INTERFRAME DEPENDENT HIDDEN MARKOV MODEL FOR SPEECH RECOGNITION

被引：2
|
作者：
MING, J
SMITH, FJ
机构：
[1] Computer Science Department, Queen's University
来源：
ELECTRONICS LETTERS | 1994年 / 30卷 / 03期
关键词：
SPEECH RECOGNITION; MODELING;
D O I：
10.1049/el:19940134
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
A hidden Markov model (HMM) with first-order dependent observation densities is presented to account for the statistical dependence between successive frames. A modified Viterbi algorithm is described to optimise jointly the state sequence and dependence relation for the model parameter estimation as well as likelihood calculation. Preliminary experiments show that this approach achieves better performance than the standard muitivariate Gaussian HMM.
引用
收藏
页码：188 / 189
页数：2
相关论文
共 50 条
  • [41] A Study on Hidden Markov Model's Generalization Capability for Speech Recognition
    Xiao, Xiong
    Li, Jinyu
    Chng, Eng Siong
    Li, Haizhou
    Lee, Chin-Hui
    2009 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION & UNDERSTANDING (ASRU 2009), 2009, : 118 - +
  • [42] The Application of Hidden Markov Models in Speech Recognition
    Gales, Mark
    Young, Steve
    FOUNDATIONS AND TRENDS IN SIGNAL PROCESSING, 2007, 1 (03): : 195 - 304
  • [43] Noisy Hidden Markov Models for Speech Recognition
    Audhkhasi, Kartik
    Osoba, Osonde
    Kosko, Bart
    2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2013,
  • [44] Hidden Markov models for speech and signal recognition
    Rose, RC
    Juang, BH
    CONTINUOUS WAVE-FORM ANALYSIS, 1996, (45): : 137 - 152
  • [45] HIDDEN MARKOV-MODELS FOR SPEECH RECOGNITION
    JUANG, BH
    RABINER, LR
    TECHNOMETRICS, 1991, 33 (03) : 251 - 272
  • [46] Time-Inhomogeneous Hidden Bernoulli Model: An alternative to Hidden Markov Model for automatic speech recognition
    Kabudian, Jahanshah
    Homayounpour, M. Mehdi
    Ahadi, S. Mohammad
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4101 - +
  • [47] Hidden Markov model training with contaminated speech material for distant-talking speech recognition
    Matassoni, M
    Omologo, M
    Giuliani, D
    Svaizer, P
    COMPUTER SPEECH AND LANGUAGE, 2002, 16 (02): : 205 - 223
  • [48] DEVELOPMENT OF AN ACOUSTIC-PHONETIC HIDDEN MARKOV MODEL FOR CONTINUOUS SPEECH RECOGNITION
    LJOLJE, A
    LEVINSON, SE
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, 1991, 39 (01) : 29 - 39
  • [49] A hidden Markov optimization model for processing and recognition of English speech feature signals
    Chen, Yinchun
    JOURNAL OF INTELLIGENT SYSTEMS, 2022, 31 (01) : 716 - 725
  • [50] Noise compensation methods for hidden Markov model speech recognition in adverse environments
    Vaseghi, SV
    Milner, BP
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1997, 5 (01): : 11 - 21
12345