INTERSPEECH 2010
11th Annual Conference of the International Speech Communication Association

Makuhari, Chiba, Japan
September 26-30. 2010

Audio-Visual Synchronisation for Speaker Diarisation

Giulia Garau, Alfred Dielmann, Hervé Bourlard

Idiap Research Institute, Switzerland

The role of audio–visual speech synchrony for speaker diarisation is investigated on the multiparty meeting domain. We measured both mutual information and canonical correlation on different sets of audio and video features. As acoustic features we considered energy and MFCCs. As visual features we experimented both with motion intensity features, computed on the whole image, and Kanade Lucas Tomasi motion estimation. Thanks to KLT we decomposed the motion in its horizontal and vertical components. The vertical component was found to be more reliable for speech synchrony estimation. The mutual information between acoustic energy and KLT vertical motion of skin pixels, not only resulted in a 20% relative improvement over a MFCC only diarisation system, but also outperformed visual features such as motion intensities and head poses.

Full Paper

Bibliographic reference.  Garau, Giulia / Dielmann, Alfred / Bourlard, Hervé (2010): "Audio-visual synchronisation for speaker diarisation", In INTERSPEECH-2010, 2654-2657.