Automatic meeting participant role detection by dialogue patterns

Authors:
Jing Su;Bridget Kane;Saturnino Luz
Affiliations:
Department of Computer Science, O’Reilly Institute, Trinity College Dublin, Dublin 2, Ireland;Department of Computer Science, O’Reilly Institute, Trinity College Dublin, Dublin 2, Ireland;Department of Computer Science, O’Reilly Institute, Trinity College Dublin, Dublin 2, Ireland
Venue:
COST'09 Proceedings of the Second international conference on Development of Multimodal Interfaces: active Listening and Synchrony
Year:
2009

Citing 5
Cited 0

Discourse segmentation of multi-party conversation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Achieving Diagnosis by Consensus

Computer Supported Cooperative Work
Modeling vocal interaction for text-independent participant characterization in multi-party conversation

SIGdial '08 Proceedings of the 9th SIGdial Workshop on Discourse and Dialogue
Locating case discussion segments in recorded medical team meetings

SSCS '09 Proceedings of the third workshop on Searching spontaneous conversational speech
The significance of empty speech pauses: cognitive and algorithmic issues

BVAI'07 Proceedings of the 2nd international conference on Advances in brain, vision and artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We introduce a new concept of ‘Vocalization Horizon’ for automatic speaker role detection in general meeting recordings. We demonstrate that classification accuracy reaches 38.5% when Vocalization Horizon and other features (i.e. vocalization duration and start time) are available. With another type of Horizon, the Pause - Overlap Horizon, the classification accuracy reaches 39.5%. Pauses and overlaps are also useful vocalization features for meeting structure analysis. In our experiments, the Bayesian Network classifier outperforms other classifiers, and is proposed for similar applications.