A multimodal approach to extract optimized audio features for speaker detection

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.


Published in:
Proceedings of European Signal Processing Conference (EUSIPCO)
Year:
2005
Publisher:
Louvain-la-Neuve, Belgium, IEEE
Keywords:
Laboratories:




 Record created 2006-06-14, last modified 2018-03-17

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)