The search functionality is under construction.

The search functionality is under construction.

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.

- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E91-A No.6 pp.1357-1361

- Publication Date
- 2008/06/01

- Publicized

- Online ISSN
- 1745-1337

- DOI
- 10.1093/ietfec/e91-a.6.1357

- Type of Manuscript
- Special Section LETTER (Special Section on Acoustic Scene Analysis and Reproduction)

- Category

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 -