Dynamic Programming Search Techniques For Across-Word Modelling In Speech Recognition

Dynamic Programming Search Techniques For Across-Word Modelling In Speech Recognition (1999)

Cached

Download Links

[www.informatik.rwth-aachen.de]

by Klaus Beulen , Stefan Ortmanns , Christian Elting

Venue:	in Speech Recognition, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing
Citations:	4 - 0 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Dynamic Programming Search Techniques For Across-Word Modelling In Speech Recognition	user correction - Legacy Corrections
AUTHOR NAME	Klaus Beulen	SVM HeaderParse 0.1
AUTHOR AFFIL	1	SVM HeaderParse 0.2
AUTHOR NAME	Stefan Ortmanns	SVM HeaderParse 0.1
AUTHOR AFFIL	2	SVM HeaderParse 0.2
AUTHOR NAME	Christian Elting	SVM HeaderParse 0.1
AUTHOR AFFIL	; 1; 1; Lehrstuhl fur Informatik VI, RWTH Aachen-- University of Technology; 2; Lucent Technologies-- Bell Labs., Murray Hill	SVM HeaderParse 0.2
AUTHOR ADDR	; 52056 Aachen, Germany; NJ 07974, USA	SVM HeaderParse 0.1
ABSTRACT	We describe the integration of across-word models in the RWTH large vocabulary continuous speech recognition system, where our main focus is on the realization of the acoustic recognition process. This paper presents a study of two search methods based on the priniciple of dynamic programming. For both methods we discuss the implementation details and give experimental results on the Verbmobil and on the Wall Street Journal data. In addition, we introduce a score interpolation of within-word and across-word models for both search methods. In combination with across-word models this interpolation technique gives an improvement of the recognition accuracy by 14% relative to our standard system. 1. INTRODUCTION This paper describes the integration of across-word modelling into the RWTH large vocabulary continuous speech recognition system [5]. In particular, we consider two search methods, namely the n-best and one-pass approach, for handling across-word models. Both methods are based o...	user correction - Legacy Corrections
YEAR	1999	INFERENCE
VENUE	in Speech Recognition, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	609--612	INFERENCE
CITATIONS	10 found	ParsCit 1.0