Phoneme-based Thai speech recognition using fuzzy system and neural network

被引:0
|
作者
Cheirsilp, R [1 ]
Santiprabhob, P [1 ]
机构
[1] Assumption Univ, Fac Sci & Technol, Intelligent Syst Lab, Bangkok, Thailand
关键词
Thai speech recognition; fuzzy system; neural network and signal processing;
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
The Thai speech can be recognized by word or syllable. Most Thai speech recognition systems are word-based and syllable-based system. And most systems use several signal-processing functions in recognition process. These systems have a limit number of word and syllable that they can recognize. This research paper proposed the Thai speech recognition system that recognizes syllable by its phoneme representation using Fuzzy and Neural Network (NN) technique. The proposed system is designed to have desirable properties. 1. The proposed system is no! limited to the number of word or syllable. 2. The proposed system is general enough to be speaker-independent speech recognition system 3. The proposed system has small computation time to be able to be real-time system. 4. The proposed system has acceptable recognition error rate.
引用
收藏
页码:393 / 397
页数:5
相关论文
共 50 条
  • [1] Phoneme-based speech recognition via fuzzy neural networks modeling and learning
    Kasabov, NK
    Kozma, R
    Watts, MJ
    [J]. INFORMATION SCIENCES, 1998, 110 (1-2) : 61 - 79
  • [2] Improved Phoneme-Based Myoelectric Speech Recognition
    Zhou, Quan
    Jiang, Ning
    Englehart, Kevin
    Hudgins, Bernard
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2009, 56 (08) : 2016 - 2023
  • [3] Myoclectric signal classification for phoneme-based speech recognition
    Scheme, Erik J.
    Hudgins, Bernard
    Parker, Phillip A.
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2007, 54 (04) : 694 - 699
  • [4] CONTINUOUS SPEECH RECOGNITION USING A DEPENDENCY GRAMMAR AND PHONEME-BASED HMMS
    MATSUNAGA, S
    HOMMA, S
    SAGAYAMA, S
    FURUI, S
    [J]. IEICE TRANSACTIONS ON COMMUNICATIONS ELECTRONICS INFORMATION AND SYSTEMS, 1991, 74 (07): : 1826 - 1833
  • [5] A STOCHASTIC SEGMENT MODEL FOR PHONEME-BASED CONTINUOUS SPEECH RECOGNITION
    OSTENDORF, M
    ROUKOS, S
    [J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1989, 37 (12): : 1857 - 1869
  • [6] SYNTHESIS OF ARABIC SPEECH USING PHONEME-BASED SYNTHESIZERS
    MANDURAH, MM
    [J]. JOURNAL OF ENGINEERING SCIENCES, 1984, 10 (1-2): : 9 - 14
  • [7] Developing phoneme-based lip-reading sentences system for silent speech recognition
    El-Bialy, Randa
    Chen, Daqing
    Fenghour, Souheil
    Hussein, Walid
    Xiao, Perry
    Karam, Omar H.
    Li, Bo
    [J]. CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2023, 8 (01) : 129 - 138
  • [9] INTEGRATING TIME-DELAY NEURAL NETWORKS AND FUZZY HMM FOR PHONEME-BASED WORD RECOGNITION
    JANG, CS
    UN, CK
    [J]. ELECTRONICS LETTERS, 1992, 28 (25) : 2319 - 2320
  • [10] ADAPTABLE PHONEME-BASED MODELS FOR LARGE-VOCABULARY SPEECH RECOGNITION
    BAMBERG, PG
    MANDEL, MA
    [J]. SPEECH COMMUNICATION, 1991, 10 (5-6) : 437 - 451