Patent · US Active

Conversion of non-back-off language models for efficient speech decoding

US9484023B2 · kind B2 · utility

7Cited by

1References

18Claims

0Family size

Assignee

International Business Machines Corporation · US

Inventors

Ebru Arisoy · New York, US
Bhuvana Ramabhadran · Campion Road, US
Abhinav Sethy · Seattle, US
Stanley Chen · New York, US

Key dates

Filing date	Feb 22, 2013
Grant date	Nov 1, 2016
Priority date	—
Expiry date	Nov 18, 2033

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/197
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Techniques for conversion of non-back-off language models for use in speech decoders. For example, a method comprises the following step. A non-back-off language model is converted to a back-off language model. The converted back-off language model is pruned. The converted back-off language model is usable for decoding speech.

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