LOG-SPECTRAL AMPLITUDE ESTIMATION WITH GENERALIZED GAMMA DISTRIBUTIONS FOR SPEECH ENHANCEMENT

被引：0
|
作者：
Borgstroem, Bengt J. [1 ]
Alwan, Abeer [1 ]
机构：
[1] Univ Calif Los Angeles, Dept Elect Engn, Los Angeles, CA 90024 USA
来源：
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING | 2011年
关键词：
Speech Enhancement; Log-spectral Amplitude Estimator; Generalized Gamma Distribution; SQUARE ERROR ESTIMATION;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper presents a family of log-spectral amplitude (LSA) estimators for speech enhancement. Generalized Gamma distributed (GGD) priors are assumed for speech short-time spectral amplitudes (STSAs), providing mathematical flexibility in capturing the statistical behavior of speech. Although solutions are not obtainable in closed-form, estimators are expressed as limits, and can be efficiently approximated. When applied to the Noizeus database [1], proposed estimators are shown to provide improvements in segmental signal-to-noise ratio (SSNR) and COSH distance [2], relative to the LSA estimator proposed by Ephraim and Malah [3].
引用
收藏
页码：4756 / 4759
页数：4
相关论文
共 50 条
  • [41] Noise Estimation Using a Constrained Sequential Hidden Markov Model in the Log-Spectral Domain
    Ying, Dongwen
    Yan, Yonghong
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2013, 21 (06): : 1145 - 1157
  • [42] Adaptive log-spectral regression for in-car speech recognition using multiple distributed microphones
    Li, WF
    Takeda, K
    Itakura, F
    IEEE SIGNAL PROCESSING LETTERS, 2005, 12 (04) : 340 - 343
  • [43] INTRODUCTION OF SPEECH LOG-SPECTRAL PRIORS INTO DEREVERBERATION BASED ON ITAKURA-SAITO DISTANCE MINIMIZATION
    Iwata, Yasuaki
    Nakatani, Tomohiro
    2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 245 - 248
  • [44] Speech enhancement based on β-order MMSE estimation of Short Time Spectral Amplitude and Laplacian speech modeling
    Abutalebi, Hamid Reza
    Rashidinejad, Mehdi
    SPEECH COMMUNICATION, 2015, 67 : 92 - 101
  • [45] Speech enhancement using MMSE short time spectral estimation with gamma distributed speech priors
    Martin, R
    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 253 - 256
  • [46] Music and Voice Separation Using Log-Spectral Amplitude Estimator Based on Kernel Spectrogram Models Backfitting
    Lee, Jun-Yong
    Kim, Hyoung-Gook
    JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2015, 34 (03): : 227 - 233
  • [47] Microphone Array Post-filter in Frequency Domain for Speech Recognition Using Short-Time Log-Spectral Amplitude Estimator and Spectral Harmonic/Noise Classifier
    Salishev, Sergey
    Klotchkov, Ilya
    Barabanov, Andrey
    SPEECH AND COMPUTER, SPECOM 2017, 2017, 10458 : 525 - 534
  • [48] Speech enhancement based on masking properties and short-time spectral amplitude estimation
    Chen, Guo-Ming
    Zhao, Li
    Zou, Cai-Rong
    Dianzi Yu Xinxi Xuebao/Journal of Electronics and Information Technology, 2007, 29 (04): : 863 - 866
  • [49] EVALUATION OF GENERALIZED MAXIMUM A POSTERIORI SPECTRAL AMPLITUDE (GMAPA) SPEECH ENHANCEMENT ALGORITHM IN HEARING AIDS
    Lai, Ying-Hui
    Su, Yu-Cheng
    Tsao, Yu
    Young, Shuenn-Tsong
    2013 IEEE 17TH INTERNATIONAL SYMPOSIUM ON CONSUMER ELECTRONICS (ISCE), 2013, : 245 - +
  • [50] Speech Enhancement By Minimum Mean-Square Error Spectral Amplitude Estimation Assuming Weibull Speech Priors
    Bahrami, Mojtaba
    Faraji, Neda
    2017 19TH CSI INTERNATIONAL SYMPOSIUM ON ARTIFICIAL INTELLIGENCE AND SIGNAL PROCESSING (AISP), 2017, : 190 - 194
12345