Single Channel Blind Source Separation Based on NMF and Its Application to Speech Enhancement

被引：0
|
作者：
Chen, Yongqiang [1 ]
机构：
[1] Chengdu Univ Informat Technol, Coll Commun Engn, Chengdu, Sichuan, Peoples R China
来源：
2017 IEEE 9TH INTERNATIONAL CONFERENCE ON COMMUNICATION SOFTWARE AND NETWORKS (ICCSN) | 2017年
关键词：
single channel blind source separation; nonnegative matrix factorization; time correlation constraint; non-stationary noise; speech enhancement; ALGORITHMS;
D O I：
暂无
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
In this paper, an improved nonnegative matrix factorization (NMF) algorithm is proposed for single channel blind source separation and applied to speech enhancement. By adding time correlation item to objective function to constrain the time-varying gain coefficients of noise, it can achieve better effect of speech enhancement. We propose an efficient algorithm to optimize objective function with constraint item and effectively improve the estimation precision of the time-varying gain coefficients. Experiment results show that the proposed algorithm has more advantages compared with existing methods.
引用
收藏
页码：1066 / 1069
页数：4
相关论文
共 50 条
  • [1] Discriminative NMF and its application to single-channel source separation
    Weninger, Felix
    Le Roux, Jonathan
    Hershey, John R.
    Watanabe, Shinji
    15TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2014), VOLS 1-4, 2014, : 865 - 869
  • [2] Blind Speech Separation and Enhancement With GCC-NMF
    Wood, Sean U. N.
    Rouat, Jean
    Dupont, Stephane
    Pironkov, Gueorgui
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2017, 25 (04) : 745 - 755
  • [3] Single Channel Audio Source Separation by Clustered NMF
    Kirbiz, Serap
    Gunsel, Bilge
    2014 22ND SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2014, : 469 - 472
  • [4] A method for extracting fetal ECG based on EMD-NMF single channel blind source separation algorithm
    He, Pengju
    Chen, Xiaomeng
    TECHNOLOGY AND HEALTH CARE, 2016, 24 : S17 - S26
  • [5] A Two-step NMF Based Algorithm for Single Channel Speech Separation
    Wang, Shuo
    Wu, Wenjun
    13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 1987 - 1990
  • [6] Speech enhancement using blind source separation and two-channel energy based speaker detection
    Visser, E
    Lee, TW
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING I, 2003, : 884 - 887
  • [7] SINGLE-CHANNEL ENHANCEMENT OF CONVOLUTIVE NOISY SPEECH BASED ON A DISCRIMINATIVE NMF ALGORITHM
    Chung, Hanwook
    Plourde, Eric
    Champagne, Benoit
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 2302 - 2306
  • [8] The system of speech enhancement algorithm for blind source separation based on FastICA
    Zhang, Minsan
    PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON INFORMATION SCIENCES, MACHINERY, MATERIALS AND ENERGY (ICISMME 2015), 2015, 126 : 776 - 779
  • [9] Single-channel blind source separation of underwater acoustic signals using improved NMF and FastICA
    Li, Dawei
    Wu, Minghui
    Yu, Liang
    Han, Jianhui
    Zhang, Hao
    FRONTIERS IN MARINE SCIENCE, 2023, 9
  • [10] Blind Speech Separation with GCC-NMF
    Wood, Sean U. N.
    Rouat, Jean
    17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 3329 - 3333
12345