A MULTIMODAL APPROACH TO EXTRACT OPTIMIZED AUDIO FEATURES FOR SPEAKER DETECTION (TueAmOR6)

Author(s) : Patricia Besson (Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland) Murat Kunt (Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland) Torsten Butz (Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland) Jean-Philippe Thiran (Ecole Polytechnique Federale de Lausanne (EPFL), Switzerland)

Abstract : We present a method that exploits an information theoretic framework to extract optimal audio features with respect to the video features. A simple measure of mutual information between the resulting audio features and the video ones allows to detect the active speaker among different candidates. The results show that our method is able to exploit the shared speech information contained in audio and video signals to recover their common source.

Menu