Speech recognition and utterance verification based on a generalized confidence score.

In this paper, we introduce a generalized confidence score (GCS) function that enables a framework to integrate different confidence scores in speech recognition and utterance verification. A modified decoder based on the GCS is then proposed. The GCS is defined as a combination of various confidenc...

Description complète

Détails bibliographiques
Publié dans:	IEEE Transactions on speech and audio processing 9, 8 (2001).
Auteur principal:	Myoung-Wan Koo
Format:	Article
Langue:	English
Sujets:	GCS function. Confidence preprocessor. Exponential weighting. Extended hybrid decoder. Frame-level confidence scores. Frame-level likelihood ratio. Generalized confidence score. Ill-formed utterances. Multilevel information. Ordinary hybrid decoder. Out-of-vocabulary phrases. Phone-level confidence scores. Speech recognition. Utterance verification. Word-level confidence scores.