A new Dynamic Synapse Neural Network for speech recognition

被引：14
|
作者：
Namarvar, HH [1 ]
Liaw, JS [1 ]
Berger, TW [1 ]
机构：
[1] Univ So Calif, Dept Biomed Engn, Los Angeles, CA 90089 USA
来源：
IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS | 2001年
关键词：
Dynamic Synapses Neural Network; speech recognition; wavelet; Genetic Algorithm;
D O I：
10.1109/IJCNN.2001.938853
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A new version of Dynamic Synapses Neural Network (DSNN) has been applied to recognize noisy raw waveforms of words spoken by multiple speakers. The new architecture of DSNN is based on the original DSNN and a wavelet fitter bank, which decomposes speech signals in multi-resolution frequency bands. In this study we have applied a Genetic Algorithm (GA) learning method to optimize the neural network. The advantage of the GA method is that it facilitates finding of a semi-optimal parameter set in the search space domain. In order to speed training time of the network, a new discrete time implementation of the DSNN has been introduced bused on the impulse invariant transformation, The network has been tested for difficult discrimination conditions.
引用
收藏
页码：2985 / 2990
页数：6
相关论文
共 50 条
  • [1] A new approach for isolated word recognition using dynamic synapse neural networks
    Dibazar, AA
    Namarvar, HH
    Berger, TW
    [J]. PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS 2003, VOLS 1-4, 2003, : 3146 - 3150
  • [2] Nonlinear Model for Dynamic Synapse Neural Network
    Park, Hyung O.
    Dibazar, Alireza A.
    Berger, Theodore W.
    [J]. 2012 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2012, : 5441 - 5444
  • [3] Artificial neural network with dynamic synapse model
    Zimin, I. A.
    Kazantsev, V. B.
    Stasenko, S., V
    [J]. IZVESTIYA VYSSHIKH UCHEBNYKH ZAVEDENIY-PRIKLADNAYA NELINEYNAYA DINAMIKA, 2024, 32 (04): : 460 - 471
  • [4] DYNAMIC NEURAL NETWORKS FOR SPEECH RECOGNITION
    OLAFSSON, S
    [J]. BT TECHNOLOGY JOURNAL, 1992, 10 (03): : 48 - 58
  • [5] Quantum neural network in speech recognition
    Fei, L
    Zhao, SM
    Zheng, BY
    [J]. 2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 1267 - 1270
  • [6] A New Bidirectional Neural Network for Lexical Modeling and Speech Recognition Improvement
    Yazdchi, M. R.
    Salehi, S. A. Seyyed
    Zafarani, R.
    [J]. SCIENTIA IRANICA, 2007, 14 (06) : 571 - 578
  • [7] The application of dynamic synapse neural networks on footstep and vehicle recognition
    Dibazar, Alireza A.
    Park, Hyung O.
    Berger, Theodore W.
    [J]. 2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 1842 - +
  • [8] Speaker recognition using dynamic synapse-neural networks
    George, S
    Dibazar, A
    Berger, TW
    [J]. SECOND JOINT EMBS-BMES CONFERENCE 2002, VOLS 1-3, CONFERENCE PROCEEDINGS: BIOENGINEERING - INTEGRATIVE METHODOLOGIES, NEW TECHNOLOGIES, 2002, : 151 - 152
  • [9] Implementation of Convolutional Neural Network for Speech Recognition
    Wang, Zhichao
    Na, Xingyu
    Liu, Yong
    Pan, Jielin
    Yan, Yonghong
    [J]. INTERNATIONAL ACADEMIC CONFERENCE ON THE INFORMATION SCIENCE AND COMMUNICATION ENGINEERING (ISCE 2014), 2014, : 239 - 243
  • [10] Stimulated Deep Neural Network for Speech Recognition
    Wu, Chunyang
    Karanasou, Penny
    Gales, Mark J. F.
    Sim, Khe Chai
    [J]. 17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 400 - 404
12345