Time-frequency distributions for automatic speech recognition

被引：36
|
作者：
Potamianos, A [1 ]
Maragos, P [1 ]
机构：
[1] Georgia Inst Technol, Sch Elect & Comp Engn, Atlanta, GA 30332 USA
来源：
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING | 2001年 / 9卷 / 03期
基金：
美国国家科学基金会;
关键词：
speech analysis; speech processing; speech recognition; time-frequency analysis;
D O I：
10.1109/89.905994
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
The use of general time-frequency distributions as features for automatic speech recognition (ASR) is discussed in the context of hidden Markov classifiers. Short-time averages of quadratic operators, e.g., energy spectrum, generalized first spectral moments, and short-time averages of the instantaneous frequency, are compared to the standard front end features, and applied to ASR. Theoretical and experimental results indicate a close relationship among these feature sets.
引用
收藏
页码：196 / 200
页数：5
相关论文
共 50 条
  • [1] Time-frequency analysis and auditory modeling for automatic recognition of speech
    Pitton, JW
    Wang, KS
    Juang, BH
    PROCEEDINGS OF THE IEEE, 1996, 84 (09) : 1199 - 1215
  • [2] Weighting Time-Frequency Representation of Speech using Auditory Saliency for Automatic Speech Recognition
    Cong-Thanh Do
    Stylianou, Yannis
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1591 - 1595
  • [3] Optimizing time-frequency distributions for automatic classification
    Atlas, L
    Droppo, J
    McLaughlin, J
    ADVANCED SIGNAL PROCESSING: ALGORITHMS, ARCHITECTURES, AND IMPLEMENTATIONS VII, 1997, 3162 : 161 - 171
  • [4] Robust Automatic Speech Recognition System Based on Using Adaptive Time-Frequency Masking
    Gouda, Ahmed Mostafa
    Tamazin, Mohamed
    Khedr, Mohamed
    PROCEEDINGS OF 2016 11TH INTERNATIONAL CONFERENCE ON COMPUTER ENGINEERING & SYSTEMS (ICCES), 2016, : 181 - 186
  • [5] Applications of Positive Time-Frequency Distributions to Speech Processing
    Pitton, James W.
    Atlas, Les E.
    Loughlin, Patrick J.
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1994, 2 (04): : 554 - 566
  • [6] Automatic feature-finding for time-frequency distributions
    Owsley, L
    McLaughlin, J
    Bernard, G
    PROCEEDINGS OF THE IEEE-SP INTERNATIONAL SYMPOSIUM ON TIME-FREQUENCY AND TIME-SCALE ANALYSIS, 1996, : 333 - 336
  • [7] Speech recognition with localized time-frequency pattern detectors
    Schutte, Ken
    Glass, James
    2007 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, VOLS 1 AND 2, 2007, : 341 - 346
  • [8] TIME-FREQUENCY CONVOLUTIONAL NETWORKS FOR ROBUST SPEECH RECOGNITION
    Mitra, Vikramjit
    Franco, Horacio
    2015 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING (ASRU), 2015, : 317 - 323
  • [9] TIME-FREQUENCY REASSIGNED FEATURES FOR AUTOMATIC CHORD RECOGNITION
    Khadkevich, Maksim
    Omologo, Maurizio
    2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 181 - 184
  • [10] Time-frequency representation based cepstral processing for speech recognition
    Fineberg, AB
    Yu, KC
    1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, 1996, : 25 - 28
12345