Google Inc.

Michiel Bacchiani

Rajeev Conrad Nongpiur

Chanwoo Kim

Vijayaditya Peddinti

Chan Woo Kim

Systems and methods are described for improving endpoint detection of a voice query submitted by a user. In some implementations, a synchronized video data and audio data is received. A sequence of frames of the video data that includes images corresponding to lip movement on a face is determined. The audio data is endpointed based on first audio data that corresponds to a first frame of the sequence of frames and second audio data that corresponds to a last frame of the sequence of frames. A transcription of the endpointed audio data is generated by an automated speech recognizer. The generated transcription is then provided for output.

Query endpointing based on lip detection

An example method includes receiving, by a computing system, an indication of one or more audible sounds that are detected by a first sensing device, the one or more audible sounds originating from a user; determining, by the computing system and based at least in part on an indication of one or more signals detected by a second sensing device, a distance between the user and the second sensing device; determining, by the computing system and based at least in part on the indication of the one or more audible sounds, one or more acoustic features that are associated with the one or more audible sounds; and determining, by the computing system, and based at least in part on the one or more acoustic features and the distance between the user and the second sensing device, one or more words that correspond to the audible sounds.

Growing community of inventors

Summit, NJ, United States of America

Michiel Bacchiani