Grapheme-to-phoneme Conversion in Theory and Practice

Peter Juel Henrichsen

    Research output: Contribution to conferenceConference abstract for conferenceResearchpeer-review

    Abstract

    Tools for mapping between written words and phonetic forms are essential components in many applications of speech technology, such as automatic speech recognition (ASR) and speech synthesis (TTS). Simple converters can be derived from annotated speech corpora using machine learning, and such tools are available for almost all European languages and a great number of others. Whereas their performance is adequate for ASR and for low-quality TTS, their lack of precision makes them unfit for linguistic research purposes such as phonetic annotation of spontaneous speech recordings. A common method of enhancing their predictive power (e.g. faced with out-of-vocabulary tokens) is to include phonetic and lexical rules, and sometimes even semantic and contextual knowledge. In this paper we present some of the principles underlying the typical linguistically informed phonetic converter. We illustrate our points with examples from the Danish grapheme-to-phoneme converter Phonix.
    Original languageEnglish
    Publication date2014
    Number of pages1
    Publication statusPublished - 2014
    Event2014 CRITT - WCRE Conference: Translation in Transition: Between Cognition, Computing and Technology - Copenhagen Business School, Frederiksberg, Denmark
    Duration: 30 Jan 201431 Jan 2014
    http://bridge.cbs.dk/platform/?q=conference2014

    Conference

    Conference2014 CRITT - WCRE Conference
    LocationCopenhagen Business School
    CountryDenmark
    CityFrederiksberg
    Period30/01/201431/01/2014
    Internet address

    Bibliographical note

    CBS Library does not have access to the material

    Cite this

    Juel Henrichsen, P. (2014). Grapheme-to-phoneme Conversion in Theory and Practice. Abstract from 2014 CRITT - WCRE Conference, Frederiksberg, Denmark.