93 results about "SPEECH DISTORTION" patented technology

A method of reducing noise by cascading a plurality of noise reduction algorithms is provided. A sequence of noise reduction algorithms are applied to the noisy signal. The noise reduction algorithms are cascaded together, with the final noise reduction algorithm in the sequence providing the system output signal. The sequence of noise reduction algorithms includes a plurality of noise reduction algorithms that are sufficiently different from each other such that resulting distortions and artifacts are sufficiently different to result in reduced human perception of the artifact and distortion levels in the system output signal.

Hands-free phones with voice activity detection using a comparison of frame power estimate with an adaptive frame noise power estimate, automatic gain control with fast adaptation and minimal speech distortion, echo cancellation updated in the frequency domain with stepsize optimization and smoothed spectral whitening, and echo suppression with adaptive talking-state transitions.

The present technology provides adaptive noise reduction of an acoustic signal using a sophisticated level of control to balance the tradeoff between speech loss distortion and noise reduction. The energy level of a noise component in a sub-band signal of the acoustic signal is reduced based on an estimated signal-to-noise ratio of the sub-band signal, and further on an estimated threshold level of speech distortion in the sub-band signal. In embodiments, the energy level of the noise component in the sub-band signal may be reduced to no less than a residual noise target level. Such a target level may be defined as a level at which the noise component ceases to be perceptible.

A method of reducing noise by cascading a plurality of noise reduction algorithms is provided. A sequence of noise reduction algorithms are applied to the noisy signal. The noise reduction algorithms are cascaded together, with the final noise reduction algorithm in the sequence providing the system output signal. The sequence of noise reduction algorithms includes a plurality of noise reduction algorithms that are sufficiently different from each other such that resulting distortions and artifacts are sufficiently different to result in reduced human perception of the artifact and distortion levels in the system output signal.

The present technology provides a robust noise suppression system which may concurrently reduce noise and echo components in an acoustic signal while limiting the level of speech distortion. An acoustic signal may be received and transformed to cochlear domain sub-band signals. Features such as pitch may be identified and tracked within the sub-band signals. Initial speech and noise models may be then be estimated at least in part from a probability analysis based on the tracked pitch sources. Speech and noise models may be resolved from the initial speech and noise models and noise reduction may be performed on the sub-band signals and an acoustic signal may be reconstructed from the noise-reduced sub-band signals.

Hands-free phones with voice activity detection using a comparison of frame power estimate with an adaptive frame noise power estimate, automatic gain control with fast adaptation and minimal speech distortion, echo cancellation updated in the frequency domain with stepsize optimization and smoothed spectral whitening, and echo suppression with adaptive talking-state transitions.

A robust noise reduction system may concurrently reduce noise and echo components in an acoustic signal while limiting the level of speech distortion. The system may receive acoustic signals from two or more microphones in a close-talk, hand-held or other configuration. The received acoustic signals are transformed to cochlea domain sub-band signals and echo and noise components may be subtracted from the sub-band signals. Features in the acoustic sub-band signals are identified and used to generate a multiplicative mask. The multiplicative mask is applied to the noise subtracted sub-band signals and the sub-band signals are reconstructed in the time domain.

A band division noise suppressor suppressing noise sufficiently with a small amount of processing and a little voice distortion. In the band division noise suppressor, a band dividing section (101) divides an input voice signal into a low band voice signal and a high band voice signal. The low band voice signal is subjected to decimate at a decimation section (102), subjected to noise suppression at a low band noise suppressing section (103), and then interpolated at an interpolation section (104). On the other hand, the high band voice signal is subjected to noise suppression at a high band noise suppressing section (105). A band combination section (106) composes the bands of low-band and high-band voice signals subjected to noise suppression and outputs a voice signal subjected to noise suppression over the entire band.

Hands-free phones with voice activity detection using a comparison of frame power estimate with an adaptive frame noise power estimate, automatic gain control with fast adaptation and minimal speech distortion, echo cancellation updated in the frequency domain with stepsize optimization and smoothed spectral whitening, and echo suppression with adaptive talking-state transitions.

A system that provides measurements of speech distortion that correspond closely to user perceptions of speech distortion is provided. The system calculates and analyzes first and second discrete derivatives to detect and determine the incidence of change in the voice waveform that would not have been made by human articulation because natural voice signals change at a limited rate. Statistical analysis is performed of both the first and second discrete derivatives to detect speech distortion by looking at the distribution of the signals. For example, the kurtosis of the signals is analyzed as well as the number of times these values exceed a predetermined threshold. Additionally, the number of times the first derivative data is less than a predetermined low value is analyzed to provide a level of speech distortion and clipping of the signal due to lost data packets.

A method and apparatus are provided for determining uncertainty in noise reduction based on a parametric model of speech distortion. The method is first used to reduce noise in a noisy signal. In particular, noise is reduced from a representation of a portion of a noisy signal to produce a representation of a cleaned signal by utilizing an acoustic environment model. The uncertainty associated with the noise reduction process is then computed. In one embodiment, the uncertainty of the noise reduction process is used, in conjunction with the noise-reduced signal, to decode a pattern state.

A method and apparatus are provided for determining uncertainty in noise reduction based on a parametric model of speech distortion. The method is first used to reduce noise in a noisy signal. In particular, noise is reduced from a representation of a portion of a noisy signal to produce a representation of a cleaned signal by utilizing an acoustic environment model. The uncertainty associated with the noise reduction process is then computed. In one embodiment, the uncertainty of the noise reduction process is used, in conjunction with the noise-reduced signal, to decode a pattern state.

Hands-free phones with voice activity detection using a comparison of frame power estimate with an adaptive frame noise power estimate, automatic gain control with fast adaptation and minimal speech distortion, echo cancellation updated in the frequency domain with stepsize optimization and smoothed spectral whitening, and echo suppression with adaptive talking-state transitions.

The invention relates to a method for reducing a noise by using the hearing threshold of impaired hearing. The method comprises the following steps of: dividing an input speech signal into N subband signals, compensating the hearing, respectively reducing the noise of the subband signals, and comprehensively processing various paths of input subband signals into a path of output signals by a weighted stacking filter bank. The invention provides a generalized spectral subtraction method according to noise levels and hearing threshold adjustment parameters, wherein a posteriori signal-to-noise ratio is replaced by an a priori signal-to-noise ratio to adjust a gain function, so that musical noise generated by noise reduction can be effectively reduced. The noise reduction gain function is related to the signal-to-noise ratio, and is adjusted according to the noise levels and the hearing threshold of a patient; when the hearing threshold is high, the suppression to the noise is low, and speech distortion is reduced simultaneously; and when the hearing threshold is low, the suppression to the noise is increased so as to improve listening comfort, so that the method has pertinence to different hearing loss conditions and different noise conditions, and makes the suppression effect and the speech distortion relatively balanced.

A robust noise reduction system may concurrently reduce noise and echo components in an acoustic signal while limiting the level of speech distortion. The system may receive acoustic signals from two or more microphones in a close-talk, hand-held or other configuration. The received acoustic signals are transformed to frequency domain sub-band signals and echo and noise components may be subtracted from the sub-band signals. Features in the acoustic sub-band signals are identified and used to generate a multiplicative mask. The multiplicative mask is applied to the noise subtracted sub-band signals and the sub-band signals are reconstructed in the time domain.

The invention discloses a double-talk detection and echo cancellation method based on zero-crossing rate, comprising the following steps: S1, zero-crossing rate calculation and double-talk monitoring: different echo cancellation strategies are adopted for double-talk and single-talk scenarios; S2, echo filter estimation and echo cancellation; there is difference between an echo signal collected by a microphone and a far-end signal because of room impulse response, and the echo component is eliminated from the signal collected by the microphone; and S3, recovery of a target speech harmonic structure. A harmonic structure analysis method is used to compensate for the missing harmonic components of near-end speech to further inhibit speech distortion. Compared with the traditional echo cancellation technology, double-end monitoring is realized based on the zero-crossing rate, and elimination of target speech is avoided. Based on the criterion of frequency-domain minimum mean square error, an echo cancellation filter converges rapidly. By adopting a frequency-domain parallel processing framework, the complexity is low. A speech distortion inhibition module is added, and the distortion degree of target speech is reduced.

The embodiment of the invention discloses a voice processing method, a voice processing device and a device for processing voice. The embodiment of the method comprises the following steps of performing time-frequency analysis on noisy voice to obtain the frequency spectrum of the noisy voice in complex domains; inputting the frequency spectrum of the noisy voice in the complex fields into a pretrained time-frequency shielding prediction model; obtaining a prediction value of time-frequency masking of the noisy voice in the complex domains; multiplying the prediction value by the frequency spectrum of the noisy voice in the complex domains; generating the frequency spectrum of target voice in the noisy voice in the complex domains; and synthesizing the target voice on the basis of the frequency spectrum of the target voice in the complex domains. The embodiment has the advantages that the voice distortion degree is reduced, and the voice noise reduction effect is improved.

The invention discloses a method, system and device for converting voice into a lip shape and a storage medium. The method comprises the steps: acquiring a voice sequence; receiving and processing thevoice sequence by using a trained generative adversarial network model; and obtaining a lip-shaped image output by the trained generative adversarial network model. According to the method, the generative adversarial network model (GAN) is trained, and the trained generative adversarial network model is utilized to convert the voice into the lip shape, so that the lip-shaped image with high quality and high resolution can be obtained; the generative adversarial network model is trained in an unsupervised learning mode, so that the voice quality can be obviously improved, the voice distortionis reduced, and the robustness of the system is enhanced; when changed voice is continuously input, a dynamic lip-shaped image can be finally output, and a smooth visual effect can be provided; and meanwhile, the generated lip-shaped image is combined with the voice, so that a high-quality face speaking video can be synthesized. The method, system and device are widely applied to the technical field of voice data.

A robust noise reduction system may concurrently reduce noise and echo components in an acoustic signal while limiting the level of speech distortion. The system may receive acoustic signals from two or more microphones in a close-talk, hand-held or other configuration. The received acoustic signals are transformed to frequency domain sub-band signals and echo and noise components may be subtracted from the sub-band signals. Features in the acoustic sub-band signals are identified and used to generate a multiplicative mask. The multiplicative mask is applied to the noise subtracted sub-band signals and the sub-band signals are reconstructed in the time domain.

A method for suppressing noise includes applying sectioned linear function to approximate interflow supergeomatric function and utilizing geometric column weight to carry out time axis smooth and frequency axis smooth on voice chart composition after minimum mean square error is estimated as well as regulating verified SNR for controlling balance between noise suppression and voice distortion.

A test system measures performance of telephone network echo cancellers using a primary criterion of estimated user annoyance due to audible returned echo. The invention generates live telephone calls, uses real speech samples as stimulus signals and provides tail-circuit emulation using actual measured telephone tail-circuit impulse responses. These features provide better ‘real-life’ test conditions for the echo canceller system under test than current ITU standard test methods. Two methods are employed for echo canceller performance evaluation via metrics of estimated user annoyance due to echo. Energy-based method employs point-by-point comparison of talker speech and talker echo signal energy envelopes and uses variable energy thresholds for estimation of echo audibility. A perceptual-model based method uses a Perceptual Speech Distortion Metric (PSDM), such as ITU P.861, in an unique configuration to estimate user annoyance due to audible echo. Echo canceller performance is tested under both single-talk and double-talk conditions. Innovative application of the PSDM method in double-talk tests allow estimation of quality of received double-talk speech.

The invention discloses a speech recognition method suitable for a noise environment. According to the speech recognition method, a beam-forming device which integrates minimum variance undistorted response beam-forming and diagonally loaded beam-forming is established for noisy speech signals collected by double micro microphone arrays, the computational complexity is reduced by using a recursivematrix inversion method, and after beam-forming is carried out, a speech signal which is preliminarily denoised is obtained; then a post-modulation domain spectral subtraction method further processes the preliminarily denoised speech signal, the residual noise is removed, the speech distortion is reduced, and the final denoised speech signal is obtained; and moreover, the speech recognition method adopts a convolution neural network to train speech models and extract deep features of speech. According to the speech recognition method, the problem of speech recognition rate decline in the noisy environment is solved, and the speech recognition method has the advantage of good robustness, can be applied to aspects such as household robots, intelligent speakers and speech devices working inthe noisy environment.

A harmonic synchronized electronic cochlea with lower speech distortion is composed of external unit and internal unit. Said external unit consists of speech signal input module with microphone and power amplifier, speech signal processing module with resonant spectrum analyzer, harmonic synchronization processing module, speech coding module, and emitting module. Said internal unit comprises receiver module, decoding module of stimulator, stimulating pulse generating module and stimulating electrode.

In prediction of a speech quality evaluation score such as a phone speech, even when a background noise exists, a subjective opinion score is predicted with high precision. A speech quality evaluation system that outputs a predicted value of the subjective opinion score for an evaluation speech such as a far-end speech of a phone, includes a speech distortion calculation unit conducts, after calculating frequency characteristics of the evaluation speech, a process of subtracting given frequency characteristics from frequency characteristics of the evaluation speech, and calculates the speech distortion on the basis of the frequency characteristics after the subtracting process has been conducted, and a subjective evaluation prediction unit that calculates the predicted value of the subjective opinion score on the basis of the speech distortion.

The invention discloses a noise elimination system and method of mobile phone microphones. A voice and noise activity detection device and a noise elimination module are utilized for performing noise elimination treatment on a noisy voice signal received by the main microphone and the secondary microphone of a mobile phone, and the problems that because an existing double-channel voice activity detection device depends on a fixed threshold value, voice and noise can not be accurately distinguished in a complex noise environment, and if the existing double-channel voice activity detection device is applied to a mobile phone noise elimination system, voice distorts, and speech intelligibility is lowered are solved. The situation that because the voice activity detection device makes a wrong judgment, the performance of the noise elimination system is lowered is reduced, the noise elimination system can perform accurate noise reduction on the noisy voice signal received by the microphones, and the quality of mobile phone communication is improved.

Systems and methods for adaptive intelligent noise suppression are provided. In exemplary embodiments, a primary acoustic signal is received. A speech distortion estimate is then determined based on the primary acoustic signal. The speech distortion estimate is used to derive control signals which adjust an enhancement filter. The enhancement filter is used to generate a plurality of gain masks, which may be applied to the primary acoustic signal to generate a noise suppressed signal.

Hands-free phones with voice activity detection using a comparison of frame power estimate with an adaptive frame noise power estimate, automatic gain control with fast adaptation and minimal speech distortion, echo cancellation updated in the frequency domain with stepsize optimization and smoothed spectral whitening, and echo suppression with adaptive talking-state transitions.