Multistream Dynamic Bayesian Network for Meeting Segmentation

13 years 9 months ago
Multistream Dynamic Bayesian Network for Meeting Segmentation
This paper investigates the automatic analysis and segmentation of meetings. A meeting is analysed in terms of individual behaviours and group interactions, in order to decompose each meeting in a sequence of relevant phases, named meeting actions. Three feature families are extracted from multimodal recordings: prosody from individual lapel microphone signals, speaker activity from microphone array data and lexical features from textual transcripts. A statistical approach is then used to relate low-level features with a set of abstract categories. In order to provide a flexible and powerful framework, we have employed a dynamic Bayesian network based model, characterized by multiple stream processing and flexible state duration modelling. Experimental results demonstrate the strength of this system, providing a meeting action error rate of 9%.
Alfred Dielmann, Steve Renals
Added 02 Jul 2010
Updated 02 Jul 2010
Type Conference
Year 2004
Where MLMI
Authors Alfred Dielmann, Steve Renals
Comments (0)