Convolutive Blind Source Separation Based on Wavelet De-Noising

2013 ◽  
Vol 756-759 ◽  
pp. 3356-3361 ◽  
Author(s):  
Hong Bin Zhang ◽  
Peng Fei Xu
Keyword(s):  
Blind Source Separation ◽  
Time Domain ◽  
Source Separation ◽  
Noise Pollution ◽  
Processing Method ◽  
Separation System ◽  
Communication Signals ◽  
The Time Domain ◽  
Ica Algorithm ◽  
Convolutive Blind Source Separation

The paper discusses the time-domain blind seperation applied to communication signals, using an ICA algorithm EFICA together with a wavelet de-noising processing method. In the Blind source separation system, regardless of the mixed signals and separated signals, noise pollution occurs frequently, it increases the complexity of BSS and the difficulty of dealing with the aftermath. So an automatic method of and wavelet de-noising processing is proposed finally. It yields good results in the experiment and improves the performance of BSS system.

scholarly journals Real Time Blind Source Separation in Reverberant Environments

2021 ◽  
Author(s):  
◽  
Timothy Sherry
Keyword(s):  
Real Time ◽  
Blind Source Separation ◽  
Real World ◽  
Source Separation ◽  
Real World Data ◽  
The Core ◽  
Reverberant Environments ◽  
Ica Algorithm ◽  
Stationary Sources ◽  
Convolutive Blind Source Separation

<p>An online convolutive blind source separation solution has been developed for use in reverberant environments with stationary sources. Results are presented for simulation and real world data. The system achieves a separation SINR of 16.8 dB when operating on a two source mixture, with a total acoustic delay was 270 ms. This is on par with, and in many respects outperforms various published algorithms [1],[2]. A number of instantaneous blind source separation algorithms have been developed, including a block wise and recursive ICA algorithm, and a clustering based algorithm, able to obtain up to 110 dB SIR performance. The system has been realised in both Matlab and C, and is modular, allowing for easy update of the ICA algorithm that is the core of the unmixing process.</p>

The Improved Method for Solving Permutation Problem in Frequency Domain Blind Source Separation of Speech Signals

2012 ◽  
Vol 433-440 ◽  
pp. 7029-7034
Author(s):  
De Xiang Zhang ◽  
Xiao Pei Wu ◽  
Zhao Lv ◽  
Xiao Jing Guo
Keyword(s):  
Frequency Domain ◽  
Blind Source Separation ◽  
Time Domain ◽  
Source Separation ◽  
Speech Signals ◽  
Source Signal ◽  
Frequency Components ◽  
Permutation Problem ◽  
The Time Domain ◽  
Permutation Ambiguity

The signals of convolutive mixture in time-domain can be transformed to instantaneous mixtures in frequency-domain and complex-valued independent component analysis (CICA) can separate efficiently the signals of instantaneous mixture in each frequency bin. However, since CICA is calculated in each frequency bin independently, the permutation ambiguity becomes a serious problem. The permutation ambiguity of CICA in each frequency bin should be aligned so that a separated signal in the time-domain contains frequency components of the same source signal. The paper presents a novel and efficient approach for solving the permutation problem in frequency domain blind source separation of speech signals. The new algorithm models the frequency-domain separated signals by means of Teager energy correlation between neighboring bins for the detection of correct permutations. Experimental results show that the proposed algorithm can efficiently solve the permutation ambiguity problem in each frequency bin.

scholarly journals Real Time Blind Source Separation in Reverberant Environments

2021 ◽  
Author(s):  
◽  
Timothy Sherry
Keyword(s):  
Real Time ◽  
Blind Source Separation ◽  
Real World ◽  
Source Separation ◽  
Real World Data ◽  
The Core ◽  
Reverberant Environments ◽  
Ica Algorithm ◽  
Stationary Sources ◽  
Convolutive Blind Source Separation

<p>An online convolutive blind source separation solution has been developed for use in reverberant environments with stationary sources. Results are presented for simulation and real world data. The system achieves a separation SINR of 16.8 dB when operating on a two source mixture, with a total acoustic delay was 270 ms. This is on par with, and in many respects outperforms various published algorithms [1],[2]. A number of instantaneous blind source separation algorithms have been developed, including a block wise and recursive ICA algorithm, and a clustering based algorithm, able to obtain up to 110 dB SIR performance. The system has been realised in both Matlab and C, and is modular, allowing for easy update of the ICA algorithm that is the core of the unmixing process.</p>

Sign in / Sign up

Export Citation Format

Share Document