FREQUENCY-WEIGHTED ITAKURA SPECTRAL DISTORTION MEASURE AND ITS APPLICATION TO SPEECH RECOGNITION IN NOISE.

被引：0
|
作者：
Soong, Frank K. [1 ]
Sondhi, Man Mohan [1 ]
机构：
[1] AT&T Bell Lab, Murray Hill, NJ,, USA, AT&T Bell Lab, Murray Hill, NJ, USA
来源：
IEEE Transactions on Acoustics, Speech, and Signal Processing | 1988年 / 25卷 / 01期
关键词：
CONTROL SYSTEMS; ADAPTIVE - SIGNAL DISTORTION - Spectrum Analysis - SIGNAL FILTERING AND PREDICTION;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The authors propose an adaptively weighted Itakura distortion measure. They studied its effects on the performance of a conventional dynamic time-warping (DTW)-based speech recognizer in a series of speaker-independent, isolated-digit-recognition experiments. The equivalent SNR improvement achieved by using the proposed weighted Itakura distortion at low SNRs is about 5-7 dB.
引用
收藏
页码：41 / 48
相关论文
共 30 条
  • [1] A FREQUENCY-WEIGHTED ITAKURA SPECTRAL DISTORTION MEASURE AND ITS APPLICATION TO SPEECH RECOGNITION IN NOISE
    SOONG, FK
    SONDHI, MM
    [J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (01): : 41 - 48
  • [2] A MODIFIED FREQUENCY-WEIGHTED ITAKURA SPECTRAL DISTORTION MEASURE
    LI, J
    KRISHNAMURTHY, AK
    [J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1989, 37 (10): : 1614 - 1617
  • [3] Smoothed spectral subtraction for a frequency-weighted HMM in noisy speech recognition
    Matsumoto, H
    Naitoh, N
    [J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 905 - 908
  • [4] A FREQUENCY WEIGHTED ITAKURA-SAITO SPECTRAL DISTANCE MEASURE
    CHU, PL
    MESSERSCHMITT, DG
    [J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1982, 30 (04): : 545 - 560
  • [5] A FREQUENCY-WEIGHTED BLOCK LMS ALGORITHM AND ITS APPLICATION TO SPEECH PROCESSING
    LEE, JC
    UN, CK
    CHO, DH
    [J]. PROCEEDINGS OF THE IEEE, 1985, 73 (06) : 1137 - 1138
  • [6] A frequency-weighted HMM based on minimum error classification for noisy speech recognition
    Matsumoto, H
    Ono, M
    [J]. 1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 1511 - 1514
  • [7] Speech distortion weighted multi-channel Wiener filter and its application to speech recognition
    Kim, Gibak
    [J]. IEICE ELECTRONICS EXPRESS, 2015, 12 (06): : 1 - 7
  • [8] END-TO-END WHISPERED SPEECH RECOGNITION WITH FREQUENCY-WEIGHTED APPROACHES AND PSEUDO WHISPER PRE-TRAINING
    Chang, Heng-Jui
    Liu, Alexander H.
    Lee, Hung-yi
    Lee, Lin-shan
    [J]. 2021 IEEE SPOKEN LANGUAGE TECHNOLOGY WORKSHOP (SLT), 2021, : 186 - 193
  • [9] Performance Estimation of Noisy Speech Recognition Using Spectral Distortion and SNR of Noise-reduced Speech
    Ling, Guo
    Yamada, Takeshi
    Makino, Shoji
    Kitawaki, Nobuhiko
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE OF IEEE REGION 10 (TENCON), 2013,
  • [10] Sub-band weighted projection measure for sub-band speech recognition in noise
    Nasersharif, B.
    Akbari, A.
    [J]. ELECTRONICS LETTERS, 2006, 42 (14) : 829 - 831
123