Boosting HMMS with an application to speech recognition

被引：0
|
作者：
Dimitrakakis, C [1 ]
Bengio, S [1 ]
机构：
[1] IDIAP, CH-1920 Martigny, Switzerland
来源：
2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: DESIGN AND IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS INDUSTRY TECHNOLOGY TRACKS MACHINE LEARNING FOR SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING SIGNAL PROCESSING FOR EDUCATION | 2004年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Boosting is a general method for training an ensemble of classifiers with a view to improving performance relative to that of a single classifier. While the original AdaBoost algorithm has been defined for classification tasks, the current work examines its applicability to sequence learning problems, focusing on speech recognition. We apply boosting at the phoneme model level and recombine expert decisions using multi-stream techniques.
引用
收藏
页码：621 / 624
页数：4
相关论文
共 50 条
  • [11] Robust speech recognition using discrete-mixture HMMs
    Kosaka, T
    Katoh, M
    Kohda, M
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2005, E88D (12): : 2811 - 2818
  • [12] Robust speech recognition using factorial HMMs for home environments
    Betkowska, Agnieszka
    Shinoda, Koichi
    Furui, Sadaoki
    EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2007, 2007 (1)
  • [13] Landmark-based Approach to Speech Recognition: An Alternative to HMMs
    Espy-Wilson, Carol Y.
    Pruthi, Tarun
    Juneja, Amit
    Deshmukh, Om
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 2516 - +
  • [14] Robust Speech Recognition Using Factorial HMMs for Home Environments
    Agnieszka Betkowska
    Koichi Shinoda
    Sadaoki Furui
    EURASIP Journal on Advances in Signal Processing, 2007
  • [15] Boosted Mixture Learning of Gaussian Mixture HMMs for Speech Recognition
    Du, Jun
    Hu, Yu
    Jiang, Hui
    11TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2010 (INTERSPEECH 2010), VOLS 3 AND 4, 2010, : 2942 - +
  • [16] Lecture speech recognition using discrete-mixture HMMs
    Graduate School of Science and Engineering, Yamagata University, 4-3-16 Jonan, Yonezawa-shi, Yamagata 992-8510, Japan
    IEEJ Trans. Electr. Electron. Eng., 1 (23-29):
  • [17] Simultaneous Discriminative Training and Mixture Splitting of HMMs for Speech Recognition
    Tahir, Muhammad Ali
    Nussbaum-Thom, Markus
    Schlueter, Ralf
    Ney, Hermann
    13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 570 - 573
  • [18] In-ear microphone speech data recognition using HMMs
    Kurcan, R. S.
    Fargues, M. P.
    Vaidyanathan, R.
    2006 IEEE 12TH DIGITAL SIGNAL PROCESSING WORKSHOP & 4TH IEEE SIGNAL PROCESSING EDUCATION WORKSHOP, VOLS 1 AND 2, 2006, : 268 - 272
  • [19] Speech recognition in nonstationary noise based on parallel HMMs and spectral subtraction
    Mine, R
    Kobayashi, T
    Shirai, K
    SYSTEMS AND COMPUTERS IN JAPAN, 1996, 27 (14) : 37 - 44
  • [20] Connected phoneme HMMs with implicit duration modelling for better speech recognition
    Ramachandrula, S
    Thippur, S
    ICICS - PROCEEDINGS OF 1997 INTERNATIONAL CONFERENCE ON INFORMATION, COMMUNICATIONS AND SIGNAL PROCESSING, VOLS 1-3: THEME: TRENDS IN INFORMATION SYSTEMS ENGINEERING AND WIRELESS MULTIMEDIA COMMUNICATIONS, 1997, : 1024 - 1028
12345