Partly hidden Markov model and its application to speech recognition

被引：8
|
作者：
Kobayashi, T [1 ]
Furuyama, J [1 ]
Masumitsu, K [1 ]
机构：
[1] Waseda Univ, Dept EECE, Shijuku Ku, Tokyo 1698555, Japan
来源：
ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI | 1999年
关键词：
D O I：
10.1109/ICASSP.1999.758077
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
A new pattern matching method, Partly Hidden Markov Model, is proposed and applied to speech recognition. Hidden Markov Model, which is widely used for speech recognition, can deal with only piecewise stationary stochastic process. We solved this problem by introducing the modified second order Markov Model, in which the first state is hidden and the second one is observable. In this model, not only the feature parameter observations but also the state transitions are dependent on the previous feature observation. Therefore, even the complicated transient can be modeled precisely. Some simulational experiments showed the high potential of the proposed model. As the results of word recognition test, the error rate was reduced by 39% compared with normal HMM.
引用
收藏
页码：121 / 124
页数：4
相关论文
共 50 条
  • [31] Adaptation of hidden Markov model for telephone speech recognition and speaker adaptation
    Natl Tsing Hua Univ, Hsinchu, Taiwan
    IEE Proc Vision Image Signal Proc, 3 (129-135):
  • [32] Speech Recognition for English to Indonesian Translator Using Hidden Markov Model
    Muhammad, Hariz Zakka
    Nasrun, Muhammad
    Setianingsih, Casi
    Murti, Muhammad Ary
    2018 INTERNATIONAL CONFERENCE ON SIGNALS AND SYSTEMS (ICSIGSYS), 2018, : 255 - 260
  • [33] Visual Speech Recognition Using Optical Flow and Hidden Markov Model
    Sharma, Usha
    Maheshkar, Sushila
    Mishra, A. N.
    Kaushik, Rahul
    WIRELESS PERSONAL COMMUNICATIONS, 2019, 106 (04) : 2129 - 2147
  • [34] Visual Speech Recognition Using Optical Flow and Hidden Markov Model
    Usha Sharma
    Sushila Maheshkar
    A. N. Mishra
    Rahul Kaushik
    Wireless Personal Communications, 2019, 106 : 2129 - 2147
  • [35] Use of a novel generalized fuzzy hidden Markov model for speech recognition
    Cheok, AD
    Chevalier, S
    Kaynak, M
    Sengupta, K
    Chung, KC
    10TH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1-3: MEETING THE GRAND CHALLENGE: MACHINES THAT SERVE PEOPLE, 2001, : 1207 - 1210
  • [36] Visual speech recognition based on improved type of hidden Markov model
    Zhang, Zeliang
    Li, Xiongfei
    Yang, Chengjia
    Journal of Convergence Information Technology, 2012, 7 (13) : 119 - 126
  • [37] Tone recognition of Vietnamese continuous speech using hidden Markov model
    Quang, Nguyen Hong
    Pascal, Nocera
    Eric, Castelli
    Van Loan, Trinh
    2008 SECOND INTERNATIONAL CONFERENCE ON COMMUNICATIONS AND ELECTRONICS, 2008, : 233 - +
  • [38] Speech recognition using hybrid hidden Markov model and NN classifier
    Kundu, A.
    Bayya, A.
    International Journal of Speech Technology, 1998, 2 (03): : 227 - 240
  • [39] Speech recognition using hybrid hidden Markov model and NN classifier
    Kundu A.
    Bayya A.
    International Journal of Speech Technology, 1998, 2 (3) : 227 - 240
  • [40] Phoneme Modeling for Speech Recognition in Kannada Using Hidden Markov Model
    Kannadaguli, Prashanth
    Thalengala, Ananthakrishna
    2015 IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, INFORMATICS, COMMUNICATION AND ENERGY SYSTEMS (SPICES), 2015,
12345