Online directional speech enhancement using geometrically constrained independent vector analysis

被引:11
作者
Li, Li [1 ]
Koishida, Kazuhito [2 ]
Makino, Shoji [1 ]
机构
[1] Univ Tsukuba, Tsukuba, Ibaraki, Japan
[2] Microsoft Corp, Redmond, WA 98052 USA
来源
INTERSPEECH 2020 | 2020年
关键词
multichannel speech enhancement; geometric constraint; independent vector analysis (IVA); online; real-time; BLIND SOURCE SEPARATION; PERMUTATION PROBLEM; ICA;
D O I
10.21437/Interspeech.2020-1484
中图分类号
R36 [病理学]; R76 [耳鼻咽喉科学];
学科分类号
100104 ; 100213 ;
摘要
This paper proposes an online dual-microphone system for directional speech enhancement, which employs geometrically constrained independent vector analysis (IVA) based on the auxiliary function approach and vectorwise coordinate descent. Its offline version has recently been proposed and shown to outperform the conventional auxiliary function approach-based IVA (AuxIVA) thanks to the properly designed spatial constraints. We extend the offline algorithm to online by incorporating the autoregressive approximation of an auxiliary variable. Experimental evaluations revealed that the proposed online algorithm could work in real-time and achieved superior speech enhancement performance to online AuxIVA in both situations where a fixed target was interfered by a spatially stationary or dynamic interference.
引用
收藏
页码:61 / 65
页数:5
相关论文
共 50 条
  • [31] Electrocardiogram beat detection enhancement using Independent Component Analysis
    Kuzilek, Jakub
    Lhotska, Lenka
    MEDICAL ENGINEERING & PHYSICS, 2013, 35 (06) : 704 - 711
  • [32] Evaluation of Multichannel Speech Signal Separation using Independent Component Analysis
    Hussain, Abrar
    2016 IEEE STUDENTS' CONFERENCE ON ELECTRICAL, ELECTRONICS AND COMPUTER SCIENCE (SCEECS), 2016,
  • [33] An Acoustic Signal Enhancement Method Based on Independent Vector Analysis for Moving Target Classification in the Wild
    Zhao, Qin
    Guo, Feng
    Zu, Xingshui
    Chang, Yuchao
    Li, Baoqing
    Yuan, Xiaobing
    SENSORS, 2017, 17 (10)
  • [34] Texture Defect Detection using Independent Vector Analysis in Wavelet Domain
    Sari, Leda
    Ertuzun, Aysin
    2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 1639 - 1644
  • [35] Low-latency real-time independent vector analysis using convolutive transfer function
    Wang, Taihui
    Yang, Feiran
    Li, Nan
    Zhang, Chen
    Yang, Jun
    APPLIED ACOUSTICS, 2022, 197
  • [36] Probabilistic Formulation of Independent Vector Analysis Using Complex Gaussian Scale Mixtures
    Palmer, Jason A.
    Kreutz-Delgado, Ken
    Makeig, Scott
    INDEPENDENT COMPONENT ANALYSIS AND SIGNAL SEPARATION, PROCEEDINGS, 2009, 5441 : 90 - +
  • [37] AN ALTERNATIVE PROOF FOR THE IDENTIFIABILITY OF INDEPENDENT VECTOR ANALYSIS USING SECOND ORDER STATISTICS
    Lahat, Dana
    Jutten, Christian
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 4363 - 4367
  • [38] Content-based facial image retrieval using constrained independent component analysis
    Nguyen Duc Thang
    Rasheed, Tahir
    Lee, Young-Koo
    Lee, Sungyoung
    Kim, Tae-Seong
    INFORMATION SCIENCES, 2011, 181 (15) : 3162 - 3174
  • [39] Separation of Maternal and Fetal ECG Signals Using Improved Independent Vector Analysis
    Sugumar, D.
    Vanathi, P. T.
    JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, 2016, 6 (08) : 2048 - 2056
  • [40] Financial time series forecasting using independent component analysis and support vector regression
    Lu, Chi-Jie
    Lee, Tian-Shyug
    Chiu, Chih-Chou
    DECISION SUPPORT SYSTEMS, 2009, 47 (02) : 115 - 125