For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Bayesian Confidence Scoring and Adaptation Techniques for Speech Recognition
Tae-Yoon KIM Hanseok KO
IEICE TRANSACTIONS on Communications
Publication Date: 2005/04/01
Print ISSN: 0916-8516
Type of Manuscript: LETTER
Category: Multimedia Systems for Communications" Multimedia Systems for Communications
speech recognition, confidence measure, adaptation, OOV rejection,
Full Text: PDF(182.3KB)>>
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.