Patent · US Active

Using codec parameters for endpoint detection in speech recognition

US8762150B2 · kind B2 · utility

39Cited by

5References

47Claims

0Family size

Assignee

Nuance Communications, Inc. · US

Inventors

Michael D. Edgington · Bridgewater, US
Stephen W. Laverty · Somerville, US
Gunnar Evermann · Boston, US

Key dates

Filing date	Sep 16, 2010
Grant date	Jun 24, 2014
Priority date	—
Expiry date	Nov 18, 2032

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/30
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Systems, methods and apparatus for determining an estimated endpoint of human speech in a sound wave received by a mobile device having a speech encoder for encoding the sound wave to produce an encoded representation of the sound wave. The estimated endpoint may be determined by analyzing information available from the speech encoder, without analyzing the sound wave directly and without producing a decoded representation of the sound wave. The encoded representation of the sound wave may be transmitted to a remote server for speech recognition processing, along with an indication of the estimated endpoint.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.