Shrinking Language Models by Robust Approximation

Shrinking Language Models by Robust Approximation (1998)

Cached

Download Links

[www.research.att.com]

by Adam L. Buchsbaum , Raffaele Giancarlo , Jeffery R. Westbrook

Venue:	in Proc. IEEE Int'l. Conf. on Acoustics, Speech, and Signal Processing '98
Citations:	1 - 1 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Shrinking Language Models by Robust Approximation	user correction - Legacy Corrections
AUTHOR NAME	Adam L. Buchsbaum	user correction - Legacy Corrections
AUTHOR AFFIL	y	user correction - Legacy Corrections
AUTHOR NAME	Raffaele Giancarlo	user correction - Legacy Corrections
AUTHOR AFFIL	y	user correction - Legacy Corrections
AUTHOR NAME	Jeffery R. Westbrook	user correction - Legacy Corrections
AUTHOR AFFIL	z	user correction - Legacy Corrections
ABSTRACT	We study the problem of reducing the size of a language model while preserving recognition performance (accuracy and speed). A successful approach has been to represent language models by weighted finite-state automata (WFAs). Analogues of classical automata determinization and minimization algorithms then provide a general method to produce smaller but equivalent WFAs. We extend this approach by introducing the notion of approximate determinization. We provide an algorithm that, when applied to language models for the North American Business task, achieves 25--35% size reduction compared to previous techniques, with negligible effects on recognition time and accuracy. 1. INTRODUCTION An important goal of language model engineering is to produce small language models that guarantee fast and accurate automatic speech recognition (ASR). In practice we see tradeoffs: e.g., in size vs. accuracy and in accuracy vs. speed. There has been recent progress, however, on automatic methods for r...	user correction - Legacy Corrections
YEAR	1998	INFERENCE
VENUE	in Proc. IEEE Int'l. Conf. on Acoustics, Speech, and Signal Processing '98	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	685--8	INFERENCE
VOLUME	2	INFERENCE
CITATIONS	9 found	ParsCit 1.0