Comparison Of Part-Of-Speech And Automatically Derived Category-Based Language Models For Speech Recognition

Comparison Of Part-Of-Speech And Automatically Derived Category-Based Language Models For Speech Recognition (1998)

Cached

Download Links

[svr-www.eng.cam.ac.uk]

by T.R. Niesler , E. W. D. Whittaker , P.C. Woodland

Venue:	Proc. ICASSP’98
Citations:	28 - 6 self

Versions

Version History

Metadata Version 2

Datum	Value	Source
TITLE	Comparison of part-of-speech and automatically derived category-based language models for speech recognition	INFERENCE
AUTHOR NAME	T. R. Niesler	SVM HeaderParse 0.1
AUTHOR AFFIL	Cambridge University Engineering Department; Trumpington Street	SVM HeaderParse 0.2
AUTHOR ADDR	Cambridge, CB2 1PZ, England	SVM HeaderParse 0.1
AUTHOR NAME	E. W. D. Whittaker	SVM HeaderParse 0.1
AUTHOR AFFIL	Cambridge University Engineering Department; Trumpington Street	SVM HeaderParse 0.2
AUTHOR ADDR	Cambridge, CB2 1PZ, England	SVM HeaderParse 0.1
AUTHOR NAME	P. C. Woodl	SVM HeaderParse 0.1
AUTHOR AFFIL	Cambridge University Engineering Department; Trumpington Street	SVM HeaderParse 0.2
AUTHOR ADDR	Cambridge, CB2 1PZ, England	SVM HeaderParse 0.1
ABSTRACT	This paper compares various category-based language models when used in conjunction with a word-based trigram by means of linear interpolation. Categories corresponding to parts-of-speech as well as automatically clustered groupings are considered. The category-based model employs variable-length n-grams and permits each word to belong to multiple categories. Relative word error rate reductions of between 2 and 7 % over the baseline are achieved in N-best rescoring experiments on the Wall Street Journal corpus. The largest improvement is obtained with a model using automatically determined categories. Perplexities continue to decrease as the number of different categories is increased, but	SVM HeaderParse 0.1
YEAR	1998	INFERENCE
VENUE	Proc. ICASSP'98	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	177--180	INFERENCE
CITATIONS	14 found	ParsCit 1.0