Abstract
Bayesian combining of confidence measures is proposed for speech recognition. Bayesian combining is achieved by the estimation of joint pdf of confidence feature vector in correct and incorrect hypothesis classes. In addition, the adaptation of a confidence score using the pdf is presented. The proposed methods reduced the classification error rate by 18% from the conventional single feature based confidence scoring method in isolated word Out-of-Vocabulary rejection test.
Original language | English |
---|---|
Pages (from-to) | 1756-1759 |
Number of pages | 4 |
Journal | IEICE Transactions on Communications |
Volume | E88-B |
Issue number | 4 |
DOIs | |
Publication status | Published - 2005 |
Keywords
- Adaptation
- Confidence measure
- OOV rejection
- Speech recognition
ASJC Scopus subject areas
- Software
- Computer Networks and Communications
- Electrical and Electronic Engineering