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
  • [41] Incorporating the voicing information into HMM-based automatic speech recognition
    Jancovic, Peter
    Koekueer, Muenevver
    2007 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, VOLS 1 AND 2, 2007, : 42 - 46
  • [42] COMPARISON OF PERFORMANCE BETWEEN NORMAL AND WHISPERED SPEECH IN CHINESE ISOLATED WORD RECOGNITION
    Sha, Jun
    Chen, Xueqin
    Yu, Yibiao
    2014 12TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP), 2014, : 545 - 548
  • [43] A Novel Visual Speech Representation and HMM Classification for Visual Speech Recognition
    Yu, Dahai
    Ghita, Ovidiu
    Sutherland, Alistair
    Whelan, Paul F.
    ADVANCES IN IMAGE AND VIDEO TECHNOLOGY, PROCEEDINGS, 2009, 5414 : 398 - 409
  • [44] English Language Speech Recognition using MFCC and HMM
    Naithani, Kanchan
    Thakkar, V. M.
    Semwal, Ashish
    2018 IEEE INTERNATIONAL CONFERENCE ON RESEARCH IN INTELLIGENT AND COMPUTING IN ENGINEERING (RICE III), 2018,
  • [45] Implementation of HMM and Radial Basis Function for Speech Recognition
    Umarani, S. D.
    Raviram, P.
    Wahidabanu, R. S. D.
    IAMA: 2009 INTERNATIONAL CONFERENCE ON INTELLIGENT AGENT & MULTI-AGENT SYSTEMS, 2009, : 344 - +
  • [46] Latent correlation analysis of HMM parameters for speech recognition
    Ou, Zhijian
    Luo, Jun
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 753 - +
  • [47] A Research on HMM based Speech Recognition in Spoken English
    Wang, Na
    Zhang, Xiaohong
    Sharma, Ashutosh
    RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING, 2021, 14 (06) : 617 - 626
  • [48] Simplified Scoring Methods in HMM Based Speech Recognition
    Paramonov, Pavel
    Sutula, Nadezhda
    2014 INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE ISCMI 2014, 2014, : 154 - 156
  • [49] Isolated word recognition in the Sigma cognitive architecture
    Joshi, Himanshu
    Rosenbloom, Paul S.
    Ustun, Volkan
    BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES, 2014, 10 : 1 - 9
  • [50] Multi-rate HMM quantization for speech recognition
    Vasilache, Marcel
    2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4341 - 4344
12345