English  |  正體中文  |  简体中文  |  Items with full text/Total items : 54367/62174 (87%)
Visitors : 14182954      Online Users : 109
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTHU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    National Tsing Hua University Institutional Repository > 電機資訊學院 > 資訊工程學系 > 會議論文  >  Minimum Phone Error Discriminative Training For Mandarin Chinese Speaker Adaptation

    Please use this identifier to cite or link to this item: http://nthur.lib.nthu.edu.tw/dspace/handle/987654321/37564

    Title: Minimum Phone Error Discriminative Training For Mandarin Chinese Speaker Adaptation
    Authors: Liang-Yu Chen;Chun-Jen Lee;Jyh-Shing Roger Jang
    教師: 張智星
    Date: 2008
    Publisher: Interspeech 2008
    Relation: Proceedings of INTERSPEECH 2008, Brisbane, Australia, Sept. 2008.
    Keywords: Speaker adaptation
    speaker-independent model
    minimum phone error
    maximum likelihood
    Abstract: ©2008 Interspeech-Speaker adaptation is an efficient way to model a new speaker from an existing speaker-independent model with limited speaker-dependent data. In this paper, we investigate the use of discriminative training schemes based on the minimum phone error (MPE) criterion to improve a well-known speaker adaptation technique, a combination of transform-based adaptation and Bayesian adaptation. Furthermore, a new approach utilizing the statistics of the model-based regression tree for controlling the interpolation between maximum likelihood (ML) and MPE objective functions is also presented. Several comparative experiments were conducted on a continuous speech recognition task for Mandarin Chinese. Experimental results show that the proposed approach can further improve the performance of the original hybrid adaptation.
    URI: http://www.interspeech2008.org/
    Appears in Collections:[資訊工程學系] 會議論文

    Files in This Item:

    There are no files associated with this item.


    SFX Query


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback