Hybrid model decomposition of speech and noise in a radial basis function neural model framework

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

314 Downloads (Pure)

Abstract

The aim of the paper is to focus on a new approach to automatic speech recognition in noisy environments where the noise has either stationary or non-stationary statistical characteristics. The aim is to perform automatic recognition of speech in the presence of additive car noise. The technique applied is based on a combination of the hidden Markov model (HMM) decomposition method, for speech recognition in noise, developed by Varga and Moore (1990) from DRA and the hybrid (HMM/RBF) recognizer containing hidden Markov models and radial basis function (RBF) neural networks, developed by Singer and Lippmann (1992) from MIT Lincoln Lab. The present authors modified the hybrid recognizer to fit into the decomposition method to achieve high performance speech recognition in noisy environments. The approach has been denoted the hybrid model decomposition method and it provides an optimal method for decomposition of speech and noise by using a set of speech pattern models and a noise model(s), each realized as an HMM/RBF pattern model
Original languageEnglish
Title of host publicationProceedings og the IEEE International Conference on Acoustics, Speech, and Signal Processing
VolumeVolume 2
PublisherIEEE
Publication date1994
Pages657-660
ISBN (Print)07-80-31775-0
DOIs
Publication statusPublished - 1994
EventIEEE International Conference on Acoustics, Speech, and Signal Processing 1994 - Adelaide, SA, Australia
Duration: 19 Apr 199422 Apr 1994
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3104

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing 1994
CountryAustralia
CityAdelaide, SA
Period19/04/199422/04/1994
Internet address

Bibliographical note

Copyright: 1994 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

Fingerprint Dive into the research topics of 'Hybrid model decomposition of speech and noise in a radial basis function neural model framework'. Together they form a unique fingerprint.

Cite this