Abstract: A method includes receiving, as input, reference audio data representing a reference audio signal captured by an audio input device. The method also includes receiving, as input, from a beamformer, spatially-filtered audio data representing an output of the beamformer, the beamformer configured to spatially filter, based on additional audio data captured by one or more additional audio input devices, the reference audio data to attenuate one or more interfering signals in the spatially-filtered audio data. The method processes, using a trained guided speech-enhancement network, the reference audio data and the spatially-filtered audio data to generate, as output, enhanced audio data, the guided speech-enhancement network processing the reference audio data and the spatially-filtered audio data to further attenuate, in the enhanced audio data, the one or more interfering signals attenuated by the beamformer.

Abstract: A computer-implemented method of applying a trained neural network for sound separation based on distance estimation is provided. The method includes receiving, by an audio input component of a computing device, an audio mixture from one or more sources. The method includes predicting, by a trained distance estimation neural network and based on the audio mixture, respective distances of the one or more sources from the audio input component. The method includes determining one or more near sounds and one or more far sounds based on the respective distances. The near sounds correspond to sources that are located within a threshold distance of the audio input component, and the far sounds correspond to sources that are not located within the threshold distance of the audio input component. The method includes providing the predicted one or more near sounds.

Abstract: Methods and systems for one or more computers, in which a method includes obtaining encoding sequences of an input data item, in which each encoding sequence includes a respective encoding vector at each position of multiple positions. The method includes generating a combined encoding sequence by, at each position, combining the respective encoding vectors at the position in the multiple of encoding sequences. The method includes processing the combined encoding sequence using a deduplicator neural network to generate a deduplicated encoding sequence that includes a respective deduplicated encoding vector for each of the positions and applying a tokenizer to the deduplicated encoding sequence to identify, for each deduplicated encoding vector, a discrete representation of the deduplicated encoding vector generated from respective codebook vectors from each of a set of one or more codebooks, in which each codebook is a respective discrete set of codebook vectors.

Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.

Abstract: A method includes receiving target audio data captured by a first audio input device, the target audio data comprising a target audio signal and a first version of an interfering audio signal, and receiving reference audio data captured by a second audio input device different from the first audio input device, the reference audio data comprising a second version of the interfering audio signal. The method also includes processing, using a trained neural network, the target audio data and the reference audio data to generate enhanced audio data, the neural network attenuating the interfering audio signal in the enhanced audio data.

Abstract: A system and method are disclosed. Audio input comprising the mixed audio signals is received by one or more client devices. The audio input is converted into a plurality of discrete tokens. A plurality of sound sources, each corresponding to a subset of discrete tokens of a plurality of subsets of discrete tokens, is determined using a trained machine learning model.

Abstract: A method includes receiving, as input, reference audio data representing a reference audio signal captured by an audio input device. The method also includes receiving, as input, from a beamformer, spatially-filtered audio data representing an output of the beamformer, the beamformer configured to spatially filter, based on additional audio data captured by one or more additional audio input devices, the reference audio data to attenuate one or more interfering signals in the spatially-filtered audio data. The method processes, using a trained guided speech-enhancement network, the reference audio data and the spatially-filtered audio data to generate, as output, enhanced audio data, the guided speech-enhancement network processing the reference audio data and the spatially-filtered audio data to further attenuate, in the enhanced audio data, the one or more interfering signals attenuated by the beamformer.

Abstract: Implementations relate to an automated assistant that can bypass invocation phrase detection when an estimation of device-to-device distance satisfies a distance threshold. The estimation of distance can be performed for a set of devices, such as a computerized watch and a cellular phone, and/or any other combination of devices. The devices can communicate ultrasonic signals between each other, and the estimated distance can be determined based on when the ultrasonic signals are sent and/or received by each respective device. When an estimated distance satisfies the distance threshold, the automated assistant can operate as if the user is holding onto their cellular phone while wearing their computerized watch. This scenario can indicate that the user may be intending to hold their device to interact with the automated assistant and, based on this indication, the automated assistant can temporarily bypass invocation phrase detection (e.g., invoke the automated assistant).

Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.

Abstract: A system and method include reception of a first plurality of audio signals, generation of a second plurality of beamformed audio signals based on the first plurality of audio signals, each of the second plurality of beamformed audio signals associated with a respective one of a second plurality of beamformer directions, generation of a first TF mask for a first output channel based on the first plurality of audio signals, determination of a first beamformer direction associated with a first target sound source based on the first TF mask, generation of first features based on the first beamformer direction and the first plurality of audio signals, determination of a second TF mask based on the first features, and application of the second TF mask to one of the second plurality of beamformed audio signals associated with the first beamformer direction.

Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.

Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.

Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.

Abstract: This document relates to separation of audio signals into speaker-specific signals. One example obtains features reflecting mixed speech signals captured by multiple microphones. The features can be input a neural network and masks can be obtained from the neural network. The masks can be applied one or more of the mixed speech signals captured by one or more of the microphones to obtain two or more separate speaker-specific speech signals, which can then be output.

Abstract: A system and method include reception of a first plurality of audio signals, generation of a second plurality of beamformed audio signals based on the first plurality of audio signals, each of the second plurality of beamformed audio signals associated with a respective one of a second plurality of beamformer directions, generation of a first TF mask for a first output channel based on the first plurality of audio signals, determination of a first beamformer direction associated with a first target sound source based on the first TF mask, generation of first features based on the first beamformer direction and the first plurality of audio signals, determination of a second TF mask based on the first features, and application of the second TF mask to one of the second plurality of beamformed audio signals associated with the first beamformer direction.

Abstract: A system and method include reception of a first plurality of audio signals, generation of a second plurality of beamformed audio signals based on the first plurality of audio signals, each of the second plurality of beamformed audio signals associated with a respective one of a second plurality of beamformer directions, generation of a first TF mask for a first output channel based on the first plurality of audio signals, determination of a first beamformer direction associated with a first target sound source based on the first TF mask, generation of first features based on the first beamformer direction and the first plurality of audio signals, determination of a second TF mask based on the first features, and application of the second TF mask to one of the second plurality of beamformed audio signals associated with the first beamformer direction.

Abstract: Embodiments are associated with determination of a first plurality of multi-dimensional vectors, each of the first plurality of multi-dimensional vectors representing speech of a target speaker, determination of a multi-dimensional vector representing a speech signal of two or more speakers, determination of a weighted vector representing speech of the target speaker based on the first plurality of multi-dimensional vectors and on similarities between the multi-dimensional vector and each of the first plurality of multi-dimensional vectors, and extraction of speech of the target speaker from the speech signal based on the weighted vector and the speech signal.

Abstract: A system and method include reception of a first plurality of audio signals, generation of a second plurality of beamformed audio signals based on the first plurality of audio signals, each of the second plurality of beamformed audio signals associated with a respective one of a second plurality of beamformer directions, generation of a first TF mask for a first output channel based on the first plurality of audio signals, determination of a first beamformer direction associated with a first target sound source based on the first TF mask, generation of first features based on the first beamformer direction and the first plurality of audio signals, determination of a second TF mask based on the first features, and application of the second TF mask to one of the second plurality of beamformed audio signals associated with the first beamformer direction.

Abstract: This document relates to separation of audio signals into speaker-specific signals. One example obtains features reflecting mixed speech signals captured by multiple microphones. The features can be input a neural network and masks can be obtained from the neural network. The masks can be applied one or more of the mixed speech signals captured by one or more of the microphones to obtain two or more separate speaker-specific speech signals, which can then be output.

Abstract: A method transforms a noisy audio signal to an enhanced audio signal, by first acquiring the noisy audio signal from an environment. The noisy audio signal is processed by an enhancement network having network parameters to jointly produce a magnitude mask and a phase estimate. Then, the magnitude mask and the phase estimate are used to obtain the enhanced audio signal.