This paper presents a novel approach to language model adaptation for speech recognition. We define mutual information histograms which account for different semantic and syntactic relations between words in text data. We introduce a novel word distance measure which is based on mutual information histograms. By using this measure we were able to create linguistically meaningful word clusters composed of words obtained in first-pass speech recognition. Words included in the clusters were used to adapt language models. Adapted language models were used for a second pass of speech recognition. We conducted experiments on the Fisher speech corpus of telephone conversations. Mutual information histograms for word pairs were estimated from the Fisher data as well as from data extracted from a corpus of New York Times articles. Results showed that word clusters conveyed significant information and could be helpful in improving speech recognition accuracy.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Boosting of Speech Recognition Performance by Language Model Adaptation


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    01.03.2007


    Format / Umfang :

    272242 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Speech Recognition for Japanese Spoken Language

    Furui, S. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994


    Language Processing for Chinese Speech Recognition

    Huang, T. / Jiang, Y. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994



    Air traffic control speech recognition system cross-task & speaker adaptation

    de Cordoba, R. / Ferreiros, J. / San-Segundo, R. et al. | IEEE | 2006


    Speaker Adaptation Through Spectral Transformation for HMM Based Speech Recognition

    Choi, H. C. / King, R. W. / IEEE; Hong Kong Chapter of Signal Processing | British Library Conference Proceedings | 1994