Google Inc.

Shyam Upadhyay

Tara N Sainath

Bo Li

Trevor D Strohman

Shuo-Yiin Chang

Qiao Liang

Guru Prakash Arumugam

Manaal Faruqui

Zelin Wu

Adam Stambler

A method includes receiving, as input to a speech recognition model, audio data corresponding to a spoken utterance. The method also includes performing, using the speech recognition model, speech recognition on the audio data by, at each of a plurality of time steps, encoding, using an audio encoder, the audio data corresponding to the spoken utterance into a corresponding audio encoding, and decoding, using a speech recognition joint network, the corresponding audio encoding into a probability distribution over possible output labels. At each of the plurality of time steps, the method also includes determining, using an intended query (IQ) joint network configured to receive a label history representation associated with a sequence of non-blank symbols output by a final softmax layer, an intended query decision indicating whether or not the spoken utterance includes a query intended for a digital assistant.

Intended query detection using E2E modeling for continued conversation

Growing community of inventors

Mountain View, CA, United States of America

Shyam Upadhyay