@article{zhang2008boosting-based,
author = {Zhang, Cha and Yin, Pei and Rui, Yong and Cutler, Ross and Viola, Paul and Sun, Xinding and Pinto, Nelson and Zhang, Zhengyou},
title = {Boosting-Based Multimodal Speaker Detection for Distributed Meeting Videos},
year = {2008},
month = {August},
abstract = {Identifying the active speaker in a video of a distributed meeting can be very helpful for remote participants to understand the dynamics of the meeting. A straightforward application of such analysis is to stream a high resolution video of the speaker to the remote participants. In this paper, we present the challenges we met while designing a speaker detector for the Microsoft RoundTable distributed meeting device, and propose a novel boosting-based multimodal speaker detection (BMSD) algorithm. Instead of separately performing sound source localization (SSL) and multiperson detection (MPD) and subsequently fusing their individual results, the  proposed algorithm fuses audio and visual information at feature level by using 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. In experiments that includes hundreds of real-world meetings, the proposed BMSD algorithm reduces the error rate of SSL-only approach by 24.6%, and the SSL and MPD fusion approach by 20.9%. To the best of our knowledge, this is the first real-time multimodal speaker detection algorithm that is deployed in commercial products.},
url = {http://approjects.co.za/?big=en-us/research/publication/boosting-based-multimodal-speaker-detection-distributed-meeting-videos/},
pages = {1541-1552},
journal = {IEEE Transactions on Multimedia},
}