Discriminative training of self-structuring hidden control neural models

Helge Bjarup Dissing Sørensen, Uwe Hartmann, Preben Hunnerup

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

    423 Downloads (Pure)

    Abstract

    This paper presents a new training algorithm for self-structuring hidden control neural (SHC) models. The SHC models were trained non-discriminatively for speech recognition applications. Better recognition performance can generally be achieved, if discriminative training is applied instead. Thus we developed a discriminative training algorithm for SHC models, where each SHC model for a specific speech pattern is trained with utterances of the pattern to be recognized and with other utterances. The discriminative training of SHC neural models has been tested on the TIDIGITS database
    Original languageEnglish
    Title of host publicationProceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing
    VolumeVolume 5
    PublisherIEEE
    Publication date1995
    Pages3379-3382
    ISBN (Print)07-80-32431-5
    DOIs
    Publication statusPublished - 1995
    Event1995 IEEE International Conference on Acoustics, Speech, and Signal Processing - Detroit, United States
    Duration: 8 May 199512 May 1995
    Conference number: 20

    Conference

    Conference1995 IEEE International Conference on Acoustics, Speech, and Signal Processing
    Number20
    Country/TerritoryUnited States
    CityDetroit
    Period08/05/199512/05/1995

    Bibliographical note

    Copyright: 1995 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 'Discriminative training of self-structuring hidden control neural models'. Together they form a unique fingerprint.

    Cite this