Google Inc.

Mitsubishi Electric Research Laboratories, Inc.

Hologic, Inc.

Other

Kevin William Wilson

Tara N Sainath

Ron J Weiss

Michiel A U Bacchiani

Bo Li

Arun Narayanan

Andrew William Senior

Ehsan Variani

William T Freeman

Ajay Divakaran

Michael Rubinstein

Avinatan Hassidim

Inbar Mosseri

Tali Dekel

Ariel Ephrat

Oran Lang

Jay A Stein

Thomas L Kelly

Paris Smaragdis

Kyung T Park

Bhiksha Ramakrishnan

Isao Otsuka

Mitchell L Thompson

Klaus Kubierschky

Feng Niu

Naveen Goela

Yedid Hoshen

Julie M Robino

Yubo Cheng

Xiaoqian Jiang

Glen MacGibbon

Dick Cabral

Hong Wang

Michiel AU Bacchiani

A system for measuring muscle mass of a patient has a dual-energy radiation emission source. A radiation detector is configured to detect radiation emitted from the dual-energy radiation emission source passed through the patient. A processor has a memory with storing instructions, that when executed by the processor, perform a set of operations. The operations include receiving radiation detection data; generating a scan representation; identifying a primary fat target; determining an amount of fat in the primary fat target; comparing the amount of fat in the primary fat target to a reference; and based on the comparison, correcting an estimated amount of lean tissue to generate a corrected muscle mass value.

Methods for physiological state determination in body scans

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: obtaining, for each frame in a stream of frames from a video in which faces of one or more speakers have been detected, a respective per-frame face embedding of the face of each speaker; processing, for each speaker, the per-frame face embeddings of the face of the speaker to generate visual features for the face of the speaker; obtaining a spectrogram of an audio soundtrack for the video; processing the spectrogram to generate an audio embedding for the audio soundtrack; combining the visual features for the one or more speakers and the audio embedding for the audio soundtrack to generate an audio-visual embedding for the video; determining a respective spectrogram mask for each of the one or more speakers; and determining a respective isolated speech spectrogram for each speaker.

Audio-visual speech separation

This specification describes computer-implemented methods and systems. One method includes receiving, by a neural network of a speech recognition system, first data representing a first raw audio signal and second data representing a second raw audio signal. The first raw audio signal and the second raw audio signal describe audio occurring at a same period of time. The method further includes generating, by a spatial filtering layer of the neural network, a spatial filtered output using the first data and the second data, and generating, by a spectral filtering layer of the neural network, a spectral filtered output using the spatial filtered output. Generating the spectral filtered output comprises processing frequency-domain data representing the spatial filtered output. The method still further includes processing, by one or more additional layers of the neural network, the spectral filtered output to predict sub-word units encoded in both the first raw audio signal and the second raw audio signal.

Enhanced multi-channel acoustic models

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for neural network adaptive beamforming for multichannel speech recognition are disclosed. In one aspect, a method includes the actions of receiving a first channel of audio data corresponding to an utterance and a second channel of audio data corresponding to the utterance. The actions further include generating a first set of filter parameters for a first filter based on the first channel of audio data and the second channel of audio data and a second set of filter parameters for a second filter based on the first channel of audio data and the second channel of audio data. The actions further include generating a single combined channel of audio data. The actions further include inputting the audio data to a neural network. The actions further include providing a transcription for the utterance.

Adaptive audio enhancement for multichannel speech recognition

Multichannel speech recognition using neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing audio waveforms. In some implementations, a time-frequency feature representation is generated based on audio data. The time-frequency feature representation is input to an acoustic model comprising a trained artificial neural network. The trained artificial neural network comprising a frequency convolution layer, a memory layer, and one or more hidden layers. An output that is based on output of the trained artificial neural network is received. A transcription is provided, where the transcription is determined based on the output of the acoustic model.

Processing audio waveforms

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using neural networks. One of the methods includes receiving, by a neural network in a speech recognition system, first data representing a first raw audio signal and second data representing a second raw audio signal, the first raw audio signal and the second raw audio signal for the same period of time, generating, by a spatial filtering convolutional layer in the neural network, a spatial filtered output the first data and the second data, generating, by a spectral filtering convolutional layer in the neural network, a spectral filtered output using the spatial filtered output, and processing, by one or more additional layers in the neural network, the spectral filtered output to predict sub-word units encoded in both the first raw audio signal and the second raw audio signal.

Multichannel raw-waveform neural networks

Methods, including computer programs encoded on a computer storage medium, for enhancing the processing of audio waveforms for speech recognition using various neural network processing techniques. In one aspect, a method includes: receiving multiple channels of audio data corresponding to an utterance; convolving each of multiple filters, in a time domain, with each of the multiple channels of audio waveform data to generate convolution outputs, wherein the multiple filters have parameters that have been learned during a training process that jointly trains the multiple filters and trains a deep neural network as an acoustic model; combining, for each of the multiple filters, the convolution outputs for the filter for the multiple channels of audio waveform data; inputting the combined convolution outputs to the deep neural network trained jointly with the multiple filters; and providing a transcription for the utterance that is determined.

Processing multi-channel audio waveforms

A method selects features used in continuous-valued regression analysis. Training data input to the method includes features and corresponding target values, wherein the target values are continuous, and there is one target value for each feature. Each threshold value is thresholded and discretized with respect to a threshold value to produce a discretized target value. Then, categorical feature selection is applied to the features, using the discrete target values, to produces selected features. The selected values can be used in any regression analysis.

Method for selecting features used in continuous-valued regression analysis

Growing community of inventors

Cambridge, MA, United States of America

Kevin William Wilson