An analytical evaluation of search by content and interaction patterns on multimodal meeting records

Bouamrane, M.M. and Luz, S. (2007) An analytical evaluation of search by content and interaction patterns on multimodal meeting records. Multimedia Systems, 13(2), pp. 89-102. (doi: 10.1007/s00530-007-0087-8)

Full text not currently available from Enlighten.

Publisher's URL: http://dx.doi.org/10.1007/s00530-007-0087-8

Abstract

It has been suggested that combining content-based indexing with automatically generated temporal metadata might help improve search and browsing of recordings of computer-mediated collaborative activities such as on-line meetings, which are characterised by extensive multimodal communication. This paper presents an analytical evaluation of the effectiveness of these techniques as implemented through automatic speech recognition and temporal mapping. In particular, it assesses the extent to which this strategy can help uncover contextual relationships between audio and text segments in recorded remote meetings. Results show that even simple temporal mapping can effectively support retrieval of recorded audio segments, improve retrieval performance in situations where speech recognition alone would have exhibited prohibitively high word error rates, and provide a basic form of semantic adaptation

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Bouamrane, Dr Matt-Mouley
Authors: Bouamrane, M.M., and Luz, S.
College/School:College of Medical Veterinary and Life Sciences > School of Medicine, Dentistry & Nursing > Centre for Population and Health Sciences
College of Medical Veterinary and Life Sciences > School of Health & Wellbeing > General Practice and Primary Care
Journal Name:Multimedia Systems
ISSN:0942-4962

University Staff: Request a correction | Enlighten Editors: Update this record