A sound crosstalk suppression device includes: a speaker analysis unit configured to analyze a speaker situation in a closed space based on voice signals respectively collected by a plurality of microphones arranged in the closed space; a filter update unit that includes a filter configured to generate a suppression signal of a crosstalk component included in a voice signal of a main speaker, that is configured to update a parameter of the filter, and that is configured to store the updated parameter in a memory; a reset unit configured to reset the parameter of the filter in a case where it is determined that an analysis result of the speaker situation is switched; and a crosstalk suppression unit configured to suppress a crosstalk component by using a suppression signal.

This application relates to the field of signal processing technologies and headsets, and provides a speech signal processing method and apparatus, to provide a full-band low-noise speech signal. The method is applied to a headset including at least two speech collectors, where the at least two speech collectors include an ear canal speech collector and at least one external speech collector. The method includes: preprocessing a speech signal that is in a first frequency band and that is collected by the ear canal speech collector, to obtain a first speech signal; preprocessing a speech signal that is in a second frequency band and that is collected by the at least one external speech collector, to obtain an external speech signal, where frequency ranges of the first frequency band and the second frequency band are different; performing correlation processing on the first speech signal and the external speech signal to obtain a second speech signal; and outputting a target speech signal, where the target speech signal includes the first speech signal and the second speech signal.

This application relates to the field of signal processing technologies and headsets, and provides a speech signal processing method and apparatus, to provide a full-band low-noise speech signal. The method is applied to a headset including at least two speech collectors, where the at least two speech collectors include an ear canal speech collector and at least one external speech collector. The method includes: preprocessing a speech signal that is in a first frequency band and that is collected by the ear canal speech collector, to obtain a first speech signal; preprocessing a speech signal that is in a second frequency band and that is collected by the at least one external speech collector, to obtain an external speech signal, where frequency ranges of the first frequency band and the second frequency band are different; performing correlation processing on the first speech signal and the external speech signal to obtain a second speech signal; and outputting a target speech signal, where the target speech signal includes the first speech signal and the second speech signal.

This application provides a speech signal processing method and apparatus, and relates to the field of signal processing technologies and earphone, to monitor an ambient sound signal and improve a monitoring effect and user experience. The method is applied to an earphone, where the earphone includes at least one external speech collector. The method includes: preprocessing a speech signal collected by the at least one external speech collector, to obtain an external speech signal; extracting an ambient sound signal from the external speech signal; and performing audio mixing processing on a first speech signal and the ambient sound signal based on amplitudes and phases of the first speech signal and the ambient sound signal and a location of the at least one external speech collector, to obtain a target speech signal.

This application provides a speech signal processing method and apparatus, and relates to the field of signal processing technologies and earphone, to monitor an ambient sound signal and improve a monitoring effect and user experience. The method is applied to an earphone, where the earphone includes at least one external speech collector. The method includes: preprocessing a speech signal collected by the at least one external speech collector, to obtain an external speech signal; extracting an ambient sound signal from the external speech signal; and performing audio mixing processing on a first speech signal and the ambient sound signal based on amplitudes and phases of the first speech signal and the ambient sound signal and a location of the at least one external speech collector, to obtain a target speech signal.

A device includes a memory configured to store instructions and one or more processors configured to execute the instructions. The one or more processors are configured to execute the instructions to receive audio data including a first audio frame corresponding to a first output of a first microphone and a second audio frame corresponding to a second output of a second microphone. The one or more processors are also configured to execute the instructions to provide the audio data to a first noise-suppression network and a second noise-suppression network. The first noise-suppression network is configured to generate a first noise-suppressed audio frame and the second noise-suppression network is configured to generate a second noise-suppressed audio frame. The one or more processors are further configured to execute the instructions to provide the noise-suppressed audio frames to an attention-pooling network. The attention-pooling network is configured to generate an output noise-suppressed audio frame.

Described herein is a method of determining parameters for a generative neural network for processing an audio signal, wherein the generative neural network includes an encoder stage mapping to a coded feature space and a decoder stage, each stage including a plurality of convolutional layers with one or more weight coefficients, the method comprising a plurality of cycles with sequential processes of: pruning the weight coefficients of either or both stages based on pruning control information, the pruning control information determining the number of weight coefficients that are pruned for respective convolutional layers; training the pruned generative neural network based on a set of training data; determining a loss for the trained and pruned generative neural network based on a loss function; and determining updated pruning control information based on the determined loss and a target loss. Further described are corresponding apparatus, programs, and computer-readable storage media.

Various embodiments herein provide a method for managing an audio based on a spectrogram. The method includes generating, by a transmitter device, the spectrogram of the audio. The method includes identifying a first spectrogram corresponding to vocals in the audio and a second spectrogram corresponding to music in the audio from the spectrogram of the audio, and extracting a music feature from the second spectrogram. The method includes transmitting a signal comprising the first spectrogram, the second spectrogram, the music feature and the audio to a receiver device. The method includes determining, by the receiver device, whether an audio drop is occurring in the received signal based on a parameter associated with the received signal. The method includes generating the audio using the first spectrogram, the second spectrogram, the music feature, in response to determining that the audio drop is occurring in the received signal.

Various embodiments herein provide a method for managing an audio based on a spectrogram. The method includes generating, by a transmitter device, the spectrogram of the audio. The method includes identifying a first spectrogram corresponding to vocals in the audio and a second spectrogram corresponding to music in the audio from the spectrogram of the audio, and extracting a music feature from the second spectrogram. The method includes transmitting a signal comprising the first spectrogram, the second spectrogram, the music feature and the audio to a receiver device. The method includes determining, by the receiver device, whether an audio drop is occurring in the received signal based on a parameter associated with the received signal. The method includes generating the audio using the first spectrogram, the second spectrogram, the music feature, in response to determining that the audio drop is occurring in the received signal.

A method, computer program product, and computing system for obtaining one or more speech signals from a first device, thus defining one or more first device speech signals. One or more speech signals may be obtained from a second device, thus defining one or more second device speech signals. One or more acoustic relative transfer functions mapping reverberation from the one or more first device speech signals to the one or more second device speech signals may be generated. One or more augmented second device speech signals may be generated based upon, at least in part, the one or more acoustic relative transfer functions and first device training data.