Speaker adaptation of language and prosodic models for automatic dialog act segmentation of speech
DOI: 10.1016/j.specom.2009.10.005
Title: Speaker adaptation of language and prosodic models for automatic dialog act segmentation of speech
Journal Title: Speech Communication
Volume: 52
Issue: 3
Publication Date: March 2010
Start Page: 236
End Page: 245
Published online: online 25 October 2009
ISSN: 0167-6393
Author: ;chym Kolá?a, Yang Liub, Elizabeth Shribergcd

  • a Department of Cybernetics, Faculty of Applied Sciences, University of West Bohemia, Pilsen, Czech Republic

  • b Department of Computer Science, University of Texas at Dallas, Richardson, TX, USA

  • c Speech Technology and Research Laboratory, SRI International, Menlo Park, CA, USA

  • d International Computer Science Institute, Berkeley, CA, USA
  • Abstract: Speaker-dependent modeling has a long history in speech recognition, but has received less attention in speech understanding. This study explores Speaker-specific modeling for the task of automatic segmentation of speech into dialog acts (DAs), using a linear combination of Speaker-dependent and Speaker-independent language and prosodic models. Data come from 20 frequent Speakers in the ICSI meeting corpus; adaptation data per Speaker ranges from 5 k to 115 k words. We compare performance for both reference transcripts and automatic speech recognition output. We find that: (1) Speaker adaptation in this domain results both in a significant overall improvement and in improvements for many individual Speakers, (2) the magnitude of improvement for individual Speakers does not depend on the amount of adaptation data, and (3) language and prosodic models differ both in degree of improvement, and in relative benefit for specific DA classes. These results suggest important future directions for Speaker-specific modeling in spoken language understanding tasks.
    Accepted: 20 October 2009
    Received: 14 July 2009
    Revised: 20 October 2009
    Tel: +420 377 63 2563
    Fax: +420 377 63 2502
    Email: jachym@kky.zcu.cz yangl@hlt.utdallas.edu ees@speech.sri.com

    Please Share this Paper with friends:
    Comment Content
    User Name
    Post new Comment
    Post to Facebook
    Search Full Text