Confidence measures for spontaneous speech recognition

Author

Schaaf, Thomas ; Kemp, Thomas

Author_Institution

Interactive Syst. Labs., Karlsruhe Univ., Germany

Volume

2

fYear

1997

fDate

21-24 Apr 1997

Firstpage

875

Abstract

For many practical applications of speech recognition systems, it is desirable to have an estimate of confidence for each hypothesized word, i.e. to have an estimate of which words of the output of the speech recognizer are likely to be correct and which are not reliable. We describe the development of the measure of the confidence tagger JANKA, which is able to provide confidence information for the words at the output of the speech recognizer JANUS-3-SR. On a spontaneous German human-to-human database, JANKA achieves a tagging accuracy of 90% at a baseline word accuracy of 82%

Keywords

estimation theory; neural nets; pattern classification; speech recognition; JANKA; JANUS-3-SR; baseline word accuracy; confidence measures; confidence tagger; hypothesized word; spontaneous German human-to-human database; spontaneous speech recognition; tagging accuracy; Databases; Decoding; Error correction; Interactive systems; Laboratories; Maximum likelihood linear regression; Natural languages; Speech recognition; System testing; Tagging;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1997. ICASSP-97., 1997 IEEE International Conference on

Conference_Location

Munich

ISSN

1520-6149

Print_ISBN

0-8186-7919-0

Type

conf

DOI

10.1109/ICASSP.1997.596075

Filename

596075