Speech dereverberation and source separation using DNN-WPE and LWPR-PCA

被引:3
|
作者
Sheeja, Jasmine J. C. [1 ]
Sankaragomathi, B. [2 ]
机构
[1] Rohini Coll Engn & Technol, Dept ECE, Kanyakumari, India
[2] Sri Sakthi Inst Engn & Technol, Dept Biomed Engn, Coimbatore, India
来源
NEURAL COMPUTING & APPLICATIONS | 2023年 / 35卷 / 10期
关键词
Locally Weighted Projection Regression (LWPR); Blind Source Separation (BSS); Dereverberation; Reverberation; PCA; Speech signals; SELECTIVE HARMONIC ELIMINATION; INDEPENDENT VECTOR ANALYSIS; BLIND SOURCE SEPARATION; MULTILEVEL INVERTER TOPOLOGIES; PARTICLE SWARM OPTIMIZATION; NEURAL-NETWORK; ALGORITHM; MODULATION; EFFICIENT; REDUCTION;
D O I
10.1007/s00521-022-07884-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Speech signals observed from distantly placed microphones may have some acoustic interference, such as noise and reverberation. These may lead to the degradation of the quality of blind speech. Hence, it is necessary to process the acquired speech signals to separate the blind source and eliminate the reverberation. Therefore, we proposed a novel speech separation and dereverberation method, which is based on the incorporation of Locally Weighted Projection Regression (LWPR)-based Principal Component Analysis (PCA) and Deep Neural Network (DNN)-based Weighted Prediction Error (WPE). The proposed method preprocesses the mixed reverberant signal prior to the application of Blind Source Separation (BSS) and Blind Dereverberation (BD). The preprocessing of the input sample signals is performed with the exploitation of fast Fourier transform (FFT) and whitening approaches to convert the time domain signal into frequency domain signal and to generate the transformation matrices. Besides, the utilization of LWPR-PCA can perform the BSS and the DNN-WPE can be used to conduct the BD. Moreover, the experimental analysis of our proposed method is compared with the existing RPCA-SNMF, CBF, BA-CNMF, AFMNMF, and ISC-LPKF approaches. The experimental outcomes depict that the proposed method effectively separates the original signal from the mixed reverberant signals.
引用
收藏
页码:7339 / 7356
页数:18
相关论文
共 50 条
  • [1] Speech dereverberation and source separation using DNN-WPE and LWPR-PCA
    Jasmine J. C. Sheeja
    B. Sankaragomathi
    [J]. Neural Computing and Applications, 2023, 35 : 7339 - 7356
  • [2] FRAME-ONLINE DNN-WPE DEREVERBERATION
    Heymann, Jahn
    Drude, Lukas
    Haeb-Umbach, Reinhold
    Kinoshita, Keisuke
    Nakatani, Tomohiro
    [J]. 2018 16TH INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC), 2018, : 466 - 470
  • [3] Cascaded Speech Separation Denoising and Dereverberation Using Attention and TCN-WPE Networks for Speech Devices
    Zhang, Xuan
    Tang, Jun
    Cao, Huiliang
    Wang, Chenguang
    Shen, Chong
    Liu, Jun
    [J]. IEEE INTERNET OF THINGS JOURNAL, 2024, 11 (10): : 18047 - 18058
  • [4] Over-determined Speech Source Separation and Dereverberation
    Togami, Masahito
    Scheibler, Robin
    [J]. 2020 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2020, : 705 - 710
  • [5] Speech Recognition Using Blind Source Separation and Dereverberation Method for Mixed Sound of Speech and Music
    Wang, Longbiao
    Odani, Kyohei
    Kai, Atsuhiko
    Li, Weifeng
    [J]. 2013 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2013,
  • [6] Improvement of Mask-Based Speech Source Separation Using DNN
    Zhan, Ge
    Huang, Zhaoqiong
    Ying, Dongwen
    Pan, Jielin
    Yan, Yonghong
    [J]. 2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2016,
  • [7] A Semi-blind Source Separation Approach for Speech Dereverberation
    Wang, Ziteng
    Na, Yueyue
    Liu, Zhang
    Li, Yun
    Tian, Biao
    Fu, Qiang
    [J]. INTERSPEECH 2020, 2020, : 3925 - 3929
  • [8] Blind Speech Separation and Dereverberation using neural beamforming
    Pfeifenberger, Lukas
    Pernkopf, Franz
    [J]. SPEECH COMMUNICATION, 2022, 140 : 29 - 41
  • [9] ONLINE SPEECH DEREVERBERATION USING RLS-WPE BASED ON A FULL SPATIAL CORRELATION MATRIX INTEGRATED IN A SPEECH ENHANCEMENT SYSTEM
    Kim, Jun Hyung
    Park, Jazzson
    Ahn, Minwook
    Lee, Yeonbok
    Kim, Wonsub
    Park, Hyung-Min
    [J]. 2018 16TH INTERNATIONAL WORKSHOP ON ACOUSTIC SIGNAL ENHANCEMENT (IWAENC), 2018, : 36 - 40
  • [10] Single channel speech dereverberation and separation using RPCA and SNMF
    Ullah, Rizwan
    Islam, Md Shohidul
    Hossain, Md. Imran
    Wahab, Fazal E.
    Ye, Zhongfu
    [J]. APPLIED ACOUSTICS, 2020, 167