A Combined Speaker Adaptation Method for Mandarin Speech Recognition

被引：0
|
作者：
徐向华
朱杰
机构：
[1] Shanghai Jiaotong Univ.
[2] Dept. of Electronic Eng.
[3] China
[4] Shanghai 200030
来源：
Journal of Shanghai Jiaotong University | 2004年 / 04期
关键词：
speech recognition; speaker adaptation; maximum a posteriori (MAP); maximum likelihood model interpolation (MLMI);
D O I：
暂无
中图分类号：
TN912.3 [语音信号处理];
学科分类号：
0711 ;
摘要：
A speaker adaptation method that combines transformation matrix linear interpolation with maximum a posteriori (MAP) was proposed. Firstly this method can keep the asymptotical characteristic of MAP. Secondly, as the method uses linear interpolation with several speaker-dependent (SD) transformation matrixes, it can fully use the prior knowledge and keep fast adaptation. The experimental results show that the combined method achieves an 8.24% word error rate reduction with only one adaptation utterance, and keeps asymptotic to the performance of SD model for large amounts of adaptation data.
引用
收藏
页码：21 / 24
页数：4
相关论文
共 50 条
  • [1] PREDICTIVE SPEAKER ADAPTATION IN SPEECH RECOGNITION
    COX, S
    COMPUTER SPEECH AND LANGUAGE, 1995, 9 (01): : 1 - 17
  • [2] An Undergraduate Mandarin Speech Database for Speaker Recognition Research
    Wang Hong
    Pan Jin'gui
    ORIENTAL COCOSDA 2009 - INTERNATIONAL CONFERENCE ON SPEECH DATABASE AND ASSESSMENTS, 2009, : 94 - +
  • [3] Speaker clustering and transformation for speaker adaptation in speech recognition systems
    Padmanabhan, M
    Bahl, LR
    Nahamoo, D
    Picheny, MA
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1998, 6 (01): : 71 - 77
  • [4] Rapid speaker adaptation for continuous speech recognition
    Lu, Ping
    Wu, Ji
    Wang, Zuoying
    Lu, Dajin
    Qinghua Daxue Xuebao/Journal of Tsinghua University, 2002, 42 (07): : 977 - 980
  • [5] SPEAKER ADAPTATION IN A LIMITED SPEECH RECOGNITION SYSTEM
    MAKHOUL, J
    IEEE TRANSACTIONS ON COMPUTERS, 1971, C 20 (09) : 1057 - &
  • [6] Quick fMLLR for speaker adaptation in speech recognition
    Varadarajan, Balakrishnan
    Povey, Daniel
    Chu, Stephen M.
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4297 - +
  • [7] Speaker Adaptation on Myanmar Spontaneous Speech Recognition
    Naing, Hay Mar Soe
    Pa, Win Pa
    COMPUTATIONAL LINGUISTICS, PACLING 2017, 2018, 781 : 303 - 313
  • [8] XMLLR for Improved Speaker Adaptation in Speech Recognition
    Povey, Daniel
    Kuo, Hong-Kwang J.
    INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1705 - +
  • [9] DOMAIN AND SPEAKER ADAPTATION FOR CORTANA SPEECH RECOGNITION
    Zhao, Yong
    Li, Jinyu
    Zhang, Shixiong
    Chen, Liping
    Gong, Yifan
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5984 - 5988
  • [10] Low-rank constraint eigenphone speaker adaptation method for speech recognition
    Zhang, W.-L. (zwlin_2004@163.com), 1600, Science Press (36):
12345