism module composed of a self-attention module and a global space attention module, and on the basis of the feature modeling capability of the U-shaped network, on one hand, the self-attention module pays attention to the correlation of context information; and on the other hand, global features are fully modeled through a global space attention module, and intra-class compactness is improved, so that feature representation is optimized, the speech enhancement effect of the speech enhancement model is improved, and the speech quality of a speech enhancement result is improved.

The present application discloses a method for extending the frequency band of a speech signal, comprising the following steps: determining a source speech and obtaining a signal spectrum of the source speech; obtaining a harmonic signal and an unvoiced noise signal of an extended speech corresponding to the source speech based on the signal spectrum of the source speech; performing speech synthesis processing on the source speech, the signal spectrum of the source speech, and the harmonic signal and unvoiced noise signal of the extended speech corresponding to the source speech, to obtain the extended speech corresponding to the source speech. The application of the technical solution provided by the present application improves the speech quality of the speech signal obtained after the frequency band extension, thereby improving the user's listening experience. The present application also discloses a speech signal frequency band extension device, equipment, storage medium and computer program product, which have corresponding technical effects.

The present invention relates to the field of speech signal processing technology, and in particular to a speech signal denoising method, system and device. The method comprises the following steps: adaptively framing speech signal data to be processed to obtain framed speech signal data; semantically embedding space processing is performed according to the framed speech signal data to obtain semantically embedded space data; semantic vector field is constructed according to the semantically embedded space data to generate speech semantic vector field data; speech noise area is marked on the speech semantic vector field data to generate semantic noise area data; noise frame repair processing is performed according to the semantic noise area data to generate denoised speech signal data; auditory masking spectrum correction is performed on the denoised speech signal data to generate enhanced speech signal data. The present invention accurately guides speech signal denoising through semantic information, and can still achieve excellent denoising effect even in complex scenarios such as low signal-to-noise ratio, significantly improving user experience.

The application discloses a microphone array sound pickup method, electronic equipment and computer readable storage medium. The sound pickup method comprises the following steps: fixed beam forming is performed on a voice signal received by a microphone array, and a beam forming direction of the microphone array is pointed to an estimated expected direction of arrival; blocking processing is performed on the processed voice signal, so that the voice signal from the expected direction of arrival is blocked, and only the voice signal from a non-expected direction of arrival is reserved; the processed signal is used as a reference signal, a first filter is used to filter out the signal from the non-expected direction of arrival and reserve the signal from the expected direction of arrival; and an update factor of the first filter is calculated according to the following formula (I), wherein the update factor of the first filter of the mth microphone channel is SNR f,d (ω, l) is Y f,d (ω, l) is a signal-to-noise ratio of Y f,d (ω, l) is a delay signal obtained by delaying the signal processed in the step S1, SNR m (ω, l) is a signal U m (ω, l) is a signal-to-noise ratio of Y. The application further improves voice quality.

The invention provides a speech enhancement method, a speech enhancement device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the steps of obtaining original voice data; inputting the original voice data into a voice enhancement model, and encoding the original voice data through an encoder to obtain encoded voice features; performing first speech enhancement on the coded speech feature through a first speech enhancement module to obtain a first enhanced speech feature; performing second speech enhancement on the first enhanced speech feature through a second speech enhancement module to obtain a second enhanced speech feature; performing feature fusion on the first enhanced speech feature, the second enhanced speech feature and the coded speech feature through a feature fusion module to obtain a target enhanced speech feature; and decoding the target enhanced voice features through a decoder to obtain enhanced voice data. The voice quality of the voice can be improved and enhanced. The method and the device can be used for scenes such as e-commerce and online transaction.

The present invention provides a method, system and device for transcribing multilingual long recordings with adaptive noise suppression, including: performing audio segmentation on the multilingual long recording to obtain multiple audio segments; performing spectrum analysis on each audio segment to obtain corresponding spectrum features; performing noise detection on each audio segment according to the spectrum features to determine the noise segment; performing adaptive noise suppression on each noise segment in the multilingual long recording to obtain denoised multilingual audio; performing voice activity detection on the denoised multilingual audio to determine voice segments and non-voice segments; performing feature extraction on the voice segments to obtain voice features; inputting the voice features into a pre-trained multilingual transcription model for transcription to obtain corresponding text results. In the present invention, by performing adaptive noise suppression on each noise segment in the multilingual long recording, the interference of noise is effectively reduced and the voice quality is improved.

The application provides a speech noise reduction method and device, the method comprises the following steps: obtaining air conduction sound signals and bone conduction sound signals, and bone conduction target event signal segments, bone conduction non-target event signal segments, air conduction target event signal segments and air conduction non-target event signal segments; fusing signals in at least part of frequency bands in the bone conduction target event signal segments and the air conduction target event signal segments to generate a fused signal; and performing noise reduction processing on the fused signal and the non-target event signal segments and then outputting. Thus, the bone conduction sound signals and the air conduction sound signals are effectively fused, so that the speech signal is reduced in noise, and the speech quality of the electronic device is improved.

Audio devices with ultrasound guided processing and related methods are disclosed. An audio device includes an interface, a memory, one or more processors including a signal processor, one or more speakers, one or more microphones, and an ultrasound device. The audio device is configured to: output an ultrasonic signal via an ultrasonic device output; obtaining an input ultrasound signal via the ultrasound device; obtaining an audio input signal via one or more microphones; determining a direction of arrival of the audio input signal based on the audio input signal; determining position data based on the input ultrasound signal and the output ultrasound signal, the position data including first position data indicating a first position of the first moving object; the audio input signal is processed for providing an audio output signal based on whether the direction of arrival satisfies a position criterion.

The present application discloses a cross-language speech synthesis method, device, electronic device and storage medium, the method comprising: obtaining speech data of a target object and speech data of an object to be synthesized; wherein the speech data of the target object is in a first language; the speech data of the object to be synthesized is in a second language; the second language and the first language are different languages; obtaining a timbre feature matrix of the target object; and encoding the phonemes, pitches and phoneme durations of the speech data of the object to be synthesized, and adding a set note at the phonemes with the same pronunciation or fuzzy pronunciation to obtain processed encoded data; decoding the timbre feature matrix and the encoded data to obtain synthesized speech data based on the second language with the timbre feature matrix. The present application can make the synthesized speech data have the timbre of the target object while retaining the pronunciation habits of the second language, so as to improve the transferability of the language, and then improve the cross-language speech synthesis effect.

The present invention relates to an echo elimination method, comprising the following steps: adaptively updating a main filter and an auxiliary filter in a dual filter structure, wherein the updating function is as follows: #imgabs0# wherein w(k+1) is a filter updating function, w(k) is a filter original function, u is a step size factor, Q(k) is a step size gain matrix, x(k) is a system input signal, e(k) is an evaluation error, δ is a minimum regularization parameter, and x(k) T The system input signal is transposed; the dual filter structure is used to accelerate the convergence speed of the echo in the sound signal, the echo is linearly processed and the processed sound signal is output; the sound signal after linear processing is nonlinearly processed. The present invention solves the problems of residual echo, noise, fluctuating volume and double-talking mute in existing voice communication by adaptively updating the main filter and auxiliary filter in the dual filter structure, and adding double-talking judgment and double-talking processing method to nonlinear processing.

The invention provides a speech synthesis method and device, electronic equipment and a storage medium. The speech synthesis method comprises the following steps: acquiring an intermediate acoustic feature generated according to a target text, wherein the intermediate acoustic feature corresponds to a to-be-synthesized target speech; obtaining a prior noise signal, and extracting a time domain envelope feature of the target voice from the intermediate acoustic feature; and inputting the prior noise signal, the intermediate acoustic feature and the time domain envelope feature into a pre-trained neural vocoder, and obtaining a target voice which is output by the neural vocoder and is matched with the target text.

The present invention provides a scene-aware audio-visual speech enhancement method, device, medium and program product, wherein the method comprises the following steps: extracting the visual scene embedding and scene-aware audio embedding corresponding to the current scene by a pre-trained contrastive audio-visual mask autoencoder; using a one-dimensional convolutional layer to encode the noisy speech signal after short-time Fourier transform to obtain an acoustic spectrum embedding; fusing the visual scene embedding, scene-aware audio embedding and acoustic spectrum embedding to obtain a fused feature representation; processing the fused feature representation by a ConMamba module to obtain a phase-sensitive mask; performing an inverse short-time Fourier transform based on the phase-sensitive mask and the noisy speech signal to obtain an enhanced speech signal. The present invention uses visual cues as a component of the enhancement strategy, and processes them through the ConMamba architecture for a larger visual context range to improve the effect of speech enhancement.

The utility model discloses equipment for assisting double recording of a mobile phone, and solves the problem of repeated recording when a single mobile phone is used for double recording in the prior art. According to the equipment, in the double-recording process, the definition of double-recording video pictures is improved, the smoothness of voice in the recording process is improved, it is ensured that the electric quantity of a mobile phone is sufficient, the pictures recorded in real time can be seen, the integrity and definition of the pictures in the recording process are adjusted in time, the smoothness of double-recording recording is ensured, and the working efficiency is improved.

The invention relates to the technical field of artificial intelligence, and discloses a voice denoising real-time interaction method based on a cleaning robot, and the method comprises the steps: collecting a voice signal in a target environment through a preset cleaning robot; extracting a signal feature of the voice signal; performing noise suppression processing on noise in the voice signal according to the signal feature to obtain a primary de-noised signal of the voice signal; performing dynamic weighting on the primary de-noised signal by using a preset signal weighting algorithm and the signal features to obtain a weighted signal of the primary de-noised signal; generating an operation instruction of the cleaning robot according to the weighted signal; and generating a task sequence table of the cleaning robot according to the operation instruction, wherein the cleaning robot works according to the task sequence table. According to the invention, the efficiency of voice denoising real-time interaction based on the cleaning robot can be improved.

The invention relates to a voice signal processing method and device, electronic equipment and a storage medium. The method comprises the steps that content coding features, rhythm coding features and timbre coding features are acquired, the content coding features are used for representing the content of a voice signal, the rhythm coding features are used for representing the rhythm of the voice signal, and the timbre coding features are used for representing the timbre of the voice signal; content context construction is carried out on the content coding features based on the tone coding features and the rhythm coding features, and content context features are obtained; and performing voice reconstruction according to the timbre coding feature, the rhythm coding feature and the content context feature to obtain a target reconstructed voice signal. According to the technical scheme provided by the invention, high-quality speech reconstruction can be provided at a low code rate.

This disclosure provides a causal adaptive single-channel speech denoising method and apparatus. The method includes: acquiring noise information in a first time period and noisy speech information in a second time period; processing the noise information and noisy speech information to obtain a noise correlation matrix and a speech correlation matrix; performing generalized eigenvalue decomposition on the noise correlation matrix and the speech correlation matrix to obtain multiple initial feature vectors; generating a target filter vector based on the multiple initial feature vectors and the filter function of the initial filter; and generating enhanced target output speech information based on the target filter vector and the noisy speech information.

The invention discloses an acousto-optic signal enhancement method based on a neural network, and belongs to the technical field of signal processing. According to the invention, the hidden mapping relation between the enhanced signal and the original signal is constructed through deep learning based on the neural network, and the acousto-optic signal enhancement model is continuously trained and updated, so that the signal-to-noise ratio and the voice quality of the original signal are remarkably improved, and convenient output is realized. The phase loss Lphase and the amplitude loss LMagnitude are respectively output into the acousto-optic signal enhancement model to update corresponding parameters, so that data test correction and parameter updating of the acousto-optic signal enhancement model are realized; meanwhile, model parameters of the acousto-optic signal enhancement model are continuously updated and iterated by adopting an AdamW optimization algorithm, a loss function is minimized by calculating gradients and updating the parameters, the training efficiency and performance of the model are improved, and the voice quality and the signal-to-noise ratio of output signals of the acousto-optic signal enhancement model can be continuously improved.

The audio signal processing method and system for suppressing echo provided in this specification controls the selection of the target audio processing mode according to the speaker signal strength. The method and system generate a corresponding control signal according to the speaker signal strength, and control the target audio processing mode according to the control signal, and perform signal processing on the microphone signal to obtain better voice quality. When the speaker signal does not exceed the threshold, the system selects the first mode, and performs signal processing on the first audio signal and the second audio signal to obtain the first target audio. When the speaker signal exceeds the threshold, the system selects the second mode, and performs signal processing on the second audio signal to obtain the second target audio. The method and system can switch the target audio processing mode according to the speaker signal, ensuring better voice quality in different scenarios and improving the quality of voice communication.

The invention relates to the technical field of noise suppression, in particular to a residual noise suppression method based on characteristic component filtering. A residual noise suppression method based on feature component filtering is characterized in that noise is suppressed by increasing correlation of voice frames, and adjacent small feature components are replaced with large feature components or the adjacent small feature components are removed. In most cases, the three methods provided by the invention all have a relatively high SegSNR score, which reflects the strong ability of noise reduction under the condition of a low signal-to-noise ratio; in the aspect of segmentation signal-to-noise ratio scoring, the three methods provided by the invention are obviously improved, and the PESQ score of auditory speech quality is almost the highest.

The application discloses a kind of regulation voice data effective information enhancement method and system, and steps successively include: regulation voice signal separation, regulation voice signal noise reduction and regulation voice signal enhancement;Regulation voice signal separation utilizes the characteristics of different regulation voice center frequency difference, phase difference etc., and the regulation voice of multiple interweaves is separated into effective single voice signal;Regulation voice signal noise reduction extracts pure regulation voice signal, and filters out background noise and the process noise brought by deinterleaving;Regulation voice signal enhancement carries out lossless enhancement to the phase-frequency characteristics of voice signal;The application in the complex air traffic control environment that multiple people speak simultaneously, there is weak effective signal or background noise interference, maintains stable high recognition rate, reduces error and improves the overall efficiency of system.