Title
Multichannel Speech Separation and Enhancement Using the Convolutive Transfer Function.
Abstract
This paper addresses the problem of speech separation and enhancement from multichannel convolutive and noisy mixtures, assuming known mixing filters. We propose to perform speech separation and enhancement in the short-time Fourier transform domain using the convolutive transfer function (CTF) approximation. Compared to time-domain filters, the CTF has much less taps. Consequently, it requires le...
Year
DOI
Venue
2019
10.1109/TASLP.2019.2892412
IEEE/ACM Transactions on Audio, Speech, and Language Processing
Keywords
Field
DocType
Time-domain analysis,Source separation,Microphones,Convolution,Speech enhancement,Transfer functions
Speech enhancement,Noise power,Pattern recognition,Convolution,Computer science,Basis pursuit,Filter (signal processing),Short-time Fourier transform,Transfer function,Artificial intelligence,Source separation
Journal
Volume
Issue
ISSN
27
3
2329-9290
Citations 
PageRank 
References 
2
0.36
21
Authors
4
Name
Order
Citations
PageRank
Xiaofei Li110324.78
Laurent Girin247353.76
Sharon Gannot31754130.51
Radu Horaud42776261.99