Welcome to Journal of Beijing Institute of Technology
Advance Search
Volume 23Issue 4
.
Turn off MathJax
Article Contents
Article Navigation> JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY> 2014> 23(4): 549-556
XU Chun-dong, XIA Ri-sheng, YING Dong-wen, LI Jun-feng, YAN Yong-hong. HMM-based noise estimator for speech enhancement[J]. JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY, 2014, 23(4): 549-556.
Citation: XU Chun-dong, XIA Ri-sheng, YING Dong-wen, LI Jun-feng, YAN Yong-hong. HMM-based noise estimator for speech enhancement[J].JOURNAL OF BEIJING INSTITUTE OF TECHNOLOGY, 2014, 23(4): 549-556.
shu

HMM-based noise estimator for speech enhancement

  • 1.

    School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China;Faculty of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China;Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China

  • 2.

    Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China

  • Received Date:2014-01-16
    Abstract
  • A noise estimator was presented in this paper by modeling the log-power sequence with hidden Markov model (HMM). The smoothing factor of this estimator was motivated by the speech presence probability at each frequency band. This HMM had a speech state and a nonspeech state, and each state consisted of a unique Gaussian function. The mean of the nonspeech state was the estimation of the noise logarithmic power. To make this estimator run in an on-line manner, an HMM parameter updated method was used based on a first-order recursive process. The noise signal was tracked together with the HMM to be sequentially updated. For the sake of reliability, some constraints were introduced to the HMM. The proposed algorithm was compared with the conventional ones such as minimum statistics (MS) and improved minima controlled recursive averaging (IMCRA). The experimental results confirms its promising performance.
    • FullText(HTML)
  • loading
    • References (14)
  • [1]
    Zhang Xiaolei, Wu Ji. Deep belief networks based voice activity detection [J]. IEEE Transaction on Audio, Speech, and Language Processing, 2013, 21(4):697-710.
    [2]
    Zhong L, Goubran A, Dansereau M. Noise estimation using speech/non-speech frame decision and subband spectral tracking [J]. Speech Communication, 2007, 49(7-8):542-557.
    [3]
    Martin R. Noise power spectral density estimation based on optimal smoothing and minimum statistics [J]. IEEE Transaction on Audio, Speech, and Language Processing, 2001, 9(5): 504-512.
    [4]
    Cohen I, Berdugo B. Noise estimation by minima controlled recursive averaging for robust speech enhancement [J]. IEEE Signal Processing Letters, 2002, 9(1): 12-15
    [5]
    Cohen I. Noise spectrum estimation in adverse environments: improved minima controlled recursive averaging [J]. IEEE Transaction on Audio, Speech, and Language Processing, 2003, 11(5):466-475.
    [6]
    Ying D, Yan Y, Dang J, et al. Voice activity detection based on an unsupervised learning framework[J].IEEE Trans Audio, Speech, Lang Process, 2011, 19(8):2624-2633.
    [7]
    Ying D, Yan Y. Noise estimation using a constrained sequential hidden Markov model in the log-spectral domain[J]. IEEE Trans Audio, Speech, Lang Process, 2013, 21(6):1145-1157.
    [8]
    Zhang Xiaolei, Wu Ji. Linearithmic time sparse and convex maximum margin clustering [J]. IEEE Transaction on Systems, Man, and Cybernetics-Part B, 2012, part B, 42(6):1669-1692.
    [9]
    Benesty J, Sondhi M M, Huang Y. Handbook of speech processing [M]. Berlin, Germany: Springer Publishers,2008.
    [10]
    Krishnamurthy V, Moore J. On-line estimation of hidden Markov model parameters based on the Kullback-Leibler information measure [J]. IEEE Transaction on Signal Processing, 1993, 41(8):2557-2573.
    [11]
    Huo Q, Lee C. On-line adaptive learning of the continuous density hidden Markov model based on approximate recursive Bayes estimate [J]. IEEE Transaction on Audio, Speech, and Language Processing, 1997, 5(2): 161-172.
    [12]
    Jennrich R I, Robinson S M. A newton-raphson algorithm for maximum likelihood factor analysis[J]. Psychometrika, 1969, 34(1):111-123.
    [13]
    Xu Chundong, Xia Risheng, Ying Dongwen, et al. Time-frequency speech presence probability estimation based on constrained sequential hidden markov model for speech enhancement [J]. Acta Acustica, 2014, 39(5):647-654.
    [14]
    Augustine H G, Markel J. Diatance measures for speech processing[J]. IEEE Transaction on Audio, Speech, and Language Processing, 1976, 24(5):380-391.
    • Relative Articles
  • Supplements (0)
  • Cited By
  • 加载中

Catalog

    通讯作者:陈斌, bchen63@163.com
    • 1.

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索
    Get Citation
    PDF
    XML

    Article Metrics

    Article views (1040) PDF downloads(18) Cited by()
    Proportional views
    Related

    Address:5 Zhongguancun South Street, Haidian District, Beijing

    Tel:86-10-68914374

    Email:blgywb@bit.edu.cn

    Copy Right © Journal of Beijing Institute of Technology

    Supported by:Beijing Renhe Information Technology Co. Ltd

    /

      Return
      Return
        Baidu
        map