Searching-and-averaging method of underdetermined blind speech signal separation in time domain

2007 ◽  
Vol 50 (5) ◽  
pp. 771-782 ◽  
Author(s):  
Ming Xiao ◽  
ShengLi Xie ◽  
YuLi Fu
Keyword(s):  
Time Domain ◽  
Speech Signal ◽  
Averaging Method ◽  
Signal Separation

scholarly journals Two De-Noising Methods Based on Gabor Transform

2011 ◽  
Vol 2-3 ◽  
pp. 176-181
Author(s):  
Yong Jun Shen ◽  
Guang Ming Zhang ◽  
Shao Pu Yang ◽  
Hai Jun Xing
Keyword(s):  
Wavelet Transform ◽  
Adaptive Filtering ◽  
Time Domain ◽  
Background Noise ◽  
Averaging Method ◽  
Vibration Signal ◽  
Gabor Transform ◽  
Transform Domain ◽  
Computation Scheme ◽  
Source Signals

Two de-noising methods, named as the averaging method in Gabor transform domain (AMGTD) and the adaptive filtering method in Gabor transform domain (AFMGTD), are presented in this paper. These two methods are established based on the correlativity of the source signals and the background noise in time domain and Gabor transform domain, that is to say, the uncorrelated source signals and background noise in time domain would still be uncorrelated in Gabor transform domain. The construction and computation scheme of these two methods are investigated. The de-noising performances are illustrated by some simulation signals, and the wavelet transform is used to compare with these two new de-noising methods. The results show that these two methods have better de-noising performance than the wavelet transform, and could reduce the background noise in the vibration signal more effectively.

Blind speech signal separation based on non-stationary and colored characteristics

2006 ◽  
Author(s):  
Fengyu Cong ◽  
Yanxue Liang ◽  
Shaoling Ji ◽  
Yifan Hu ◽  
Xizhi Shi
Keyword(s):  
Speech Signal ◽  
Signal Separation

scholarly journals Text–Independent Speaker Recognition Using Two–Dimensional Information Entropy

2015 ◽  
Vol 66 (3) ◽  
pp. 169-173 ◽  
Author(s):  
Boško Božilović ◽  
Branislav M. Todorović ◽  
Miroslav Obradović
Keyword(s):  
Frequency Domain ◽  
Time Domain ◽  
Information Entropy ◽  
Speaker Recognition ◽  
Speech Signal ◽  
Experimental Results ◽  
Two Dimensional ◽  
Real Numbers ◽  
The Past ◽  
Signal Features

AbstractSpeaker recognition is the process of automatically recognizing who is speaking on the basis of speaker specific characteristics included in the speech signal. These speaker specific characteristics are called features. Over the past decades, extensive research has been carried out on various possible speech signal features obtained from signal in time or frequency domain. The objective of this paper is to introduce two-dimensional information entropy as a new text-independent speaker recognition feature. Computations are performed in time domain with real numbers exclusively. Experimental results show that the two-dimensional information entropy is a speaker specific characteristic, useful for speaker recognition.

A Variational Autoencoder Approach for Speech Signal Separation

2020 ◽  
pp. 558-567
Author(s):  
Hao D. Do ◽  
Son T. Tran ◽  
Duc T. Chau
Keyword(s):  
Speech Signal ◽  
Signal Separation ◽  
Variational Autoencoder
Sign in / Sign up

Export Citation Format

Share Document