DocumentCode :
699691
Title :
A multimodal approach for frequency domain independent component analysis with geometrically-based initialization
Author :
Naqvi, S.M. ; Zhang, Y. ; Tsalaile, T. ; Sanei, S. ; Chambers, J.A.
Author_Institution :
Dept. of Electron. & Electr. Eng., Loughborough Univ., Loughborough, UK
fYear :
2008
fDate :
25-29 Aug. 2008
Firstpage :
1
Lastpage :
5
Abstract :
A novel multimodal approach for independent component analysis (ICA) of complex valued frequency domain signals is presented which utilizes video information to provide geometrical description of both the speakers and the microphones. This geometric information, the visual aspect, is incorporated into the initialization of the complex ICA algorithm for each frequency bin, as such, the method is multimodal since two signal modalities, speech and video, are exploited. The separation results show a significant improvement over traditional frequency domain convolutive blind source separation (BSS) systems. Importantly, the inherent permutation problem in the frequency domain BSS (complex valued signals) with the improvement in the rate of convergence, for static sources, is shown to be solved by simulation results at the level of each frequency bin. We also highlight that certain fixed point algorithms proposed by Hyvärinen et. al., or their constrained versions, are not valid for complex valued signals.
Keywords :
blind source separation; convolution; frequency-domain analysis; geometry; independent component analysis; complex ICA algorithm; complex valued frequency domain signals; convolutive blind source separation; fixed point algorithm; frequency domain independent component analysis; geometrically-based initialization; multimodal approach; Algorithm design and analysis; Cameras; Convergence; Frequency-domain analysis; Performance analysis; Source separation; Speech;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Conference, 2008 16th European
Conference_Location :
Lausanne
ISSN :
2219-5491
Type :
conf
Filename :
7080223
Link To Document :
بازگشت