Google Inc.

Ryan Michael Rifkin

Richard Francis Lyon

Pascal Tom Getreuer

Ron J Weiss

Yuxuan Wang

Yonghui Wu

Zhifeng Chen

Navdeep Jaitly

Ioannis Agiomyrgiannakis

Zongheng Yang

Tomer Shekel

Chien-Jung Kung

Byungchul Kim

Tavis A Maclellan

Chet N Gnegy

Quoc V Le

Samuel Bengio

Robert Andrew James Clark

Russell J Ryan

Ying Xiao

Mohammed Waleed Kadous

Brian Patrick Williams

Andrew Ames Bunner

Douglas Eck

Nadav Aharony

Thomas Chadwick Walters

Marc Stogaitis

Alan Lee Gardner, Iii

Aren Jansen

Zhentao Sun

Daniel Ellis

Kenneth John Mackay

Thomas Chao

Richard Daniel Webb

Ami Patel

Joseph A Farfel

Brian Duff

Daniel Estrada Alva

Benjamin Razon

Tony Weber

Liem Tran

Yu Zhang

Samy Bengio

Adam L Berenzweig

Jay Michael Ponte

Ruoming Pang

Jason Edward Weston

Daniel Ramage

Michael Schuster

Jonathan Shen

Russell John Wyatt Skerry-Ryan

Kenneth MacKay

Sally A Goldman

Geremy A Heitz, Iii

Jay Yagnik

Christian Plagemann

Boris Smus

Christopher Thaddeus Hughes

Katherine Irene Chou

Murphy Stein

Alvin Rishi Rajkomar

Ankit Mohan

Ian Rickard Muldoon

Rasmus Munk Larsen

Sarvjeet Singh

Anandsudhakar Kesari

Henry George Wei

Manoj Plakal

David Parish

Yi-Fan Chen

Shawn Hershey

Jiayang Liu

Ratheet Pandya

John Roberts Anderson

Richard Channing Moore

Michael Dwight Howell

Kasumi Widner

Michael Philip Brenner

Murphy Martin Stein

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating speech from text. One of the systems includes one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to implement: a sequence-to-sequence recurrent neural network configured to: receive a sequence of characters in a particular natural language, and process the sequence of characters to generate a spectrogram of a verbal utterance of the sequence of characters in the particular natural language; and a subsystem configured to: receive the sequence of characters in the particular natural language, and provide the sequence of characters as input to the sequence-to-sequence recurrent neural network to obtain as output the spectrogram of the verbal utterance of the sequence of characters in the particular natural language.

End-to-end text-to-speech conversion

Methods, systems, and computer program products for generating, from an input character sequence, an output sequence of audio data representing the input character sequence. The output sequence of audio data includes a respective audio output sample for each of a number of time steps. One example method includes, for each of the time steps: generating a mel-frequency spectrogram for the time step by processing a representation of a respective portion of the input character sequence using a decoder neural network; generating a probability distribution over a plurality of possible audio output samples for the time step by processing the mel-frequency spectrogram for the time step using a vocoder neural network; and selecting the audio output sample for the time step from the possible audio output samples in accordance with the probability distribution.

Synthesizing speech from text using neural networks

The present disclosure provides systems and methods that generating health diagnostic information from an audio recording. A computing system can include a machine-learned health model comprising that includes a sound model trained to receive data descriptive of a patient audio recording and output sound description data. The computing system can include a diagnostic model trained to receive the sound description data and output a diagnostic score. The computing system can include at least one tangible, non-transitory computer-readable medium that stores instructions that, when executed, cause the processor to perform operations. The operations can include obtaining the patient audio recording; inputting data descriptive of the patient audio recording into the sound model; receiving, as an output of the sound model, the sound description data; inputting the sound description data into the diagnostic model; and receiving, as an output of the diagnostic model, the diagnostic score.

System and method for generating diagnostic health information using deep learning and sound understanding

In a general aspect, a system for media playback can include a first media playback device configured to receive a media stream from a media casting device over a data network, the first media playback device being a member of the media playback group and a second media playback device configured to receive the media stream, the second media playback device being a member of the media playback group. The first media playback device and the second media playback device can be collectively configured to designate one of the first media playback device and the second media playback device as a leader playback device of the media playback group. The playback device not designated as the leader playback device can be designated as a follower playback device of the media playback group. The first media playback device and the second media playback device can be further collectively configured to determine a clock offset between the leader playback device and the follower playback device. The leader playback device can be configured to receive a broadcast of the media stream over the data network; play the media stream; and provide the media stream to the follower playback device. The follower playback device can be configured to play the media stream in synchronization with the leader playback device based on the clock offset.

Time-synchronized, multizone media streaming

A computing system can include an embedding model and a clustering model. The computing system input each of the plurality of inputs into the embedding model and receiving respective embeddings for the plurality of inputs as outputs of the embedding model. The computing system can input the respective embeddings for the plurality of inputs into the clustering model and receiving respective cluster assignments for the plurality of inputs as outputs of the clustering model. The computing system can evaluate a clustering loss function that evaluates a first average, across the plurality of inputs, of a respective first entropy of each respective probability distribution; and a second entropy of a second average of the probability distributions for the plurality of inputs. The computing system can modify parameter(s) of one or both of the clustering model and the embedding model based on the clustering loss function.

Minimum-example/maximum-batch entropy-based clustering with neural networks

Generating a playlist may include designating a seed track in an audio library; identifying audio tracks in the audio library having constructs that are within a range of a corresponding construct of the seed track, where the constructs for the audio tracks are derived from frequency representations of the audio tracks, and the corresponding construct for the seed track is derived from a frequency representation of the seed track; and generating the playlist using at least some of the audio tracks that were identified.

Generating a playlist

Methods are provided for generating training triplets that can be used to train multidimensional embeddings to represent the semantic content of non-speech sounds present in a corpus of audio recordings. These training triplets can be used with a triplet loss function to train the multidimensional embeddings such that the embeddings can be used to cluster the contents of a corpus of audio recordings, to facilitate a query-by-example lookup from the corpus, to allow a small number of manually-labeled audio recordings to be generalized, or to facilitate some other audio classification task. The triplet sampling methods may be used individually or collectively, and each represent a respective heuristic about the semantic structure of audio recordings.

Unsupervised learning of semantic audio representations

The various implementations described herein include methods, devices, and systems for recognizing speech, such as user commands. In one aspect, a method includes: (1) receiving audio input data via the one or more microphones; (2) generating a plurality of energy channels for the audio input data; (3) generating a feature vector by performing a per-channel normalization to each channel of the plurality of energy channels; and (4) obtaining recognized speech from the audio input utilizing the feature vector.

Systems and methods for recognizing user speech

Growing community of inventors

Oakland, CA, United States of America

Ryan Michael Rifkin