Presentation 2001/12/14
Unsupervised Adaptation of an Acoustic Model Using Confidence Measures Based on Phoneme Posterior Probabilities
Jun Ogata, Yasuo Ariki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we study on an accurate unsupervised adaptation method for spontaneous speech recognition. In unsupervised adaptation framework, the effectiveness of adaptation process is greatly affected by the mis-recognized labels. Therefore, selection of the adaptation data guided by the confidence measures is effective in unsupervised adaptation. We propose an phoneme error minimization framework for accurate phoneme-labels and use of phoneme-level confidence measures for improved unsupervised adaptation. Experimental results showed that the proposed method could reduce the mis-recognized labels in the adaptation process. and consequently improved the adaptation accuracy. Furthermore the selection of the adaptation data using the phoneme confidence measures improved the adaptation accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) unsupervised adaptation / confidence measures / word error minimization / phoneme error minimization
Paper # NLC2001-70,SP2001-105
Date of Issue

Conference Information
Committee SP
Conference Date 2001/12/14(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Unsupervised Adaptation of an Acoustic Model Using Confidence Measures Based on Phoneme Posterior Probabilities
Sub Title (in English)
Keyword(1) unsupervised adaptation
Keyword(2) confidence measures
Keyword(3) word error minimization
Keyword(4) phoneme error minimization
1st Author's Name Jun Ogata
1st Author's Affiliation Faculty of Science and Technology, Ryukoku University()
2nd Author's Name Yasuo Ariki
2nd Author's Affiliation Faculty of Science and Technology, Ryukoku University
Date 2001/12/14
Paper # NLC2001-70,SP2001-105
Volume (vol) vol.101
Number (no) 523
Page pp.pp.-
#Pages 6
Date of Issue