MLSP 2007 Data Analysis Competition: Frequency-Domain Blind Source Separation for Convolutive Mixtures of Speech/Audio Signals
作者： Hiroshi Sawada , Shoko Araki , Shoji Makino
DOI: 10.1109/MLSP.2007.4414280
关键词:
摘要: This paper describes the frequency-domain approach to blind source separation of speech/audio signals that are convolutively mixed in a real room environment. With application short- time Fourier transforms, convolutive mixtures domain can be approximated as multiple instantaneous frequency domain. We employ complex-valued independent component analysis (ICA) separate each bin. Then, permutation ambiguity ICA solutions should aligned so separated constructed properly propose alignment method based on clustering activity sequences bin-wise signals. achieved overall winner status MLSP 2007 Data Analysis Competition presented method.
elsevier.com
ntt.co.jp 
tsukuba.ac.jp 参考文章(19)
Thomas Lotter, Single- and Multi-Microphone Spectral Amplitude Estimation Using a Super-Gaussian Speech Model Springer Berlin Heidelberg. pp. 67- 95 ,(2005) , 10.1007/3-540-27489-8_4
Shun-ichi Amari, Andrzej Cichocki, Adaptive blind signal and image processing ,(2002)
David G. Stork, Richard O. Duda, Peter E. Hart, Pattern Classification (2nd Edition) Wiley-Interscience. ,(2000)
Te-Won Lee, Independent component analysis: theory and applications Kluwer Academic Publishers. ,(1998)
Atsuo Hiroe, Solution of Permutation Problem in Frequency Domain ICA, Using Multivariate Probability Density Functions Independent Component Analysis and Blind Signal Separation. pp. 601- 608 ,(2006) , 10.1007/11679363_75
Erkki Oja, Aapo Hyvarinen, Juha Karhunen, Independent Component Analysis ,(2001)
O. Yilmaz, S. Rickard, Blind separation of speech mixtures via time-frequency masking IEEE Transactions on Signal Processing. ,vol. 52, pp. 1830- 1847 ,(2004) , 10.1109/TSP.2004.828896
Tilay Adall, Hualiang Li, A Practical Formulation for Computation of Complex Gradients and its Application to Maximum Likelihood ICA international conference on acoustics, speech, and signal processing. ,vol. 2, pp. 633- 636 ,(2007) , 10.1109/ICASSP.2007.366315
Paris Smaragdis, Blind separation of convolved mixtures in the frequency domain Neurocomputing. ,vol. 22, pp. 21- 34 ,(1998) , 10.1016/S0925-2312(98)00047-2
H. Sawada, R. Mukai, S. Araki, S. Makino, A robust and precise method for solving the permutation problem of frequency-domain blind source separation IEEE Transactions on Speech and Audio Processing. ,vol. 12, pp. 530- 538 ,(2004) , 10.1109/TSA.2004.832994