Speech Dereverberation Based on Sparse Matrix Decomposition

被引:0
|
作者
Fan, Miao [1 ]
Liu, Liyang [2 ]
Li, Weifeng
机构
[1] Tsinghua Univ, Grad Sch Shenzhen, Dept Elect Engineer, Beijing, Peoples R China
[2] Shenzhen Key Lab Informat Sci & Technol, Guangzhou, Guangdong, Peoples R China
关键词
RPCA; dereverberation; sparse matrix; low rank matrix;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Because of the increasingly demands of high quality audio signal, speech dereverberation, as the preliminary processing of speaker recognition and automatic speech recognition(ASR), becomes more and more important. The speech obtained from microphones is always distorted by reverberation. Conventional approaches always build a model to dereverberate speech. However, in different environments, these models may not be effective. For this reason, we propose an algorithm which does not base on any environment model assumptions so that it can be used for all speech. A piece of clean speech can be represented through a sparse matrix. The reverberated speech matrix can be decomposed into two matrices, clean speech matrix and reverberated noise matrix, to capture the sparse components of the speech using Robust Principal Component Analysis (RPCA). Evaluations via many different criterions show that the new approach preserves the clean speech's information well and dereverberate the speech well.
引用
收藏
页码:1169 / 1173
页数:5
相关论文
共 50 条
  • [1] Blind speech dereverberation using sparse decomposition and multi-channel linear prediction
    Mousavi, Leila
    Razzazi, Farbod
    Haghbin, Afrooz
    [J]. INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2019, 22 (03) : 729 - 738
  • [2] Blind speech dereverberation using sparse decomposition and multi-channel linear prediction
    Leila Mousavi
    Farbod Razzazi
    Afrooz Haghbin
    [J]. International Journal of Speech Technology, 2019, 22 : 729 - 738
  • [3] ROBUST SPEECH DEREVERBERATION BASED ON NON-NEGATIVITY AND SPARSE NATURE OF SPEECH SPECTROGRAMS
    Kameoka, Hirokazu
    Nakatani, Tomohiro
    Yoshioka, Takuya
    [J]. 2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 45 - 48
  • [4] A tensor decomposition based multichannel linear prediction approach to speech dereverberation
    Zeng, Xiaojin
    He, Hongsen
    Chen, Jingdong
    Benesty, Jacob
    [J]. APPLIED ACOUSTICS, 2023, 214
  • [5] SPEECH DEREVERBERATION BASED ON CONVEX OPTIMIZATION ALGORITHMS FOR GROUP SPARSE LINEAR PREDICTION
    Giacobello, Daniele
    Jensen, Tobias Lindstrom
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 446 - 450
  • [6] MULTI-MICROPHONE SPEECH DEREVERBERATION BASED ON EIGEN-DECOMPOSITION: A STUDY
    Gannot, Sharon
    [J]. 2008 42ND ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS, VOLS 1-4, 2008, : 801 - 805
  • [7] Speech Dereverberation Based on Generative Adversarial Network with Additive Frequency Domain Decomposition
    Quan, Haiyan
    Wang, Tao
    Zheng, Zhiqing
    [J]. Gongcheng Kexue Yu Jishu/Advanced Engineering Sciences, 2022, 54 (02): : 180 - 187
  • [8] Multi-Channel Linear Prediction-Based Speech Dereverberation With Sparse Priors
    Jukic, Ante
    van Waterschoot, Toon
    Gerkmann, Timo
    Doclo, Simon
    [J]. IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2015, 23 (09) : 1509 - 1520
  • [9] Multi-Channel Linear Prediction-Based Speech Dereverberation With Sparse Priors
    Department of Medical Physics and Acoustics, University of Oldenburg, Oldenburg
    26111, Germany
    不详
    3000, Belgium
    [J]. IEEE Trans. Audio Speech Lang. Process., 9 (1509-1520):
  • [10] SUPERVISED SPEECH DEREVERBERATION IN NOISY ENVIRONMENTS USING EXEMPLAR-BASED SPARSE REPRESENTATIONS
    Baby, Deepak
    Van Hamme, Hugo
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 156 - 160