A New Approach To Generalized Mixture Tying For Continuous HMM-Based Speech Recognition

A New Approach To Generalized Mixture Tying For Continuous HMM-Based Speech Recognition (1997)

Cached

Download Links

[www.fb9-ti.uni-duisburg.de]

by Daniel Willett , Gerhard Rigoll

Venue:	Proc. EUROSPEECH, Rhodes
Citations:	4 - 3 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	A New Approach To Generalized Mixture Tying For Continuous HMM-Based Speech Recognition	user correction - Legacy Corrections
AUTHOR NAME	Daniel Willett	SVM HeaderParse 0.1
AUTHOR AFFIL	Department of Computer Science; Faculty of Electrical Engineering	SVM HeaderParse 0.2
AUTHOR ADDR	Gerhard-Mercator-University Duisburg, Germany	SVM HeaderParse 0.1
AUTHOR NAME	Gerhard Rigoll	SVM HeaderParse 0.1
AUTHOR AFFIL	Department of Computer Science; Faculty of Electrical Engineering	SVM HeaderParse 0.2
AUTHOR ADDR	Gerhard-Mercator-University Duisburg, Germany	SVM HeaderParse 0.1
ABSTRACT	In this paper we present a new approach for a generalized tying of mixture components for continuous mixture-density HMM-based speech recognition systems. With an iterative pruning and splitting procedure for the mixture components, this approach offers a very accurate and detailed representation of the acoustic space and at the same time keeps the number of parameters reasonably small in favor of a robust parameter estimation and a fast decoding. Contrary to other approaches, it does not require a strict clustering of the pdfs into subsets that share their mixture components, so that it is capable of providing more general and flexible types of mixture tying. We applied the new approach on a semi-continuous HMM (SCHMM)-system for the Resource Management task and improved its recognition performance by 12% and vastly accelerated the decoding because of a much faster likelihood computation. 1. INTRODUCTION In continuous mixture-density HMM-based speech recognition systems the HMM stat...	user correction - Legacy Corrections
YEAR	1997	INFERENCE
VENUE	Proc. EUROSPEECH, Rhodes	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	1175--1178	INFERENCE
CITATIONS	7 found	ParsCit 1.0