Please use this identifier to cite or link to this item: http://hdl.handle.net/1783.1/2325

Sub-phonetic polynomial segment model for large vocabulary continuous speech recognition

Authors Yeung, SKA
Li, CF
Siu, MH
Issue Date 2005
Source 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING , 2005, p. 193-196
Summary Polynomial Segment Model (PSM) has opened up an alternative research direction for acoustic modeling. In our previous papers [ 1, 2] we proposed efficient incremental likelihood evaluation and EM training algorithms for PSM, that significantly improve the speed of PSM training and recognition. In this paper, we shift our focus to use PSM on large vocabulary recognition. Recognition via N-best re-scoring shows that PSM models out-performed HMM on the 5k closed vocabulary Wall Street Journal Nov 92 testset. Our best PSM model achieved 7.15% WER compare with 7.81% using 16 mixture HMM model. Specifically, we used sub-phonetic PSM that represents a phoneme as multiple independent segmental units that allows for more effective model sharing. Also, we derived and compared different top-down mixture growing approaches that are orders of magnitude more efficient than previously proposed bottom-up agglomerative clustering techniques. Experimental results show that the top-down clustering performs better than the bottom-up approaches.
Subjects
ISSN 1520-6149
ISBN 0-7803-8874-7
Language English
Format Conference paper
Access View full-text via DOI
View full-text via Web of Science
View full-text via Scopus
Files in this item:
File Description Size Format
psmlvcsr.pdf 68768 B Adobe PDF