Hidden neural networks: application to speech recognition

Søren Kamaric Riis

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

    411 Downloads (Pure)

    Abstract

    We evaluate the hidden neural network HMM/NN hybrid on two speech recognition benchmark tasks; (1) task independent isolated word recognition on the Phonebook database, and (2) recognition of broad phoneme classes in continuous speech from the TIMIT database. It is shown how hidden neural networks (HNNs) with much fewer parameters than conventional HMMs and other hybrids can obtain comparable performance, and for the broad class task it is illustrated how the HNN can be applied as a purely transition based system, where acoustic context dependent transition probabilities are estimated by neural networks
    Original languageEnglish
    Title of host publicationAcoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
    Volume2
    PublisherIEEE
    Publication date1998
    Pages1117-1120
    ISBN (Print)0-7803-4428-6
    DOIs
    Publication statusPublished - 1998
    Event1998 IEEE International Conference on Acoustics, Speech and Signal Processing - Seattle, United States
    Duration: 12 May 199815 May 1998
    Conference number: 23

    Conference

    Conference1998 IEEE International Conference on Acoustics, Speech and Signal Processing
    Number23
    Country/TerritoryUnited States
    CitySeattle
    Period12/05/199815/05/1998

    Bibliographical note

    Copyright: 1998 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 'Hidden neural networks: application to speech recognition'. Together they form a unique fingerprint.

    Cite this