Incremental Language Models For Speech Recognition Using Finite-State Transducers

Incremental Language Models For Speech Recognition Using Finite-State Transducers (2001)

by Hans J. G. A. Dolfing , I. Lee Hetherington

Venue:	in Proc. IEEE Automatic Speech Recogntion and Understanding Workshop, Madonna di Campiglio
Citations:	10 - 2 self

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Incremental Language Models For Speech Recognition Using Finite-State Transducers	user correction - Legacy Corrections
AUTHOR NAME	Hans J. G. A. Dolfing	user correction - Legacy Corrections
AUTHOR AFFIL	Philips Research Laboratories	user correction - Legacy Corrections
AUTHOR ADDR	Weißhausstrasse 2; D-52066 Aachen, Germany	user correction - Legacy Corrections
AUTHOR NAME	I. Lee Hetherington	user correction - Legacy Corrections
ABSTRACT	to speech recognition, we investigate a novel decoding strategy to deal with very large n-gram language models often used in large-vocabulary systems. In particular, we present an alternative to full, static expansion and optimization of the finite-state transducer network. This alternative is useful when the individual knowledge sources, modeled as transducers, are too large to be composed and optimized. While the recognition decoder perceives a single, weighted finitestate transducer, we apply a divide-and-conquer technique to split the language model into two parts which add up exactly to the original language model. We investigate the merits of these `incremental language models' and present some initial results.	user correction - Legacy Corrections
YEAR	2001	INFERENCE
VENUE	in Proc. IEEE Automatic Speech Recogntion and Understanding Workshop, Madonna di Campiglio	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	194--197	INFERENCE
CITATIONS	10 found	ParsCit 1.0