A method to combine HMM and BPNN on speech recognition

被引：0
|
作者：
Huang, Wan-Chen [1 ]
机构：
[1] Wu Feng Inst Technol, Dept Mech Engn, Chiayi, Taiwan
来源：
PROCEEDINGS OF 2007 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7 | 2007年
关键词：
HMM; BPNN; viterbi algorithm; recognition rate; HMNM;
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：
Applied the concept of phonic state in Hidden Markov Model to construct the input matrix in BP Neural Network as modeling and recognition, which can decrease their dimension (almost to 1/3 similar to 1/5) under the same recognition rate. On the one hand, it can save much of memory storage space; on the other hand, it would get more efficiency in calculation. In sum, it has good effects in the application need of real time response situation.
引用
收藏
页码：1899 / 1902
页数：4
相关论文
共 50 条
  • [11] On HMM speech recognition based on complex speech analysis
    Kinjo, Tatsuhiko
    Funaki, Keiichi
    IECON 2006 - 32ND ANNUAL CONFERENCE ON IEEE INDUSTRIAL ELECTRONICS, VOLS 1-11, 2006, : 2605 - +
  • [12] Adaptive HMM Topology for Speech Recognition
    Ting, Chuan-Wei
    Lee, Kuo-Yuan
    Chien, Jen-Tzung
    INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1237 - 1240
  • [13] Dynamic Hand Gesture Recognition Using HMM-BPNN Model
    Zhou Lu
    Zhang Li-Shuang
    Sun Le
    Zhang Xue-Bo
    2016 IEEE INTERNATIONAL CONFERENCE ON REAL-TIME COMPUTING AND ROBOTICS (IEEE RCAR), 2016, : 422 - 426
  • [14] Prediction method of speech recognition performance based on HMM-based speech synthesis technique
    Terashima R.
    Yoshimura T.
    Wakita T.
    Tokuda K.
    Kitamura T.
    IEEJ Transactions on Electronics, Information and Systems, 2010, 130 (04) : 557 - 564+3
  • [15] HMM-based integrated method for speaker-independent speech recognition
    Tsinghua Univ, Beijing, China
    Int Conf Signal Process Proc, (613-616):
  • [16] A HMM-based integrated method for speaker-independent speech recognition
    Zhang, YY
    Zhu, XY
    ICSP '98: 1998 FOURTH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, PROCEEDINGS, VOLS I AND II, 1998, : 613 - 616
  • [17] The hybrid ANN/HMM method with double MLP structure for continuous speech recognition
    Lee, TZ
    Chen, DW
    PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 1096 - 1098
  • [18] A new parameter smoothing method in the hybrid TDNN/HMM architecture for speech recognition
    Jang, CS
    Un, CK
    SPEECH COMMUNICATION, 1996, 19 (04) : 317 - 324
  • [19] New feedback method of hybrid HMM/ANN methods for continuous speech recognition
    Lee, TZ
    Chen, DW
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 509 - 512
  • [20] A novel HMM and wavelet neural network hybrid method for noisy speech recognition
    Lin, SF
    Pan, YX
    Guo, HJ
    ISTM/2005: 6TH INTERNATIONAL SYMPOSIUM ON TEST AND MEASUREMENT, VOLS 1-9, CONFERENCE PROCEEDINGS, 2005, : 1057 - 1060
12345