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

被引:0
作者
Jasmine J. C. Sheeja
B. Sankaragomathi
机构
[1] Rohini College of Engineering and Technology,Department of ECE
[2] Sri Sakthi Institue of Engineering and Technology,Department of Biomedical Engineering
来源
Neural Computing and Applications | 2023年 / 35卷
关键词
Locally Weighted Projection Regression (LWPR); Blind Source Separation (BSS); Dereverberation; Reverberation; PCA; Speech signals;
D O I
暂无
中图分类号
学科分类号
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:17
相关论文
共 116 条
  • [1] Herzog A(2020)Direction and reverberation preserving noise reduction of ambisonics signals IEEE/ACM Trans Audio Speech Lang Process 28 2461-2475
  • [2] Habets EA(2021)Blind separation of coherent multipath signals with impulsive interference and Gaussian noise in time-frequency domain Signal Process 178 107750-19
  • [3] Xiao Y(2018)Improving clustering performance using independent component analysis and unsupervised feature learning HCIS 8 1-113
  • [4] Lu W(2017)Model-based estimation of late reverberant spectral variance using modified weighted prediction error method Speech Commun 92 100-6378
  • [5] Yan Q(2015)Robust kronecker product PCA for spatio-temporal covariance estimation IEEE Trans Signal Process 63 6368-27
  • [6] Zhang H(2022)Underwater IoT network by blind MIMO OFDM transceiver based on probabilistic Stone’s blind source separation ACM Trans Sensor Netw (TOSN) 18 1-165
  • [7] Gultepe E(2022)Effective methods and performance analysis on data transmission security with blind source separation in space-based AIS China Commun 19 154-87245
  • [8] Makrehchi M(2019)An analysis approach for multivariate vibration signals integrate HIWO/BBO optimized blind source separation with NA-MEMD IEEE Access 7 87233-41219
  • [9] Parchami M(2020)Convolutive blind source separation for communication signals based on the sliding Z-transform IEEE Access 8 41213-17
  • [10] Zhu WP(2021)Blind source separation based on quantum slime mould algorithm in impulse noise Math Problems Eng 2021 1-1871