A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction

G. Rigoll, D. Willett

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

This paper deals with a hybrid NN/HMM architecture for continuous speech recognition. We present a novel approach to set up a neural linear or nonlinear feature transformation that is used as a preprocessor on top of the HMM system's RBF-network to produce discriminative feature vectors that are well suited for being modeled by mixtures of Gaussian distributions. In order to omit the computational cost of discriminative training of a context-dependent system, we propose to train a discriminant neural feature transformation on a system of low complexity and reuse this transformation in the context-dependent system to output improved feature vectors. The resulting hybrid system is an extension of a state-of-the-art continuous HMM system, and in fact, it is the first hybrid system that really is capable of outperforming these standard systems with respect to the recognition accuracy, without the need for discriminative training of the entire system. In experiments carried out on the Resource Management 1000-word continuous speech recognition task we achieved a relative error reduction of about 10% with a recognition system that, even before, was among the best ever observed on this task.

Original languageEnglish
Title of host publicationProceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages9-12
Number of pages4
ISBN (Print)0780344286, 9780780344280
DOIs
StatePublished - 1998
Externally publishedYes
Event1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998 - Seattle, WA, United States
Duration: 12 May 199815 May 1998

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume1
ISSN (Print)1520-6149

Conference

Conference1998 23rd IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 1998
Country/TerritoryUnited States
CitySeattle, WA
Period12/05/9815/05/98

Fingerprint

Dive into the research topics of 'A NN/HMM hybrid for continuous speech recognition with a discriminant nonlinear feature extraction'. Together they form a unique fingerprint.

Cite this