Patent · US Active

Methods and apparatus for speech segmentation using multiple metadata

US10229686B2 · kind B2 · utility

1Cited by

4References

21Claims

0Family size

Assignee

Nuance Communications, Inc. · US

Inventors

Markus Buck · Biberach, DE
Tobias Herbig · Ulm, DE
Simon Graf · Ulm, DE
Christophe Ris · Tournai, BE

Key dates

Filing date	Aug 18, 2014
Grant date	Mar 12, 2019
Priority date	—
Expiry date	Aug 23, 2034

Classification

Technology area (CPC G)Physics
CPC primaryG10L21/02
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Methods and apparatus to process microphone signals by a speech enhancement module to generate an audio stream signal including first and second metadata for use by a speech recognition module. In an embodiment, speech recognition is performed using endpointing information including transitioning from a silence state to a maybe speech state, in which data is buffered, based on the first metadata and transitioning to a speech state, in which speech recognition is performed, based upon the second metadata.

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