Binaural bark subband preprocessing of nonstationary signals for noise robust speech feature extraction

被引：0
|
作者：
Peters, M [1 ]
机构：
[1] BMW AG, Ctr Res & Dev, D-80788 Munich, Germany
来源：
PROCEEDINGS OF THE IEEE-SP INTERNATIONAL SYMPOSIUM ON TIME-FREQUENCY AND TIME-SCALE ANALYSIS | 1998年
关键词：
D O I：
10.1109/TFSA.1998.721498
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
A two channel approach to noise robust feature extraction for speech recognition in the car is proposed. The coherence function within the Bark subbands of the Mel-Frequency-Cepstral-Transform is calculated to estimate the spectral similarity of two statistic processes. It is illustrated how the coherence of speech in binaural signals is used to increase the robustness against incoherent noise. The introduced preprocessing method of nonstationary signals in two microphones results in an additive correction term of the Mel-Frequency-Cepstral-Coefficients.
引用
收藏
页码：609 / 612
页数：4
相关论文
共 50 条
  • [1] Binaural Bark subband preprocessing of nonstationary signals for noise robust speech feature extraction
    Peters, M
    ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, : 281 - 284
  • [2] A noise robust feature extraction algorithm using joint wavelet packet subband decomposition and AR modeling of speech signals
    Kotnik, Bojan
    Kacic, Zdravko
    SIGNAL PROCESSING, 2007, 87 (06) : 1202 - 1223
  • [3] Feature domain compensation of nonstationary noise for robust speech recognition
    Kim, NS
    SPEECH COMMUNICATION, 2002, 37 (3-4) : 231 - 248
  • [4] A binaural speech processing method using subband-crosscorrelation analysis for noise robust recognition
    Kajita, S
    Takeda, K
    Itakura, F
    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, 1997, : 1243 - 1246
  • [5] Robust speech feature extraction based on dynamic minimum subband spectral subtraction
    Ma, Xin
    Zhou, Weidong
    Ju, Fang
    INTELLIGENT COMPUTING IN SIGNAL PROCESSING AND PATTERN RECOGNITION, 2006, 345 : 1056 - 1061
  • [6] Feature extraction of speech signals of exoskeleton devices in noise environments
    Chen, Wen-Jie
    Su, Zhen-Xing
    Sun, Xian-Tao
    Liu, Yuan-Yuan
    Hu, Xiang-Tao
    Zhi, Ya-Li
    Jilin Daxue Xuebao (Gongxueban)/Journal of Jilin University (Engineering and Technology Edition), 2024, 54 (10): : 3050 - 3057
  • [7] Noise robust speech parameterization using multiresolution feature extraction
    Hariharan, R
    Kiss, I
    Viikki, O
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2001, 9 (08): : 856 - 865
  • [8] A feature extraction method using subband based periodicity and aperiodicity decomposition with noise robust frontend processing for automatic speech recognition
    Ishizuka, Kentaro
    Nakatani, Tomohiro
    SPEECH COMMUNICATION, 2006, 48 (11) : 1447 - 1457
  • [9] Binaural masking level difference for speech signals in noise
    Johansson, MSK
    Arlinger, SD
    INTERNATIONAL JOURNAL OF AUDIOLOGY, 2002, 41 (05) : 279 - 284
  • [10] Robust feature extraction of speech via noise reduction in autocorrelation domain
    Farahani, G.
    Ahadi, S. M.
    Homayounpour, M. M.
    MULTIMEDIA CONTENT REPRESENTATION, CLASSIFICATION AND SECURITY, 2006, 4105 : 466 - 473
12345