A One-Pass Decoder Based on Polymorphic Linguistic Context Assignment

A One-Pass Decoder Based on Polymorphic Linguistic Context Assignment (2001)

by Hagen Soltau , Florian Metze , Christian Fügen , Alex Waibel

Citations:

29 - 10 self

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	A One-Pass Decoder Based on Polymorphic Linguistic Context Assignment	user correction - Legacy Corrections
AUTHOR NAME	Hagen Soltau	user correction - Legacy Corrections
AUTHOR AFFIL	Systems Laboratories; University of Karlsruhe (Germany), Carnegie Mellon University (USA)	user correction - Legacy Corrections
AUTHOR NAME	Florian Metze	user correction - Legacy Corrections
AUTHOR AFFIL	Systems Laboratories; University of Karlsruhe (Germany), Carnegie Mellon University (USA)	user correction - Legacy Corrections
AUTHOR NAME	Christian Fügen	user correction - Legacy Corrections
AUTHOR NAME	Alex Waibel	user correction - Legacy Corrections
AUTHOR AFFIL	Systems Laboratories; University of Karlsruhe (Germany), Carnegie Mellon University (USA)	user correction - Legacy Corrections
ABSTRACT	In this study, we examine how fast decoding of conversational speech with large vocabularies pro ts from ecient use of linguistic information, i.e. language models and grammars. Based on a re-entrant single pronunciation pre x tree, we use the concept of linguistic context polymorphism to allow an early incorporation of language model information. This approach allows us to use all available language model information in a one-pass decoder, using the same engine to decode with statistical n-gram language models as well as context free grammars or re-scoring of lattices in an ecient way.	user correction - Legacy Corrections
YEAR	2001	user correction - Legacy Corrections
CITATIONS	12 found	ParsCit 1.0