Language-Model Look-Ahead For Large Vocabulary Speech Recognition

Language-Model Look-Ahead For Large Vocabulary Speech Recognition (1996)

by S. Ortmanns , H. Ney , A. Eiden

Venue:	Proc. Int. Conf. on Spoken Language Processing
Citations:	22 - 9 self

Datum	Value	Source
TITLE	LANGUAGE-MODEL LOOK-AHEAD FOR LARGE VOCABULARY SPEECH RECOGNITION	SVM HeaderParse 0.1
AUTHOR NAME	S. Ortmanns	SVM HeaderParse 0.1
AUTHOR ADDR	D-52056 Aachen, Germany	SVM HeaderParse 0.1
AUTHOR NAME	H. Ney	SVM HeaderParse 0.1
AUTHOR ADDR	D-52056 Aachen, Germany	SVM HeaderParse 0.1
AUTHOR NAME	A. Eiden	SVM HeaderParse 0.1
AUTHOR ADDR	D-52056 Aachen, Germany	SVM HeaderParse 0.1
ABSTRACT	In this paper, we present an efficient look-ahead technique which incorporates the language model knowledge at the earliest possible stage during the search process. This so-called language model look-ahead is built into the time synchronous beam search algorithm using a tree-organized pronunciation lexicon for a bigram language model. The language model look-ahead technique exploits the full knowledge of the bigram language model by distributing the language model probabilities over the nodes of the lexical tree for each predecessor word. We present a method for handling the resulting memory requirements. The recognition experiments performed on the 20 000-word North American Business task (Nov.’96) demonstrate that in comparison with the unigram look-ahead a reduction by a factor of 5 in the acoustic search effort can be achieved without loss in recognition accuracy. 1.	SVM HeaderParse 0.1
CITATIONS	9 found	ParsCit 1.0