This paper overviews a total solution for frequency-domain blind source separation (BSS) of convolutive mixtures of audio signals, especially speech. Frequency-domain BSS performs independent component analysis (ICA) in each frequency bin, and this is more efficient than time-domain BSS. We describe a sophisticated total solution for frequency-domain BSS, including permutation, scaling, circularity, and complex activation function solutions. Experimental results of 2
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Shoji MAKINO, Hiroshi SAWADA, Ryo MUKAI, Shoko ARAKI, "Blind Source Separation of Convolutive Mixtures of Speech in Frequency Domain" in IEICE TRANSACTIONS on Fundamentals,
vol. E88-A, no. 7, pp. 1640-1655, July 2005, doi: 10.1093/ietfec/e88-a.7.1640.
Abstract: This paper overviews a total solution for frequency-domain blind source separation (BSS) of convolutive mixtures of audio signals, especially speech. Frequency-domain BSS performs independent component analysis (ICA) in each frequency bin, and this is more efficient than time-domain BSS. We describe a sophisticated total solution for frequency-domain BSS, including permutation, scaling, circularity, and complex activation function solutions. Experimental results of 2
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e88-a.7.1640/_p
Copy
@ARTICLE{e88-a_7_1640,
author={Shoji MAKINO, Hiroshi SAWADA, Ryo MUKAI, Shoko ARAKI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Blind Source Separation of Convolutive Mixtures of Speech in Frequency Domain},
year={2005},
volume={E88-A},
number={7},
pages={1640-1655},
abstract={This paper overviews a total solution for frequency-domain blind source separation (BSS) of convolutive mixtures of audio signals, especially speech. Frequency-domain BSS performs independent component analysis (ICA) in each frequency bin, and this is more efficient than time-domain BSS. We describe a sophisticated total solution for frequency-domain BSS, including permutation, scaling, circularity, and complex activation function solutions. Experimental results of 2
keywords={},
doi={10.1093/ietfec/e88-a.7.1640},
ISSN={},
month={July},}
Copy
TY - JOUR
TI - Blind Source Separation of Convolutive Mixtures of Speech in Frequency Domain
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1640
EP - 1655
AU - Shoji MAKINO
AU - Hiroshi SAWADA
AU - Ryo MUKAI
AU - Shoko ARAKI
PY - 2005
DO - 10.1093/ietfec/e88-a.7.1640
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E88-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2005
AB - This paper overviews a total solution for frequency-domain blind source separation (BSS) of convolutive mixtures of audio signals, especially speech. Frequency-domain BSS performs independent component analysis (ICA) in each frequency bin, and this is more efficient than time-domain BSS. We describe a sophisticated total solution for frequency-domain BSS, including permutation, scaling, circularity, and complex activation function solutions. Experimental results of 2
ER -