Abstract: A device for removing wind noise is provided. The device includes: processors configured to execute more instructions to control: a correlation maximizing filter to output a third sound signal to a first channel based on a first sound signal, a second sound signal and a first weight vector, and output a fourth sound signal to a second channel based on the first sound signal, the second sound signal and a second weight vector; a sound source separator to receive the third and fourth sound signals through the first and second channels, and perform a sound source separation to output a fifth and sixth sound signals to the first and second channels; a residual wind noise remover to receive the fifth and sixth sound signals, and perform a residual wind noise removal based on the fifth and sixth sound signals to generate an output signal.

Abstract: A wearable device may include a processor configured to detect a self-voice signal, based on one or more transducers. The processor may be configured to separate the self-voice signal from a background signal in an external audio signal based on using a multi-microphone speech generative network. The processor may also be configured to apply a first filter to an external audio signal, detected by at least one external microphone on the wearable device, during a listen through operation based on an activation of the audio zoom feature to generate a first listen-through signal that includes the external audio signal. The processor may be configured to produce an output audio signal that is based on at least the first listen-through signal that includes the external signal, and is based on the detected self-voice signal.

Abstract: A device includes one or more processors configured to determine, based on data descriptive of two or more audio environments, a geometry of a mutual audio environment. The one or more processors are also configured to process audio data, based on the geometry of the mutual audio environment, for output at an audio device disposed in a first audio environment of the two or more audio environments.

Abstract: 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.

Abstract: A device includes one or more processors configured to perform signal processing including a linear transformation and a non-linear transformation of an input signal to generate a reference target signal. The reference target signal has a linear component associated with the linear transformation and a non-linear component associated with the non-linear transformation. The one or more processors are also configured to perform linear filtering of the input signal by controlling adaptation of the linear filtering to generate an output signal that substantially matches the linear component of the reference target signal.

Abstract: A device to perform speech enhancement includes one or more processors configured to process image data to detect at least one of an emotion, a speaker characteristic, or a noise type. The one or more processors are also configured to generate context data based at least in part on the at least one of the emotion, the speaker characteristic, or the noise type. The one or more processors are further configured to obtain input spectral data based on an input signal. The input signal represents sound that includes speech. The one or more processors are also configured to process, using a multi-encoder transformer, the input spectral data and the context data to generate output spectral data that represents a speech enhanced version of the input signal.

Abstract: A device includes a memory configured to store instructions and one or more processors configured execute the instructions. The one or more processors are configured execute the instructions to receive audio data including first audio data corresponding to a first output of a first microphone and second audio data 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 dynamic classifier. The dynamic classifier is configured to generate a classification output corresponding to the audio data. The one or more processors are further configured to execute the instructions to determine, at least partially based on the classification output, whether the audio data corresponds to user voice activity.

Abstract: A device to process speech includes a speech processing network that includes an input configured to receive audio data. The speech processing network also includes one or more network layers configured to process the audio data to generate a network output. The speech processing network includes an output configured to be coupled to multiple speech application modules to enable the network output to be provided as a common input to each of the multiple speech application modules.

Abstract: Methods, systems, and devices for signal processing are described. Generally, as provided for by the described techniques, a wearable device to receive an input audio signal from one or more outer microphones, an input audio signal from one or more inner microphones, and a bone conduction signal from a bone conduction sensor based on the input audio signals. The wearable device may filter the bone conduction signal based on a set of frequencies of the input audio signals, such as a low frequency portion of the input audio signals. For example, the wearable device may apply a filter to the bone conduction signal that accounts for an error in the input audio signals. The wearable device may add a gain to the filtered bone conduction signal and may equalize the filtered bone conduction signal based on the gain. The wearable device may output an audio signal to a speaker.

Abstract: A wearable device may include a processor configured to perform active noise cancelation (ANC) applied to an input audio signal received by at least one microphone, and detect a self-voice signal, based on one or more transducers. The processor may also be configured to apply a first filter to an external audio signal, detected by at least one external microphone on the wearable device, during a listen through operation based on an activation of the audio zoom feature to generate a first listen-through signal that includes the external audio signal. The processor may also be configured to after the activation of the audio zoom feature terminate a second filter that provides low frequency compensation. The processor may be configured to produce an output audio signal that is based on at least the first listen-through signal that includes the external signal, and is based on the detected self-voice signal.

Abstract: A device includes a memory configured to store untransformed ambisonic coefficients at different time segments. The device includes one or more processors configured to obtain the untransformed ambisonic coefficients at the different time segments, where the untransformed ambisonic coefficients at the different time segments represent a soundfield at the different time segments. The one or more processors are configured to apply one adaptive network, based on a constraint that includes preservation of a spatial direction of one or more audio sources in the soundfield at the different time segments, to the untransformed ambisonic coefficients at the different time segments to generate transformed ambisonic coefficients at the different time segments, wherein the transformed ambisonic coefficients at the different time segments represent a modified soundfield at the different time segments, that was modified based on the constraint.

Abstract: A device includes one or more processors configured to obtain audio signals representing sound captured by at least three microphones and determine spatial audio data based on the audio signals. The one or more processors are further configured to determine a metric indicative of wind noise in the audio signals. The metric is based on a comparison of a first value and a second value. The first value corresponds to an aggregate signal based on the spatial audio data, and the second value corresponds to a differential signal based on the spatial audio data.

Abstract: A device to perform speech enhancement includes one or more processors configured to obtain input spectral data based on an input signal. The input signal represents sound that includes speech. The one or more processors are also configured to process, using a multi-encoder transformer, the input spectral data and context data to generate output spectral data that represents a speech enhanced version of the input signal.

Abstract: Systems, methods and computer-readable media are provided for speech enhancement using a hybrid neural network. An example process can include receiving, by a first neural network portion of the hybrid neural network, audio data and reference data, the audio data including speech data, noise data, and echo data; filtering, by the first neural network portion, a portion of the audio data based on adapted coefficients of the first neural network portion, the portion of the audio data including the noise data and/or echo data; based on the filtering, generating, by the first neural network portion, filtered audio data including the speech data and an unfiltered portion of the noise data and/or echo data; and based on the filtered audio data and the reference data, extracting, by a second neural network portion of the hybrid neural network, the speech data from the filtered audio data.

Abstract: A device to process speech includes a speech processing network that includes an input configured to receive audio data corresponding to audio captured by one or more microphones. The speech processing network also includes one or more network layers configured to process the audio data to generate a network output. The speech processing network includes an output configured to be coupled to multiple speech application modules to enable the network output to be provided as a common input to each of the multiple speech application modules. A first speech application module corresponds to a speaker verifier, and a second speech application module corresponds to a speech recognition network.

Abstract: A device for speech generation includes one or more processors configured to receive one or more control parameters indicating target speech characteristics. The one or more processors are also configured to process, using a multi-encoder, an input representation of speech based on the one or more control parameters to generate encoded data corresponding to an audio signal that represents a version of the speech based on the target speech characteristics.

Abstract: A device includes one or more processors configured to execute instructions to determine a first phase based on a first audio signal of first audio signals and to determine a second phase based on a second audio signal of second audio signals. The one or more processors are also configured to execute the instructions to apply spatial filtering to selected audio signals of the first audio signals and the second audio signals to generate an enhanced audio signal. The one or more processors are further configured to execute the instructions to generate a first output signal including combining a magnitude of the enhanced audio signal with the first phase and to generate a second output signal including combining the magnitude of the enhanced audio signal with the second phase. The first output signal and the second output signal correspond to an audio zoomed signal.

Abstract: A device includes a memory configured to store untransformed ambisonic coefficients at different time segments. The device also includes one or more processors configured to obtain the untransformed ambisonic coefficients at the different time segments, where the untransformed ambisonic coefficients at the different time segments represent a soundfield at the different time segments. The one or more processors are also configured to apply one adaptive network, based on a constraint, to the untransformed ambisonic coefficients at the different time segments to generate transformed ambisonic coefficients at the different time segments, wherein the transformed ambisonic coefficients at the different time segments represent a modified soundfield at the different time segments, that was modified based on the constraint.

Abstract: A device includes processors configured to determine, in a first power mode, whether an audio stream corresponds to speech of at least two talkers. The processors are configured to, based on determining that the audio stream corresponds to speech of at least two talkers, analyze, in a second power mode, audio feature data of the audio stream to generate a segmentation result. The processors are configured to perform a comparison of a plurality of user speech profiles to an audio feature data set of a plurality of audio feature data sets of a talker-homogenous audio segment to determine whether the audio feature data set matches any of the user speech profiles. The processors are configured to, based on determining that the audio feature data set does not match any of the plurality of user speech profiles, generate a user speech profile based on the plurality of audio feature data sets.

Abstract: A wearable device may include a processor configured to perform active noise cancelation (ANC) applied to an input audio signal received by at least one microphone, and detect a self-voice signal, based on one or more transducers. The processor may also be configured to apply a first filter to an external audio signal, detected by at least one external microphone on the wearable device, during a listen through operation based on an activation of the audio zoom feature to generate a first listen-through signal that includes the external audio signal. The processor may also be configured to after the activation of the audio zoom feature terminate a second filter that provides low frequency compensation. The processor may be configured to produce an output audio signal that is based on at least the first listen-through signal that includes the external signal, and is based on the detected self-voice signal.