Robust feature selection for scaling ambiguity reduction in audio-visual convolutive BSS
Liu, Q, Naqvi, SM, Wang, W, Jackson, PJB and Chambers, J (2011) Robust feature selection for scaling ambiguity reduction in audio-visual convolutive BSS In: 19th European Signal Processing Conference 2011 (EUSIPCO 2011), 2011-08-29 - 2011-09-02, Barcelona, Spain.
["document_typename_application/x-pdf" not defined]
Available under License : See the attached licence file.
Information from video has been used recently to address the issue of scaling ambiguity in convolutive blind source separation (BSS) in the frequency domain, based on statistical modeling of the audio-visual coherence with Gaussian mixture models (GMMs) in the feature space. However, outliers in the feature space may greatly degrade the system performance in both training and separation stages. In this paper, a new feature selection scheme is proposed to discard non-stationary features, which improves the robustness of the coherence model and reduces its computational complexity. The scaling parameters obtained by coherence maximization and non-linear interpolation from the selected features are applied to the separated frequency components to mitigate the scaling ambiguity. A multimodal database composed of different combinations of vowels and consonants was used to test our algorithm. Experimental results show the performance improvement with our proposed algorithm.
|Item Type:||Conference or Workshop Item (Conference Paper)|
|Divisions :||Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing|
|Depositing User :||Symplectic Elements|
|Date Deposited :||08 Oct 2013 16:20|
|Last Modified :||09 Jun 2014 13:45|
Actions (login required)
Downloads per month over past year