ICA-based speech features in the frequency domain

被引：0
|
作者：
Kasprzak, W [1 ]
Okazaki, AF [1 ]
Kowalski, AB [1 ]
机构：
[1] Warsaw Univ Technol, Inst Control & Computat Engn, PL-00665 Warsaw, Poland
来源：
INDEPENDENT COMPONENT ANALYSIS AND BLIND SIGNAL SEPARATION, PROCEEDINGS | 2006年 / 3889卷
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We apply the technique of independent component analysis to Fourier power coefficients of speech signal frames for a blind detection of basic vectors (sources). A subset of sources corresponding to the noisy influence of basic frequency is identified and its corresponding features could be eliminated. The mixing coefficients for such sources are then determined for every speech sample. We compare our features with the Mel Frequency Cepstrum Coefficient (MFCC) features, widely used today for phoneme-based speech recognition.
引用
收藏
页码：609 / 616
页数：8
相关论文
共 50 条
  • [1] Speech enhancement with MAP estimation and ICA-based speech features
    Lee, JH
    Jung, HY
    Lee, TW
    Lee, SY
    [J]. ELECTRONICS LETTERS, 2000, 36 (17) : 1506 - 1507
  • [2] ICA-BASED FEATURES FUSION FOR FACE RECOGNITION
    Wei, Xiaopeng
    Zhou, Changjun
    Zhang, Qiang
    [J]. INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2010, 6 (10): : 4651 - 4661
  • [3] ICA-based map algorithm for speech signal enhancement
    Zou, Xin
    Jancovic, Peter
    Liu, Ju
    Koekueer, Muenevver
    [J]. 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 569 - +
  • [4] ICA-based Noise Reduction Algorithm for Speech Recognition
    Xu, Yang
    Liu, Ting
    [J]. INTERNATIONAL CONFERENCE ON FRONTIERS OF ENERGY, ENVIRONMENTAL MATERIALS AND CIVIL ENGINEERING (FEEMCE 2013), 2013, : 779 - 784
  • [5] ICA-based hierarchical text classification for multi-domain text-to-speech synthesis
    Sevillano, X
    Alías, F
    Socoró, JC
    [J]. 2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL V, PROCEEDINGS: DESIGN AND IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS INDUSTRY TECHNOLOGY TRACKS MACHINE LEARNING FOR SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING SIGNAL PROCESSING FOR EDUCATION, 2004, : 697 - 700
  • [6] Speech feature enhancement based on frequency-domain ICA
    Lü, Zhao
    Wu, Xiao-Pei
    Li, Mi
    [J]. Zhendong yu Chongji/Journal of Vibration and Shock, 2011, 30 (02): : 238 - 242
  • [7] ICA-based noise reduction for mobile phone speech communication
    Zhang, Zhipeng
    Etoh, Minoru
    [J]. PROCEEDINGS - 16TH INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATIONS AND NETWORKS, VOLS 1-3, 2007, : 470 - 473
  • [8] ICA-based MAP speech enhancement with multiple variable speech distribution models
    Zou, Xin
    Jancovic, Peter
    Kokuer, Muenevver
    Russell, Martin
    [J]. INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 415 - 418
  • [9] ICA-based clustering for resolving permutation ambiguity in frequency-domain convolutive source separation
    Kim, Minje
    Choi, Seungjin
    [J]. 18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2006, : 950 - +
  • [10] ICA-BASED SPARSE FEATURES RECOVERY FROM FMRI DATASETS
    Varoquaux, Gael
    Keller, Merlin
    Poline, Jean-Baptiste
    Ciuciu, Philippe
    Thirion, Bertrand
    [J]. 2010 7TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO, 2010, : 1177 - 1180
12345