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

Helge Bjarup Dissing Sørensen, Uwe Hartmann

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

    481 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
    Event1994 IEEE International Conference on Acoustics, Speech, and Signal Processing - Adelaide, Australia
    Duration: 19 Apr 199422 Apr 1994
    Conference number: 19
    http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=3104

    Conference

    Conference1994 IEEE International Conference on Acoustics, Speech, and Signal Processing
    Number19
    Country/TerritoryAustralia
    CityAdelaide
    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