Patent · US Expired

Semi-supervised speaker adaptation

US6799162B1 · kind B1 · utility

90Cited by

10References

30Claims

0Family size

Assignees

SONY GROUP CORPORATION · JP
Sony International (Europe) GmbH · DE

Inventors

Silke Goronzy · Erlangen, DE
Ralf Kompe · Schkölen, DE
Peter Buchner · Kirchheim unter Teck, DE
Naoto Iwahashi · Pitumarca, PE

Key dates

Filing date	Dec 15, 1999
Grant date	Sep 28, 2004
Priority date	—
Expiry date	Dec 15, 2019

Classification

Technology area (CPC G)Physics
CPC primaryG10L2015/0638
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

To prevent adaptation to misrecognized words in unsupervised or on-line automatic speech recognition systems confidence measures are used or the user reaction is interpreted to decide whether a recognized phoneme, several phonemes, a word, several words or a whole utterance should be used for adaptation of the speaker independent model set to a speaker adapted model set or not and, in case an adaptation is executed, how strong the adaptation with this recognized utterance or part of this recognized utterance should be performed. Furtheron, a verification of the speaker adaptation performance is proposed to secure that the recognition rate never decreases (significantly), but only increases or stays at the same level.

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