Speaker-Independent Vowel Recognition for Malay Children Using Time-Delay Neural Network

被引：0
|
作者：
Yong, B. F. [1 ]
Ting, H. N. [1 ]
机构：
[1] Univ Malaya, Fac Engn, Dept Biomed Engn, Kuala Lumpur 50603, Malaysia
来源：
5TH KUALA LUMPUR INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING 2011 (BIOMED 2011) | 2011年 / 35卷
关键词：
Malay Vowel Recognition; Time Delay Neural Network; Automatic Speech Recognition; Children Speech; SPEECH RECOGNITION; VARIABILITY;
D O I：
暂无
中图分类号：
R318 [生物医学工程];
学科分类号：
0831 ;
摘要：
This paper investigated the speaker independent vowel recognition for Malay children using the Time Delay Neural Network (TDNN). Due to less research done on the children speech recognition, the temporal structure of the children speech was not fully understood. This 2 hidden layers TDNN was proposed to discriminate 6 Malay vowels: /a/, /e/, /a/, /i/, /o/ and /u/. The speech database consisted of vowel sounds from 360 children speakers. Cepstral coefficient was normalized for the input of TDNN. The frame rate of the TDNN was tested with 10ms, 20ms, and 30ms. It was found out that the 30ms frame rate produced the highest vowel recognition accuracy with 81.92%. The TDNN also showed higher speech recognition rate compared to the previous studies that used Multi layer Perceptron.
引用
收藏
页码：565 / 568
页数：4
相关论文
共 50 条
  • [1] Speaker-Independent Malay Vowel Recognition of Children using Neural Networks
    Ting, H. N.
    Lam, Y. M.
    [J]. WORLD CONGRESS ON MEDICAL PHYSICS AND BIOMEDICAL ENGINEERING, VOL 25, PT 4: IMAGE PROCESSING, BIOSIGNAL PROCESSING, MODELLING AND SIMULATION, BIOMECHANICS, 2010, 25 : 288 - 291
  • [2] Speaker-independent Malay vowel recognition of children using multi-layer perceptron
    Ting, HN
    Yunus, D
    [J]. TENCON 2004 - 2004 IEEE REGION 10 CONFERENCE, VOLS A-D, PROCEEDINGS: ANALOG AND DIGITAL TECHNIQUES IN ELECTRICAL ENGINEERING, 2004, : A68 - A71
  • [3] Speaker-independent phonation recognition for Malay plosives using neural networks
    Ting, HN
    Yunus, J
    Salleh, SH
    [J]. PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 619 - 623
  • [4] Speaker-Independent Time Domain Vowel Recognition.
    Zuehlwetter, Juergen
    [J]. Elektrotechnik und Maschinenbau, 1979, 96 (01): : 13 - 15
  • [5] Short Utterance Speaker Recognition Using Time-Delay Neural Network
    Toruk, Muhammet Mesut
    Gokay, Ramazan
    [J]. 2019 16TH INTERNATIONAL MULTI-CONFERENCE ON SYSTEMS, SIGNALS & DEVICES (SSD), 2019, : 383 - 386
  • [6] Speaker-independent Malay isolated sounds recognition
    Ting, HN
    Yunus, J
    Wong, LC
    [J]. ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING: COMPUTATIONAL INTELLIGENCE FOR THE E-AGE, 2002, : 2405 - 2408
  • [7] SPEAKER-INDEPENDENT VOWEL RECOGNITION IN PERSIAN SPEECH
    Nazari, Mohammad
    Sayadiyan, Abolghasem
    Valiollahzadeh, Seyyed Majid
    [J]. 2008 3RD INTERNATIONAL CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES: FROM THEORY TO APPLICATIONS, VOLS 1-5, 2008, : 672 - 676
  • [8] SPEAKER-INDEPENDENT DIGIT RECOGNITION USING A NEURAL NETWORK WITH TIME-DELAYED CONNECTIONS
    UNNIKRISHNAN, KP
    HOPFIELD, JJ
    TANK, DW
    [J]. NEURAL COMPUTATION, 1992, 4 (01) : 108 - 119
  • [9] Speaker-independent vowel recognition combining voice features and mouth shape image with neural network
    [J]. Wu, Jian-Tong, 1600, (22):
  • [10] FLEXIBLE VOWEL RECOGNITION BY THE GENERATION OF DYNAMIC COHERENCE IN OSCILLATOR NEURAL NETWORKS - SPEAKER-INDEPENDENT VOWEL RECOGNITION
    LIU, F
    YAMAGUCHI, Y
    SHIMIZU, H
    [J]. BIOLOGICAL CYBERNETICS, 1994, 71 (02) : 105 - 114
12345