Heuristic Improvements of the HMM Use in Isolated Word Speech Recognition

被引：0
作者：
Dimov, Dimo [1 ]
Azmanov, Ivan [1 ]
机构：
[1] Inst Informat Technol, Sofia 1113, Bulgaria
来源：
CYBERNETICS AND INFORMATION TECHNOLOGIES | 2007年 / 7卷 / 03期
关键词：
Speech recognition; HMM; Gaussian pdf; speech cepstrum;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The paper presents the authors' experience with HMMs (Hidden Markov Models) used for isolated word speech recognition in Bulgarian. Two methods provoked by experiments are discussed, namely: (i) the precise quantization of Gaussian probability density function (G-pdf) modeling the HMM states' output, and (ii) a method for averaging a set of HMMs trained for different versions of a given word. A universal threshold is evaluated for switching between the "large" and "slim" models of G-pdf defined here. Experimental results of the threshold usage for averaging of HMMs are also reported.
引用
收藏
页码：73 / 88
页数：16
相关论文
共 50 条
  • [21] Modified Viterbi Decoder for Hmm Based Speech Recognition System
    Kumar, Y. Rajeev
    Babu, A. Venkatesh
    Kumar, K. A. Naveen
    Alex, John Sahaya Rani
    2014 INTERNATIONAL CONFERENCE ON CONTROL, INSTRUMENTATION, COMMUNICATION AND COMPUTATIONAL TECHNOLOGIES (ICCICCT), 2014, : 470 - 474
  • [22] Design and Development of Speech Recognition System Based on HMM Algorithm
    Xu Zhengru
    PROCEEDINGS OF THE 2017 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND ENGINEERING (ICCSE 2017), 2017, 81 : 124 - 128
  • [23] On Speech Recognition Access Control System Based on HMM/ANN
    Li Bo
    Wang Dong-xia
    Zou De-jun
    Hu Tie-sen
    ICCSIT 2010 - 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND INFORMATION TECHNOLOGY, VOL 2, 2010, : 682 - 686
  • [24] A hybrid speech recognition model based on HMM and fuzzy PPM
    Bao, P
    Sim, A
    1998 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS, VOLS 1-5, 1998, : 4148 - 4153
  • [25] Dynamic segmental vector quantization in isolated-word speech recognition
    Nhat, VDM
    Lee, S
    PROCEEDINGS OF THE FOURTH IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, 2004, : 204 - 208
  • [26] Isolated word recognition of silent speech using magnetic implants and sensors
    Gilbert, J. M.
    Rybchenko, S. I.
    Hofe, R.
    Ell, S. R.
    Fagan, M. J.
    Moore, R. K.
    Green, P.
    MEDICAL ENGINEERING & PHYSICS, 2010, 32 (10) : 1189 - 1197
  • [27] Speech Recognition Approach Based on Speech Feature Clustering and HMM
    Li, XinGuang
    Yao, MinFeng
    Yang, JiaNeng
    JOURNAL OF COMPUTERS, 2012, 7 (09) : 2269 - 2275
  • [28] FUZZY SMOOTHING OF HMM PARAMETERS IN SPEECH RECOGNITION
    KOO, JM
    UN, CK
    ELECTRONICS LETTERS, 1990, 26 (11) : 743 - 744
  • [29] A method to combine HMM and BPNN on speech recognition
    Huang, Wan-Chen
    PROCEEDINGS OF 2007 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2007, : 1899 - 1902
  • [30] Research and Analysis of HMM Speech Recognition Model
    Zhu Shu-qin
    Wei Shao-qian
    Zhang Yin-xia
    2012 INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING (ICAISC 2012), 2012, 12 : 481 - 484
12345