%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 11:28:44 AM @TECHREPORT{gatica-rr-04-51, author = {Gatica-Perez, Daniel and McCowan, Iain A. and Zhang, Dong and Bengio, Samy}, projects = {Idiap}, title = {Detecting Group Interest-level in Meetings}, type = {Idiap-RR}, number = {Idiap-RR-51-2004}, year = {2004}, institution = {IDIAP}, address = {Martigny, Switzerland}, note = {Submitted for publication.}, abstract = {Finding relevant segments in meeting recordings is important for summarization, browsing, and retrieval purposes. In this paper, we define relevance as the interest-level that meeting participants manifest as a group during the course of their interaction (as perceived by an external observer,',','), and investigate the automatic detection of segments of high-interest from audio-visual cues. This is motivated by the assumption that there is a relationship between segments of interest to participants, and those of interest to the end user, e.g. of a meeting browser. We first address the problem of human annotation of group interest-level. On a 50-meeting corpus, recorded in a room equipped with multiple cameras and microphones, we found that the annotations generated by multiple people exhibit a good degree of consistency, providing a stable ground-truth for automatic methods. For the automatic detection of high-interest segments, we investigate a methodology based on Hidden Markov Models (HMMs) and a number of audio and visual features. Single- and multi-stream approaches were studied. Using precision and recall as performance measures, the results suggest that (i) the automatic detection of group interest-level is promising, and (ii) while audio in general constitutes the predominant modality in meetings, the use of a multi-modal approach is beneficial.}, pdf = {https://publications.idiap.ch/attachments/reports/2004/gatica-rr-04-51.pdf}, postscript = {ftp://ftp.idiap.ch/pub/reports/2004/gatica-rr-04-51.ps.gz}, ipdmembership={speech, learning, vision}, language={English}, }