20 results about "Pitch period" patented technology

The invention provides a helium voice correction method based on a generative adversarial network, and belongs to the technical field of voice processing and artificial intelligence. The technical problem of helium voice distortion caused by pitch period distortion and formant offset in a helium-oxygen environment is solved. According to the technical scheme, the method comprises the following steps of S1, preprocessing helium voice data; s2, constructing a special helium voice conversion model; and S3, inputting the preprocessed helium voice data into a voice recognition and semantic similarity evaluation system for processing. The beneficial effects of the invention are that the GAN is adopted as an advanced deep learning model, and the GAN can effectively capture the spectrum details in the voice signals through the multi-layer structure and the excellent unsupervised learning mechanism, thereby remarkably improving the voice correction performance.

The invention provides a voice recognition method, system and device based on artificial intelligence and a medium. The method comprises the steps of obtaining a to-be-recognized voice signal; performing keyword extraction on an initial voice text corresponding to the voice signal based on a pitch period determined by an amplitude deviation between adjacent voice amplitudes in the voice signal and a voice spectrogram of the voice signal to obtain a plurality of voice keywords; determining a homonym group of each voice keyword, and performing recognition verification on each voice keyword based on context semantic information of each voice keyword in the initial voice text and semantic features of homonyms in each homonym group to obtain recognition ambiguity of each voice keyword; and recognizing text probability distribution of the voice signal according to the recognition ambiguity and the homonym group corresponding to each voice keyword, and analyzing the text probability distribution to obtain a text recognition result of the voice signal. According to the scheme, based on the text probability distribution, the speech recognition accuracy can be improved under homonym confusion.

To provide a radio capable of performing squelch control with little erroneous determination regardless of the voice quality of a speaker. [Solution] The radio 20 in this example comprises an SSB demodulation unit 21 that performs SSB demodulation processing on the received signal, a noise cancellation unit 22 that performs noise cancellation processing on the audio signal resulting from demodulation by the SSB demodulation unit 21, a pitch period calculation unit 23 that calculates the pitch period of the audio from the audio signal after noise cancellation processing, and a squelch control unit 24 that controls the opening and closing of the squelch of a squelch circuit 25 based on the pitch period calculated by the pitch period calculation unit 23.

The present application provides a speech recognition method, system, device and medium based on artificial intelligence, which obtains a speech signal to be recognized; extracts keywords from an initial speech text corresponding to the speech signal based on a fundamental pitch period determined by an amplitude deviation between adjacent speech amplitudes in the speech signal and a speech spectrogram of the speech signal, to obtain a plurality of speech keywords; determines a homophone group of each speech keyword, and performs recognition verification on each speech keyword based on the context semantic information of each speech keyword in the initial speech text and the semantic features of homophones in each homophone group, to obtain the recognition ambiguity degree of each speech keyword; recognizes the text probability distribution of the speech signal according to the recognition ambiguity degree corresponding to each speech keyword and the homophone group, and analyzes the text probability distribution to obtain the text recognition result of the speech signal. The above solution can improve the recognition accuracy of speech under the confusion of homophones based on the text probability distribution.

The invention relates to the technical field of information hiding, and discloses a pitch period modulation information hiding detection method based on a Bayesian network. From the perspective of different network structures, the invention achieves the best effect by using a joint network combining three networks, namely, intra-frame, inter-frame and self-network. From the perspective of detection performance at different embedding rates, the detection accuracy of the method of the invention at a lower embedding rate is better than some existing steganalysis methods. From the perspective of the size of PDBNS, the smaller the number of Bayesian networks, the shorter the system detection time. When the number of Bayesian networks is small, the method still has a higher detection accuracy, and can realize real-time detection of the pitch period modulation information hiding method. From the perspective of detection performance at different time lengths, the method of the invention has a 100% detection rate of audio from 1 second to 10 seconds at an embedding rate of 1.0, which is better than some existing algorithms.

A method and an apparatus for detecting correctness of a pitch period, where the method for detecting correctness of a pitch period includes determining, according to an initial pitch period of an input signal in a time domain, a pitch frequency bin of the input signal, where the initial pitch period is obtained by performing open-loop detection on the input signal, determining, based on an amplitude spectrum of the input signal in a frequency domain, a pitch period correctness decision parameter, associated with the pitch frequency bin, of the input signal, and determining correctness of the initial pitch period according to the pitch period correctness decision parameter.

The present disclosure relates to a decoding method and apparatus, an encoding method and apparatus, an electronic device, a medium, a product and a system. The decoding method of the present disclosure comprises: parsing a code stream to obtain a high-frequency harmonic wave level identifier and a signal of a first frequency band of an audio frame, wherein the high-frequency harmonic wave level identifier is used for indicating the harmonic wave level of a second frequency band of the audio frame, and the frequency of the second frequency band is higher than that of the first frequency band; determining a signal of the second frequency band on the basis of a pitch period of the audio frame, the high-frequency harmonic wave level identifier, and the signal of the first frequency band; and obtaining a decoded signal of the audio frame on the basis of the signal of the first frequency band and the signal of the second frequency band.

The invention discloses a time delay determination method based on voice alignment and a related device, and the method comprises the steps: respectively segmenting a standard voice signal of a standard channel and a participation voice signal of a participation channel into a plurality of standard signal segments and a plurality of participation signal segments in a voice alignment scene; and carrying out pitch period calculation on each frame of signal to obtain a plurality of standard pitch period strings corresponding to the plurality of standard signal segments and a plurality of participating pitch period strings corresponding to the plurality of participating signal segments. And for a to-be-matched pitch period string in the plurality of standard pitch period strings and a plurality of candidate pitch period strings in the plurality of participating pitch period strings, performing dynamic time warping to obtain a plurality of distances between the to-be-matched pitch period string and the plurality of candidate pitch period strings. And when the minimum distance in the plurality of distances meets a preset similarity condition, determining more accurate time delay of the participating channel relative to the standard channel through the first alignment point time of the pitch period string to be matched and the second alignment point time of the candidate pitch period string corresponding to the minimum distance.

The invention discloses an audio frame supplementing method and device and a storage medium, and relates to the technical field of audio analysis, and the method comprises the steps: determining a corresponding pitch period and a sampling number according to a previous audio frame and a next audio frame of a lost audio frame, and then carrying out the sampling of the lost audio frame according to the pitch period, the sampling number and a target number; determining a target number and a target length of reconstructed audio blocks, then determining a first coefficient and a second coefficient of the previous audio frame and the next audio frame based on a discrete cosine transform algorithm, and determining the target number of reconstructed audio blocks according to the first coefficient and the second coefficient, and finally, intercepting a target audio block with the target length from the reconstructed audio block, and inserting the target audio block into the audio frame. According to the method, the audio frame missing in the middle is reconstructed through the previous audio frame and the next audio frame of the lost audio frame and is inserted into the audio frame, so that the cost for processing the packet loss of the audio data is reduced.

The present application discloses a speech rate recognition method, device, equipment and readable storage medium, which relates to the field of machine learning. The method includes: obtaining speech data, wherein the speech data includes at least two speech frames; extracting the pitch period state of the speech frame; establishing a histogram corresponding to the pitch period state; and predicting the speech rate based on the histogram to obtain a speech rate recognition result. By extracting the pitch period state of the speech frame in the speech data, and recognizing the speech rate of the speech data according to the continuous distribution of the pitch period state, it is not necessary to perform speech recognition on the speech data to obtain the text content, and then determine the speech rate according to the text content, thereby improving the efficiency of speech rate recognition. Since the amount of calculation required for speech recognition is large, speech rate recognition through the pitch period state can reduce the amount of calculation of the device and reduce the occupation of the device's calculation amount.

The present invention provides a prosody-controllable speech synthesis method and related device based on VITS, which relates to the field of speech synthesis technology. The method involves extracting prosody feature information from input text; semantically encoding the input text to generate a text context feature representation; constructing a prosody controller and independently modeling the prosody features to generate prediction results; fusing the text context feature representation with the prediction results to generate a prosody control embedding; generating a multi-speaker speech spectrum based on the VITS model, combining the prosody control embedding with speaker embedding vectors; and converting the multi-speaker speech spectrum into a time-domain speech signal through a decoder. By adjusting prosody feature parameters, the duration, pitch period, energy, pauses, and rhythm of the synthesized speech are independently controlled to improve the subjective quality of the generated speech signal.

The invention relates to a decoding and coding method and device, electronic equipment, a medium, a product and a system. The decoding method comprises the steps that a high-frequency harmonic level identifier and a signal of a first frequency band of an audio frame are analyzed from a code stream, the high-frequency harmonic level identifier is used for indicating the harmonic level of a second frequency band of the audio frame, and the frequency of the second frequency band is higher than that of the first frequency band; determining a signal of a second frequency band according to the pitch period of the audio frame, the high-frequency harmonic level identifier and the signal of the first frequency band; and obtaining a decoding signal of the audio frame according to the signal of the first frequency band and the signal of the second frequency band.

The invention provides a rhythm controllable speech synthesis method based on VITS and a related device, and relates to the technical field of speech synthesis. The method comprises the steps of extracting rhythm feature information from an input text; performing semantic coding on the input text to generate text context feature representation; constructing a rhythm controller, and performing independent modeling on the rhythm features to generate a prediction result; fusing the text context feature representation with the prediction result to generate rhythm control embedding; generating a multi-speaker speech spectrum based on a VITS model in combination with the rhythm control embedding and speaker embedding vectors; converting the multi-speaker speech spectrum into a time domain speech signal through a decoder; by adjusting the rhythm characteristic parameters, independent control of duration, pitch period, energy, pause and rhythm of the synthesized speech is realized, so that the subjective quality of the generated speech signal is improved.

This application provides a speech processing method and an electronic device. The speech processing method includes: extracting features from acquired speech to be processed to obtain a speech signal-to-noise ratio (SNR); processing the speech to be processed to obtain feature parameters, including at least one of pitch period probability, zero-crossing rate, and energy ratio; and denoising the speech to be processed based on a preset denoising algorithm and the feature parameters to determine the target speech. Thus, during the denoising process of the speech to be processed, at least one of the three parameters—pitch period probability, zero-crossing rate, and energy ratio—can be introduced to assist in the protection of voiced and unvoiced sounds, based on the SNR, and to effectively identify and distinguish noise data, thereby maintaining the original fidelity of the speech as much as possible and improving the speech quality of the target speech.

Techniques and systems are provided for speech synthesis. For instances, a process can include receiving a first predicted audio sample; causing the first predicted audio sample to be stored in one or more memories; and generating a second predicted audio sample based on the first predicted audio sample, wherein the second predicted audio sample is from a pitch period after the first predicted audio sample.

The invention provides a cross-language speaker recognition method and system based on voice fusion features, and relates to the technical field of voice process.The method comprises the steps that band-pass filtering is conducted on original voice signals, and voiced sound segments are extracted and integrated into new voice segments; extracting a pitch period and an MFCC feature in the new speech segment, and connecting in series to form a fusion feature vector; inputting multilingual speech segments of a plurality of testers, extracting fusion features, and training by using K-means clustering and an EM algorithm to obtain a GMM model of each speaker; inputting a test voice segment, extracting fusion features, calculating a likelihood probability score with the GMM model, comparing the score with a preset threshold, and confirming or rejecting the identity of a tester. According to the method, more stable features can be extracted from the voice signal, so that the accuracy of cross-language speaker recognition is improved, the situation of language mismatch of the speaker is effectively handled, the recognition performance is improved, and the method has high adaptability especially in a bilingual or multilingual application scene.

The application provides a cross-lingual speaker recognition method and system based on speech fusion features, and relates to the technical field of speech processing. The method extracts voiced segments and integrates them into new speech segments by band-pass filtering the original speech signal. The pitch period and MFCC features in the new speech segments are extracted and concatenated to form a fusion feature vector. Multilingual speech segments of multiple testers are input, fusion features are extracted, and GMM models of each speaker are trained using K-means clustering and EM algorithm. The test speech segment is input, the fusion features are extracted, the likelihood probability score is calculated with the GMM model, compared with the preset threshold, and the tester identity is confirmed or rejected. The application can extract more stable features from speech signals, thereby improving the accuracy of cross-lingual speaker recognition, effectively dealing with speaker language mismatch situations, improving recognition performance, and having strong adaptability, especially in bilingual or multilingual application scenarios.

The application discloses a kind of based on frame self-correlation's mobile terminal cough sound high trajectory and vocal cord disturbance combined extraction method, belong to audio signal processing technical field.The method includes: receiving cough audio signal and carrying out frame with fixed frame length and frame shift, obtain frame sequence;The self-correlation calculation of each frame is executed in pre-set lag range, take the lag amount corresponding to the maximum peak of self-correlation function and convert into the fundamental frequency value of this frame, form frame-level fundamental frequency sequence;Based on the frame-level fundamental frequency sequence, calculate pitch statistical features, the pitch statistical features include fundamental frequency mean and fundamental frequency standard deviation;Based on the fundamental frequency difference absolute value of adjacent frame and the fundamental frequency mean, calculate frame-level frequency microdisturbance;Based on the root mean square amplitude difference absolute value of adjacent frame, calculate frame-level amplitude microdisturbance.The application directly reuses frame-level self-correlation pitch detection result in vocal cord disturbance feature extraction, without pitch period mark, applicable to cough class non-steady-state signal, realize the joint extraction of pitch trajectory and vocal cord disturbance feature on mobile terminal, give consideration to computational efficiency and extraction stability.

The invention belongs to the technical field of data processing, and discloses an intelligent recommendation method and system based on a vocal music teaching platform, and the method comprises the steps: collecting multi-modal user data; the multi-modal user data comprises user singing audio data and singing track preference data; performing pre-emphasis and pitch period evaluation on user singing audio data through a pitch trajectory tracking algorithm to obtain a pitch frequency; extracting the Mel-frequency cepstrum coefficient of the audio data sung by the user by adjusting the smoothing coefficient, and obtaining a tone feature vector of the user; splicing the fundamental tone frequency and the user timbre feature vector to obtain technical performance data; performing K-Means clustering grouping on the singing track preference data to obtain emotion demand data; based on the technical performance data and the emotion demand data, constructing a user portrait by using a cross-modal attention mechanism algorithm; the objective of the invention is to provide vocal music teaching resources better meeting actual demands for users.

The invention provides an audio data processing method and device, electronic equipment and a storage medium, and relates to the technical field of audio enhancement, and the method comprises the steps: presetting a partial waveform parameter database and an audio overtone parameter database of a to-be-processed audio periodic wave; to-be-processed audio periodic wave data stored in an audio cache region is obtained, and when the computer equipment receives the to-be-processed audio periodic wave data, the received to-be-processed audio periodic wave data are stored in the audio cache region; according to the to-be-processed audio periodic wave data and the corresponding partial waveform parameter of the to-be-processed audio periodic wave, determining partial waveform data of the to-be-processed audio periodic wave; determining audio overtone 1 / 2 periodic wave data according to the audio 1 / 2 periodic wave data to be processed and the corresponding audio overtone 1 / 2 periodic wave parameters; the frequency of the audio overtone 1 / 2 periodic wave is a positive integer multiple of the frequency of the audio 1 / 2 periodic wave to be processed; splicing the partial waveform data of the audio periodic wave to be processed and the audio overtone 1 / 2 periodic wave data to obtain target audio enhanced periodic wave data; by adopting the method, the problems that the harmonic level is increased and the distortion of the audio pitch period signal is increased in the related technology of audio pitch period signal enhancement are solved, the audio quality of the to-be-processed audio period signal subjected to audio enhancement is improved, the audio is beautified, and the user experience is improved.