Language modeling structures in audio transcription for retrieval of historical speeches

M. Kurimo, B. Zhou, R. Huang, J.H.L. Hansen

    Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

    Abstrakti

    In this paper we apply speech recognition for automatic transcript generation for spoken document retrieval. The transcripts are used to compute an index for an archive of historical speeches and to provide the index, speech, and transcripts available for query based retrieval and browsing. In addition to acoustic variability, the task is challenging, because it covers a broad spectrum of different speaking styles and use of language. Language modeling is important for speech recognition to determine the prior probabilities of the compared word and sentence candidates in decoding. Various large text corpora are available in electronic format for language model training, but the open question is what and how should we include to improve the audio transcripts of this task. In this work we compare large overall language models to focused ones trained on selected subsets of the data, and to combinations between both. With respect to the potential index terms, improvements were obtained for transcripts that did not fit well to the scope of the large overall language model.

    AlkuperäiskieliEnglanti
    OtsikkoEuropean Signal Processing Conference, EUSIPCO 2004, Vienna, Austria, Sept. 6-10, 2004
    Sivut557-560
    Sivumäärä4
    Vuosikerta06-10-September-2004
    ISBN (elektroninen)9783200001657
    TilaJulkaistu - 3 huhtikuuta 2004
    OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
    TapahtumaEuropean Signal Processing Conference - Vienna, Itävalta
    Kesto: 6 syyskuuta 200410 syyskuuta 2004
    Konferenssinumero: 12

    Conference

    ConferenceEuropean Signal Processing Conference
    LyhennettäEUSIPCO
    MaaItävalta
    KaupunkiVienna
    Ajanjakso06/09/200410/09/2004

    Tutkimusalat

    • historical speeches
    • language modeling
    • speech recognition
    • speech retrieval

    Sormenjälki

    Sukella tutkimusaiheisiin 'Language modeling structures in audio transcription for retrieval of historical speeches'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

    Siteeraa tätä