Google Inc.

Xin Wang

Tara N Sainath

Rohit Prakash Prabhavalkar

Trevor D Strohman

Qiao Liang

Rami Botros

Weiran Wang

Ian Mcgraw

Yangzhang He

Shaojin Ding

Ding Zhao

Dongseong Hwang

Robert David

Rina Panigrahy

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

Growing community of inventors

Mountain View, CA, United States of America

Xin Wang