Context dependent modelling of phones in continuous speech using decision trees

Context dependent modelling of phones in continuous speech using decision trees (1991)

by L. R. Bahl , P. V. De Souza , P. S. Gopalakrishnan , D. Nahamoo , M. A. Picheny

Venue:	In Proceedings DARPA Speech and Natural Language Processing Workshop
Citations:	24 - 1 self

Datum	Value	Source
TITLE	Context dependent modelling of phones in continuous speech using decision trees	INFERENCE
AUTHOR NAME	L. R. Bahl	SVM HeaderParse 0.2
AUTHOR NAME	P. V. De Souza	SVM HeaderParse 0.2
AUTHOR NAME	P. S. Gopalakrishnan	SVM HeaderParse 0.2
AUTHOR NAME	D. Nahamoo	SVM HeaderParse 0.2
AUTHOR NAME	M. A. Picheny	SVM HeaderParse 0.2
ABSTRACT	In a continuous speech recognition system it is impor-tant to model the context dependent variations in the pro-nunciations of words. In this paper we present an automatic method for modeling phonological variation using decision trees. For each phone we construct a decision tree that spec-ifies the acoustic realization of the phone as a function of the context in which it appears. Several thousand sentences from a natural language corpus spoken by several talkers are used to construct these decision trees. Experimental results on a 5000-word vocabulary natural language speech recog-nition task are presented.	SVM HeaderParse 0.2
YEAR	1991	INFERENCE
VENUE	In Proceedings DARPA Speech and Natural Language Processing Workshop	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	264--270	INFERENCE
CITATIONS	3 found	ParsCit 1.0