Speech enhancement based on speech spectral complex Gaussian Mixture Model

被引：0
|
作者：
Ding, GH [1 ]
Wang, X [1 ]
Cao, Y [1 ]
Ding, F [1 ]
Tang, YZ [1 ]
机构：
[1] Nokia Res Ctr, Beijing, Peoples R China
来源：
2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING | 2005年
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：
This paper presents a speech enhancement approach based on speech spectral complex Gaussian Mixture Model (GMM). First, a construction algorithm of speech spectral GMM is introduced and it is based on the distance measure of speech spectral Gaussian probability. Then a noise estimation algorithm based on the GMM is proposed in the Maximum Likelihood criterion using the Expectation-Maximum (EM) algorithm. Speech enhancement experimental results show that the GMM-based MMSE estimators, especially the GMM-based MMSE short-time spectral estimator, can afford better performance than alternative speech enhancement algorithms and the proposed noise estimation algorithm can improve the enhancement performance more, especially at low SNRs.
引用
收藏
页码：165 / 168
页数：4
相关论文
共 50 条
  • [21] REGULARIZED NMF-BASED SPEECH ENHANCEMENT WITH SPECTRAL COMPONENTS MODELED BY GAUSSIAN MIXTURES
    Chung, Hanwook
    Plourde, Eric
    Champagne, Benoit
    2014 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2014,
  • [22] Speech separation based on Gaussian mixture model probability density function estimation
    Yu, Xiao
    Hu, Guangrui
    Shanghai Jiaotong Daxue Xuebao/Journal of Shanghai Jiaotong University, 2000, 34 (02): : 177 - 180
  • [23] Source microphone identification from speech recordings based on a Gaussian mixture model
    Eskidere, Omer
    TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2014, 22 (03) : 754 - 767
  • [24] Speech enhancement using a mixture-maximum model
    Burshtein, D
    Gannot, S
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2002, 10 (06): : 341 - 351
  • [25] Speech enhancement based on auditory spectral change
    Quatieri, TF
    Dunn, RB
    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 257 - 260
  • [26] Laplacian-Gaussian Mixture Based Dual-Gain Wiener Filter for Speech Enhancement
    Wei, Jing
    Ou, Shifeng
    Shen, Suojin
    Gao, Ying
    2016 IEEE INTERNATIONAL CONFERENCE ON SIGNAL AND IMAGE PROCESSING (ICSIP), 2016, : 543 - 547
  • [27] The subspace Gaussian mixture model-A structured model for speech recognition
    Povey, Daniel
    Burget, Lukas
    Agarwal, Mohit
    Akyazi, Pinar
    Kai, Feng
    Ghoshal, Arnab
    Glembek, Ondrej
    Goel, Nagendra
    Karafiat, Martin
    Rastrow, Ariya
    Rose, Richard C.
    Schwarz, Petr
    Thomas, Samuel
    COMPUTER SPEECH AND LANGUAGE, 2011, 25 (02): : 404 - 439
  • [28] Efficient Gaussian mixture for speech recognition
    Zouari, Leila
    Chollet, Gerard
    18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4, PROCEEDINGS, 2006, : 294 - +
  • [29] Automatic speaker verification from affective speech using Gaussian mixture model based estimation of neutral speech characteristics
    Avila, Anderson R.
    O'Shaughnessy, Douglas
    Falk, Tiago H.
    SPEECH COMMUNICATION, 2021, 132 : 21 - 31
  • [30] Speech enhancement based on a voiced-unvoiced speech model
    Goh, Z
    Tan, KC
    Tan, BTG
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 401 - 404
12345