Google Inc.

Ding Zhao

Tara N Sainath

Bo Li

Ruoming Pang

Rohit Prakash Prabhavalkar

Trevor D Strohman

David Rybach

Qiao Liang

Weiran Wang

Rami Botros

Yangzhang He

Ian Mcgraw

Zelin Wu

Shaojin Ding

Deepti Bhatia

Dongseong Hwang

Robert David

Rina Panigrahy

Xin Wang

An automated speech recognition (ASR) model includes a first encoder, a first encoder, a second encoder, and a second decoder. The first encoder receives, as input, a sequence of acoustic frames, and generates, at each of a plurality of output steps, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The first decoder receives, as input, the first higher order feature representation generated by the first encoder, and generates a first probability distribution over possible speech recognition hypotheses. The second encoder receives, as input, the first higher order feature representation generated by the first encoder, and generates a second higher order feature representation for a corresponding first higher order feature frame. The second decoder receives, as input, the second higher order feature representation generated by the second encoder, and generates a second probability distribution over possible speech recognition hypotheses.

Unified cascaded encoder ASR model for dynamic model sizes

A method includes receiving audio data encoding an utterance, processing, using a speech recognition model, the audio data to generate speech recognition scores for speech elements, and determining context scores for the speech elements based on context data indicating a context for the utterance. The method also includes executing, using the speech recognition scores and the context scores, a beam search decoding process to determine one or more candidate transcriptions for the utterance. The method also includes selecting a transcription for the utterance from the one or more candidate transcriptions.

Using context information with end-to-end models for speech recognition

Growing community of inventors

Mountain View, CA, United States of America

Ding Zhao