An on-line adaptive neural network for speech recognition

被引：0
|
作者：
Zhang L.-P. [1 ]
Li L.M. [2 ]
Chi Z. [1 ]
机构：
[1] Department of Electronic Engineering, Hong Kong Polytechnic University
[2] School of Business Administration, National University of Singapore
来源：
International Journal of Speech Technology | 1998年 / 2卷 / 3期
关键词：
Accumulative learning; Adaptive neural networks; Dynamic recognition neural network (DRNN); Hidden markov model; Speech recognition;
D O I：
10.1007/BF02111211
中图分类号：
学科分类号：
摘要：
In this paper, we present an on-line learning neural network model, Dynamic Recognition Neural Network (DRNN), for real-time speech recognition. The property of accumulative learning of the DRNN makes it very suitable for real-time speech recognition with on-line learning. A comparison between the DRNN and Hidden Markov Model (HMM) shows that the computational complexity of the former is lower than that of the latter in both training and recognition. Encouraging results are obtained when the DRNN is tested on a BUPT digit database (Mandarin) and on the on-line learning of twenty isolated English computer command words. © 1998 Kluwer Academic Publishers.
引用
收藏
页码：241 / 248
页数：7
相关论文
共 50 条
  • [21] On-Line Real Time Realization and Application of Adaptive Fuzzy Inference Neural Network
    Han Jianguo & Guo Junchao (Beijing University of Chemical Technology
    JournalofSystemsEngineeringandElectronics, 2000, (01) : 67 - 74
  • [22] Neural network approach to speech recognition
    Lee, Y.C.
    Chen, H.H.
    Sun, G.Z.
    Neural Networks, 1988, 1 (1 SUPPL)
  • [23] Quantum neural network in speech recognition
    Fei, L
    Zhao, SM
    Zheng, BY
    2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 1267 - 1270
  • [24] Method for adaptive on-line data fusion in multi-channel. automatic speech recognition systems
    Ivanov, R
    Momchedjikov, M
    2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 512 - 515
  • [25] Method for adaptive on-line data fusion in Multi-Channel automatic speech recognition systems
    Ivanov, R
    2002 FIRST INTERNATIONAL IEEE SYMPOSIUM INTELLIGENT SYSTEMS, VOL 1, PROCEEDINGS, 2002, : 350 - 353
  • [26] On-line model modification for adaptive object recognition
    Pachowicz, PW
    Baik, SW
    ECAI 2000: 14TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2000, 54 : 668 - 672
  • [27] DETECTING SPEECH WITH AN ADAPTIVE NEURAL NETWORK
    NEWMAN, WC
    ELECTRONIC DESIGN, 1990, 38 (06) : 79 - &
  • [28] A neural network for on-line tool monitoring
    Wang, YP
    Hung, SCC
    Shieh, CM
    Suen, DS
    CONDITION MONITORING '97, 1997, : 347 - 353
  • [29] Hidden Markov modeling in on-line dysarthric speech recognition
    Kostov, A
    Chen, FX
    Beliveau, C
    ADVANCEMENT OF ASSISTIVE TECHNOLOGY, 1997, 3 : 195 - 199
  • [30] Segmentation of on-line handwritten Japanese text of arbitrary line direction by a neural network for improving text recognition
    Zhu, BL
    Nakagawa, M
    EIGHTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS 1 AND 2, PROCEEDINGS, 2005, : 157 - 161
12345