TY - GEN

T1 - MLSP 2007 data analysis competition

T2 - 17th IEEE International Workshop on Machine Learning for Signal Processing, MLSP-2007

AU - Sawada, Hiroshi

AU - Araki, Shoko

AU - Makino, Shoji

PY - 2007

Y1 - 2007

N2 - This paper describes the frequency-domain approach to the blind source separation of speech/audio signals that are convolutively mixed in a real room environment. With the application of shorttime Fourier transforms, convolutive mixtures in the time domain can be approximated as multiple instantaneous mixtures in the frequency domain. We employ complex-valued independent component analysis (ICA) to separate the mixtures in each frequency bin. Then, the permutation ambiguity of the ICA solutions should be aligned so that the separated signals are constructed properly in the time domain. We propose a permutation alignment method based on clustering the activity sequences of the frequency bin-wise separated signals. We achieved the overall winner status of MLSP 2007 Data Analysis Competition based on the presented method.

AB - This paper describes the frequency-domain approach to the blind source separation of speech/audio signals that are convolutively mixed in a real room environment. With the application of shorttime Fourier transforms, convolutive mixtures in the time domain can be approximated as multiple instantaneous mixtures in the frequency domain. We employ complex-valued independent component analysis (ICA) to separate the mixtures in each frequency bin. Then, the permutation ambiguity of the ICA solutions should be aligned so that the separated signals are constructed properly in the time domain. We propose a permutation alignment method based on clustering the activity sequences of the frequency bin-wise separated signals. We achieved the overall winner status of MLSP 2007 Data Analysis Competition based on the presented method.

UR - http://www.scopus.com/inward/record.url?scp=48149093698&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48149093698&partnerID=8YFLogxK

U2 - 10.1109/MLSP.2007.4414280

DO - 10.1109/MLSP.2007.4414280

M3 - Conference contribution

AN - SCOPUS:48149093698

SN - 1424415667

SN - 9781424415663

T3 - Machine Learning for Signal Processing 17 - Proceedings of the 2007 IEEE Signal Processing Society Workshop, MLSP

SP - 45

EP - 50

BT - Machine Learning for Signal Processing 17 - Proceedings of the 2007 IEEE Signal Processing Society Workshop, MLSP

Y2 - 27 August 2007 through 29 August 2007

ER -