Google Inc.

Mirkó Visontai

Tara N Sainath

Michiel A U Bacchiani

Samuel Bengio

Ehsan Variani

Izhak Shafran

Christopher Walter George Thornton

Yonghui Wu

Ruoming Pang

Rohit Prakash Prabhavalkar

Trevor D Strohman

Chung-Cheng Chiu

Yanzhang He

Wei Li

Ian C McGraw

Li Wei

Qiao Liang

David Rybach

Tara C Sainath

Ian C Mcgraw

Two-pass automatic speech recognition (ASR) models can be used to perform streaming on-device ASR to generate a text representation of an utterance captured in audio data. Various implementations include a first-pass portion of the ASR model used to generate streaming candidate recognition(s) of an utterance captured in audio data. For example, the first-pass portion can include a recurrent neural network transformer (RNN-T) decoder. Various implementations include a second-pass portion of the ASR model used to revise the streaming candidate recognition(s) of the utterance and generate a text representation of the utterance. For example, the second-pass portion can include a listen attend spell (LAS) decoder. Various implementations include a shared encoder shared between the RNN-T decoder and the LAS decoder.

Two-pass end to end speech recognition

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

Complex linear projection for acoustic modeling

Linear transformation for speech recognition modeling

Growing community of inventors

Mountain View, CA, United States of America

Mirkó Visontai