Patent · US Expired

Recognizing speech by selectively canceling model function mixture components

US6999929B2 · kind B2 · utility

0Cited by

4References

10Claims

0Family size

Assignee

Sony International (Europe) GmbH · DE

Inventors

Ralf Kompe · Schkölen, DE
Silke Goronzy · Erlangen, DE

Key dates

Filing date	Sep 5, 2001
Grant date	Feb 14, 2006
Priority date	—
Expiry date	Jul 17, 2023

Classification

Technology area (CPC G)Physics
CPC primaryG10L15/142
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method for recognizing speech is proposed wherein the process of recognition is started using the starting acoustic model (SAM) and wherein the current acoustic model (CAM) is modified by removing or cancelling model function mixture components (MFMjk) which are negligible for the description of the speaking behavior and quality of the current speaker. Therefore, the size of the acoustic model (SAM, CAM) is reduced by adaptation to the current speaker enabling fast performance and increased recognition efficiency.

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