Show Reference: "Online Multimodal Speaker Detection for Humanoid Robots"

Online multimodal speaker detection for humanoid robots In Humanoid Robots (Humanoids), 2012 12th IEEE-RAS International Conference on (November 2012), pp. 126-133, doi:10.1109/humanoids.2012.6651509 by Jordi Sanchez-Riera, Xavier Alameda-Pineda, Johannes Wienke, et al.
@inproceedings{sanchez-riera-et-al-2012,
    address = {Osaka, Japan},
    author = {Sanchez-Riera, Jordi and Alameda-Pineda, Xavier and Wienke, Johannes and Deleforge, Antoine and Arias, Soraya and Cech, Jan and Wrede, Sebastian and Horaud, Radu},
    booktitle = {2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids)},
    citeulike-article-id = {13505205},
    citeulike-linkout-0 = {http://dx.doi.org/10.1109/humanoids.2012.6651509},
    citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs\_all.jsp?arnumber=6651509},
    doi = {10.1109/humanoids.2012.6651509},
    institution = {INRIA Grenoble Rhone-Alpes, Monbonnot, France},
    issn = {2164-0572},
    keywords = {audio, localization, multisensory-integration, robotic, visual},
    month = nov,
    pages = {126--133},
    posted-at = {2015-01-30 16:57:35},
    priority = {2},
    publisher = {IEEE},
    title = {Online Multimodal Speaker Detection for Humanoid Robots},
    url = {http://dx.doi.org/10.1109/humanoids.2012.6651509},
    year = {2012}
}

See the CiteULike entry for more info, PDF links, BibTex etc.

Sanchez-Riera et al. use a probabilistic model for audio-visual active speaker localization on a humanoid robot (the Nao robot).

Sanchez-Riera et al. use the Bayesian information criterion to choose the number of speakers in their audio-visual active speaker localization system.

Sanchez-Riera et al. use the Waldboost face detection system for visual processing.

Sanchez-Riera et al. do not report on localization accuracy, but on correct speaker detections.