Lexicon Optimization for Dutch Speech Recognition in Spoken Document Retrieval

    Research output: Book/ReportReportOther research output

    5 Citations (Scopus)

    Abstract

    In this paper, ongoing work concerning the language modelling and lexicon optimization of a Dutch speech recognition system for Spoken Document Retrieval is described: the collection and normalization of a training data set and the optimization of our recognition lexicon. Effects on lexical coverage of the amount of training data, of decompounding compound words and of different selection methods for proper names and acronyms are discussed.
    Original languageEnglish
    Place of PublicationEnschede
    PublisherCentre for Telematics and Information Technology (CTIT)
    Publication statusPublished - Jun 2001

    Publication series

    NameCTIT technical report series
    PublisherCentre for Telematics and Information Technology, University of Twente
    ISSN (Print)1381-3625

    Fingerprint

    Dive into the research topics of 'Lexicon Optimization for Dutch Speech Recognition in Spoken Document Retrieval'. Together they form a unique fingerprint.

    Cite this