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
  • [21] Subspace independent component analysis using vector kurtosis
    Sharma, Alok
    Paliwal, Kuldip K.
    PATTERN RECOGNITION, 2006, 39 (11) : 2227 - 2232
  • [22] Independent vector analysis using subband and subspace nonlinearity
    Na, Yueyue
    Yu, Jian
    Chai, Bianfang
    EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2013,
  • [23] Independent vector analysis using subband and subspace nonlinearity
    Yueyue Na
    Jian Yu
    Bianfang Chai
    EURASIP Journal on Advances in Signal Processing, 2013
  • [24] Hybrid Source Prior Based Independent Vector Analysis for Blind Separation of Speech Signals
    Khan, Junaid Bahadar
    Jan, Tariqullah
    Khalil, Ruhul Amin
    Altalbe, Ali
    IEEE ACCESS, 2020, 8 : 132871 - 132881
  • [25] Speech Enhancement by Noise Self-Supervised Rank-Constrained Spatial Covariance Matrix Estimation via Independent Deeply Learned Matrix Analysis
    Misawa, Sota
    Takamune, Norihiro
    Nakamura, Tomohiko
    Kitamura, Daichi
    Saruwatari, Hiroshi
    Une, Masakazu
    Makino, Shoji
    2021 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2021, : 578 - 584
  • [26] Inverse-free Online Independent Vector Analysis with Flexible Iterative Source Steering
    Nakashima, Taishi
    Ono, Nobutaka
    PROCEEDINGS OF 2022 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2022, : 749 - 753
  • [27] Isolation of multiple electrocardiogram artifacts using independent vector analysis
    Uddin, Zahoor
    Altaf, Muhammad
    Ahmad, Ayaz
    Qamar, Aamir
    Orakzai, Farooq Alam
    PEERJ COMPUTER SCIENCE, 2023, 9 : 1 - 23
  • [28] Extraction of P300 Using Constrained Independent Component Analysis
    Khan, Ozair Idris
    Kim, Sang-Hyuk
    Rasheed, Tahir
    Khan, Adil
    Kim, Tae-Seong
    2009 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, VOLS 1-20, 2009, : 4031 - +
  • [29] Adaptive Constrained Independent Vector Analysis: An Effective Solution for Analysis of Large-Scale Medical Imaging Data
    Bhinge, Suchita
    Long, Qunfang
    Calhoun, Vince D.
    Adali, Tulay
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2020, 14 (06) : 1255 - 1264
  • [30] Auxiliary Function Based Independent Vector Analysis with Spatial Initialization for Frequency Domain Speech Separation
    Chen, Songbo
    Zhao, Yuxin
    Liang, Yanfeng
    2014 SEVENTH INTERNATIONAL JOINT CONFERENCE ON COMPUTATIONAL SCIENCES AND OPTIMIZATION (CSO), 2014, : 185 - 189