Using linguistic and vocal expressiveness in social role recognition

Authors:
Theresa Wilson;Gregor Hofer
Affiliations:
University of Edinburgh, Edinburgh, United Kingdom;University of Edinburgh, Edinburgh, United Kingdom
Venue:
Proceedings of the 16th international conference on Intelligent user interfaces
Year:
2011

Citing 6
Cited 0

BoosTexter: A Boosting-based Systemfor Text Categorization

Machine Learning - Special issue on information retrieval
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Using the influence model to recognize functional roles in meetings

Proceedings of the 9th international conference on Multimodal interfaces
Multimodal support to group dynamics

Personal and Ubiquitous Computing - Special Issue: User-centred design and evaluation of ubiquitous groupware
Role recognition in multiparty recordings using social affiliation networks and discrete distributions

ICMI '08 Proceedings of the 10th international conference on Multimodal interfaces
Multimodal subjectivity analysis of multiparty conversation

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we investigate two types of expressiveness, linguistic and vocal, and whether they are useful for recognising the social roles of participants in meetings. Our experiments show that combining expressiveness features with speech activity does improve social role recognition over speech activity features alone.