Google Inc.

International Business Machines Corporation

Other

Andrew William Senior

Arun Hampapur

Hasim Sak

Sharathchandra UmapathiRao Pankanti

Ying-Li Tian

Vincent Olivier Vanhoucke

Michiel A U Bacchiani

Georg Heigold

Trausti T Kristjansson

Chiao-Fe Shu

Lisa Marie Brown

Erik Mcdermott

John Nicholas Jitkoff

Jonathan Hudson Connell, Ii

Lisa Maire Brown

Dave Burke

Kanury Kanishka Rao

Konrad Gianno

Ignacio Lopez Moreno

Michael J Lebeau

Rudolf Maarten Bolle

Tara N Sainath

Chalapathy Venkata Neti

Sankar Basu

Stephane Herman Maes

Ron J Weiss

Kevin William Wilson

Byungha Chun

Javier Gonzalvo Fructuoso

Nalini Kanta Ratha

Yun Zhai

Michael J LeBeau

Brenda Lynn Dietrich

Zuoxuan Lu

Sergio Borger

Chidanand V Apte

Senem Velipasalar

Raymond A Cooke

Marc'aurelio Ranzato

Philippe Christian De Cuetos

Christopher R Carlson

Jeffrey Adgate Dean

Nitendra Rajput

Oriol Vinyals

Sanjiv Kumar

Ashish Verma

L Venkata Subramaniam

Arun Narayanan

Martin G Kienzle

Eugene Weinstein

Lalit Agarwalla

Jonathan H Connell

Patrick An Phu Nguyen

Matthieu Devin

Michael Schuster

Yiming Ye

Hayden Shaw

Izhak Shafran

Tien Huynh

Homayoon S M Beigi

Benoit Emmanuel Ghislain Maison

Yedid Hoshen

Nikhil Prasad Bhat

Craig Velliquette

Tanveer Atzal Faruquie

Ying Li Tian

Linda C Owen

Christopher A LoGiudice

Barry Gottlieb

Sharatchandra Pankanti

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using neural networks. A feature vector that models audio characteristics of a portion of an utterance is received. Data indicative of latent variables of multivariate factor analysis is received. The feature vector and the data indicative of the latent variables is provided as input to a neural network. A candidate transcription for the utterance is determined based on at least an output of the neural network.

Speech recognition using neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining, by a first sequence-training speech model, a first batch of training frames that represent speech features of first training utterances; obtaining, by the first sequence-training speech model, one or more first neural network parameters; determining, by the first sequence-training speech model, one or more optimized first neural network parameters based on (i) the first batch of training frames and (ii) the one or more first neural network parameters; obtaining, by a second sequence-training speech model, a second batch of training frames that represent speech features of second training utterances; obtaining one or more second neural network parameters; and determining, by the second sequence-training speech model, one or more optimized second neural network parameters based on (i) the second batch of training frames and (ii) the one or more second neural network parameters.

Asynchronous optimization for sequence training of neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media for acoustic modeling of audio data. One method includes receiving audio data representing a portion of an utterance, providing the audio data to a trained recurrent neural network that has been trained to indicate the occurrence of a phone at any of multiple time frames within a maximum delay of receiving audio data corresponding to the phone, receiving, within the predetermined maximum delay of providing the audio data to the trained recurrent neural network, output of the trained neural network indicating a phone corresponding to the provided audio data using output of the trained neural network to determine a transcription for the utterance, and providing the transcription for the utterance.

Setting latency constraints for acoustic models

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training acoustic models and using the trained acoustic models. A connectionist temporal classification (CTC) acoustic model is accessed, the CTC acoustic model having been trained using a context-dependent state inventory generated from approximate phonetic alignments determined by another CTC acoustic model trained without fixed alignment targets. Audio data for a portion of an utterance is received. Input data corresponding to the received audio data is provided to the accessed CTC acoustic model. Data indicating a transcription for the utterance is generated based on output that the accessed CTC acoustic model produced in response to the input data. The data indicating the transcription is provided as output of an automated speech recognition service.

Training acoustic models using connectionist temporal classification

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representation of acoustic sequences. One of the methods includes: receiving an acoustic sequence, the acoustic sequence comprising a respective acoustic feature representation at each of a plurality of time steps; processing the acoustic feature representation at an initial time step using an acoustic modeling neural network; for each subsequent time step of the plurality of time steps: receiving an output generated by the acoustic modeling neural network for a preceding time step, generating a modified input from the output generated by the acoustic modeling neural network for the preceding time step and the acoustic representation for the time step, and processing the modified input using the acoustic modeling neural network to generate an output for the time step; and generating a phoneme representation for the utterance from the outputs for each of the time steps.

Generating representations of acoustic sequences

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

Growing community of inventors

New York, NY, United States of America

Andrew William Senior