We propose a new algorithm for the blind source separation (BSS) approach in which independent component analysis (ICA) and frequency subband beamforming interpolation are combined. The slow convergence of the optimization of the separation filters is a problem in ICA. Our approach to resolving this problem is based on the relationship between ICA and null beamforming (NBF). The proposed method consists of the following three parts: (I) a frequency subband selector part for learning ICA, (II) a frequency domain ICA part with direction-of-arrivals (DOA) estimation of sound sources, and (III) an interpolation part in which null beamforming constructed with the estimated DOA is used. The results of the signal separation experiments under a reverberant condition reveal that the convergence speed is superior to that of the conventional ICA-based BSS methods.
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
Keiichi OSAKO, Yoshimitsu MORI, Yu TAKAHASHI, Hiroshi SARUWATARI, Kiyohiro SHIKANO, "Fast Convergence Blind Source Separation Using Frequency Subband Interpolation by Null Beamforming" in IEICE TRANSACTIONS on Fundamentals,
vol. E91-A, no. 6, pp. 1357-1361, June 2008, doi: 10.1093/ietfec/e91-a.6.1357.
Abstract: We propose a new algorithm for the blind source separation (BSS) approach in which independent component analysis (ICA) and frequency subband beamforming interpolation are combined. The slow convergence of the optimization of the separation filters is a problem in ICA. Our approach to resolving this problem is based on the relationship between ICA and null beamforming (NBF). The proposed method consists of the following three parts: (I) a frequency subband selector part for learning ICA, (II) a frequency domain ICA part with direction-of-arrivals (DOA) estimation of sound sources, and (III) an interpolation part in which null beamforming constructed with the estimated DOA is used. The results of the signal separation experiments under a reverberant condition reveal that the convergence speed is superior to that of the conventional ICA-based BSS methods.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1093/ietfec/e91-a.6.1357/_p
Copy
@ARTICLE{e91-a_6_1357,
author={Keiichi OSAKO, Yoshimitsu MORI, Yu TAKAHASHI, Hiroshi SARUWATARI, Kiyohiro SHIKANO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Fast Convergence Blind Source Separation Using Frequency Subband Interpolation by Null Beamforming},
year={2008},
volume={E91-A},
number={6},
pages={1357-1361},
abstract={We propose a new algorithm for the blind source separation (BSS) approach in which independent component analysis (ICA) and frequency subband beamforming interpolation are combined. The slow convergence of the optimization of the separation filters is a problem in ICA. Our approach to resolving this problem is based on the relationship between ICA and null beamforming (NBF). The proposed method consists of the following three parts: (I) a frequency subband selector part for learning ICA, (II) a frequency domain ICA part with direction-of-arrivals (DOA) estimation of sound sources, and (III) an interpolation part in which null beamforming constructed with the estimated DOA is used. The results of the signal separation experiments under a reverberant condition reveal that the convergence speed is superior to that of the conventional ICA-based BSS methods.},
keywords={},
doi={10.1093/ietfec/e91-a.6.1357},
ISSN={1745-1337},
month={June},}
Copy
TY - JOUR
TI - Fast Convergence Blind Source Separation Using Frequency Subband Interpolation by Null Beamforming
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1357
EP - 1361
AU - Keiichi OSAKO
AU - Yoshimitsu MORI
AU - Yu TAKAHASHI
AU - Hiroshi SARUWATARI
AU - Kiyohiro SHIKANO
PY - 2008
DO - 10.1093/ietfec/e91-a.6.1357
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E91-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2008
AB - We propose a new algorithm for the blind source separation (BSS) approach in which independent component analysis (ICA) and frequency subband beamforming interpolation are combined. The slow convergence of the optimization of the separation filters is a problem in ICA. Our approach to resolving this problem is based on the relationship between ICA and null beamforming (NBF). The proposed method consists of the following three parts: (I) a frequency subband selector part for learning ICA, (II) a frequency domain ICA part with direction-of-arrivals (DOA) estimation of sound sources, and (III) an interpolation part in which null beamforming constructed with the estimated DOA is used. The results of the signal separation experiments under a reverberant condition reveal that the convergence speed is superior to that of the conventional ICA-based BSS methods.
ER -