Patent · US Active

System and method of using acoustic models for automatic speech recognition which distinguish pre- and post-vocalic consonants

US8015008B2 · kind B2 · utility

3Cited by

3References

18Claims

0Family size

Assignee

AT&T Intellectual Property I, L.P. · US

Inventors

Yeon-Jun Kim · Whippany, US
Alistair D. Conkie · San Jose, US
Andrej Ljolje · Bernardsville, US
Ann K. Syrdal · Morristown, US

Key dates

Filing date	Oct 31, 2007
Grant date	Sep 6, 2011
Priority date	—
Expiry date	Jun 17, 2030

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/02
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Disclosed are systems, methods and computer readable media for training acoustic models for an automatic speech recognition systems (ASR) system. The method includes receiving a speech signal, defining at least one syllable boundary position in the received speech signal, based on the at least one syllable boundary position, generating for each consonant in a consonant phoneme inventory a pre-vocalic position label and a post-vocalic position label to expand the consonant phoneme inventory, reformulating a lexicon to reflect an expanded consonant phoneme inventory, and training a language model for an automated speech recognition (ASR) system based on the reformulated lexicon.

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