A robust speech recognition system using FRM running spectrum filtering

被引：0
|
作者：
Hayasaka, N [1 ]
Wada, N [1 ]
Yoshizawa, S [1 ]
Miyanaga, Y [1 ]
机构：
[1] Hokkaido Univ, Grad Sch Engn, Sapporo, Hokkaido 0608628, Japan
来源：
ISCCSP : 2004 FIRST INTERNATIONAL SYMPOSIUM ON CONTROL, COMMUNICATIONS AND SIGNAL PROCESSING | 2004年
关键词：
FRM; robust; running spectra;
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：
This report introduces a new approach of FRM technique for a robust speech recognition system. We have already developed intelligent filtering techniques for robust speech recognition. In this method, a conventional FIR band-pass filter is applied on speech running power spectrum. In order to improve recognition accuracy, the designed FIR filter becomes considerably high order. Using a FRM filter, we can develop new robust speech recognition whose recognition ability is high enough and whose filtering order can be reduced low. Using this new FRM filter, some speech recognition experiments are shown in this report.
引用
收藏
页码：401 / 404
页数：4
相关论文
共 50 条
  • [1] Spectrum filtering with FRM for robust speech recognition
    Hayasaka, Noboru
    Miyanaga, Yoshikazu
    [J]. 2006 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOLS 1-11, PROCEEDINGS, 2006, : 3285 - +
  • [2] Noise-robust speech analysis using running spectrum filtering
    Zhu, Q
    Ohtsuki, N
    Miyanaga, Y
    Yoshida, N
    [J]. IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2005, E88A (02) : 541 - 548
  • [3] Robust speech analysis in noisy environment using running spectrum filtering
    Zhu, Q
    Ohtsuki, N
    Miyanaga, Y
    Yoshida, N
    [J]. IEEE INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS AND INFORMATION TECHNOLOGIES 2004 (ISCIT 2004), PROCEEDINGS, VOLS 1 AND 2: SMART INFO-MEDIA SYSTEMS, 2004, : 995 - 1000
  • [4] A study of robust speech recognition using FRM filter
    Hayasaka, N
    Miyanaga, Y
    [J]. TENCON 2004 - 2004 IEEE REGION 10 CONFERENCE, VOLS A-D, PROCEEDINGS: ANALOG AND DIGITAL TECHNIQUES IN ELECTRICAL ENGINEERING, 2004, : A80 - A83
  • [5] New robust speech recognition by using nonlinear running spectrum filter
    Hayasaka, Noboru
    Khankhavivone, Kham
    Miyanaga, Yoshikazu
    Songwatana, Kraisin
    [J]. 2006 INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS AND INFORMATION TECHNOLOGIES,VOLS 1-3, 2006, : 1001 - +
  • [6] Noise Robust Speech Features for Automatic Continuous Speech Recognition using Running Spectrum Analysis
    Ohnuki, Kazunaga
    Takahashi, Wataru
    Yoshizawa, Shingo
    Miyanaga, Yoshikazu
    [J]. 2008 INTERNATIONAL SYMPOSIUM ON COMMUNICATIONS AND INFORMATION TECHNOLOGIES, 2008, : 150 - 153
  • [7] Noise reduction of speech signals by running spectrum filtering
    Fujioka, Kazuma
    Hayasaka, Noboru
    Miyanaga, Yoshikazu
    Yoshida, Norinobu
    [J]. Systems and Computers in Japan, 2006, 37 (14): : 52 - 61
  • [8] Perceptual wavelet filtering for robust speech recognition
    Van Pham, Tuan
    Stark, Michael
    Kubin, Gernot
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-12, 2008, : 4385 - 4388
  • [9] Frequency and wavelet filtering for robust speech recognition
    Deviren, M
    Daoudi, K
    [J]. ARTIFICAIL NEURAL NETWORKS AND NEURAL INFORMATION PROCESSING - ICAN/ICONIP 2003, 2003, 2714 : 452 - 460
  • [10] Matched filtering approach to robust speech recognition
    Avadhanulu, J.V.
    Sreenivas, T.V.
    [J]. Journal of the Indian Institute of Science, 79 (03): : 185 - 196
12345