@inproceedings{zhang2006boosting-based,
author = {Zhang, Cha and Yin, Pei and Rui, Yong and Cutler, Ross and Viola, P.},
title = {Boosting-Based Multimodal Speaker Detection for Distributed Meetings},
booktitle = {2006 Multimedia Signal Processing},
year = {2006},
month = {September},
abstract = {Speaker detection is a very important task in distributed meeting applications. This paper discusses a number of challenges we met while designing a speaker detector for the Microsoft RoundTable distributed meeting device, and proposes a boosting-based multimodal speaker detection (BMSD) algorithm. Instead of performing sound source localization (SSL) and multi-person detection (MPD) separately and subsequently fusing their individual results, the proposed algorithm uses boosting to select features from a combined pool of both audio and visual features simultaneously. The result is a very accurate speaker detector with extremely high efficiency. The algorithm reduces the error rate of SSL-only approach by 47%, and the SSL and MPD fusion approach by 27%.},
publisher = {IEEE},
url = {http://approjects.co.za/?big=en-us/research/publication/boosting-based-multimodal-speaker-detection-for-distributed-meetings/},
pages = {86-91},
}