Patent · US Expired

Method and apparatus for adapting the language model's size in a speech recognition system

US5899973A · kind A · utility

88Cited by

5References

18Claims

0Family size

Assignee

International Business Machines Corporation · US

Inventors

Upali Bandara · Leimen, DE
Siegfried Kunzmann · Heidelberg, DE
Karlheinz Mohr · Sinsheim, DE
Burn Lewis · Ossining, US

Key dates

Filing date	Sep 25, 1997
Grant date	May 4, 1999
Priority date	—
Expiry date	Sep 25, 2017

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/183
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

In this speech recognition system, the size of the language model is reduced by discarding those n-grams that the acoustic part of the system can recognize most accurately without support from a language model. The n-grams can be discarded dynamically during the running of the system or during the build or setup-time of the system. Trigrams occurring infrequently in the text corpora are substituted for the discarded n-grams to increase the accuracy of the word recognitions.

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