%Aigaion2 BibTeX export from Idiap Publications
%Friday 05 December 2025 01:11:57 PM

@ARTICLE{gatica05db,
                      author = {Gatica-Perez, Daniel and Lathoud, Guillaume and Odobez, Jean-Marc and McCowan, Iain A.},
                    projects = {Idiap},
                       month = {3},
                       title = {Audio-visual probabilistic tracking of multiple speakers in meetings},
                     journal = {IEEE Trans. on Audio, Speech, and Language Processing, accepted for publication.},
                        year = {2006},
                        note = {IDIAP-RR 05-27},
                    crossref = {gatica05d},
                    abstract = {Tracking speakers in multiparty conversations constitutes a fundamental task for automatic meeting analysis. In this paper, we present a probabilistic approach to jointly track the location and speaking activity of multiple speakers in a multisensor meeting room, equipped with a small microphone array and multiple uncalibrated cameras. Our framework is based on a mixed-state dynamic graphical model defined on a multiperson state-space, which includes the explicit definition of a proximity-based interaction model. The model integrates audio-visual (AV) data through a novel observation model. Audio observations are derived from a source localization algorithm. Visual observations are based on models of the shape and spatial structure of human heads. Approximate inference in our model, needed given its complexity, is performed with a Markov Chain Monte Carlo particle filter (MCMC-PF,',','),
 which results in high sampling efficiency. We present results -based on an objective evaluation procedure- that show that our framework (1) is capable of locating and tracking the position and speaking activity of multiple meeting participants engaged in real conversations with good accuracy; (2) can deal with cases of visual clutter and partial occlusion; and (3) significantly outperforms a traditional sampling-based approach.},
                         pdf = {https://publications.idiap.ch/attachments/reports/2005/rr-05-27.pdf},
                  postscript = {ftp://ftp.idiap.ch/pub/reports/2005/rr-05-27.ps.gz},
ipdmembership={speech, vision},
}



crossreferenced publications: 
@TECHREPORT{gatica05d,
                      author = {Gatica-Perez, Daniel and Lathoud, Guillaume and Odobez, Jean-Marc and McCowan, Iain A.},
                    projects = {Idiap},
                       title = {Audio-visual probabilistic tracking of multiple speakers in meetings},
                        type = {Idiap-RR},
                      number = {Idiap-RR-27-2005},
                        year = {2005},
                 institution = {IDIAP},
                     address = {Martigny, Switzerland},
                        note = {submitted for publication},
                    abstract = {Tracking speakers in multiparty conversations constitutes a fundamental task for automatic meeting analysis. In this paper, we present a probabilistic approach to jointly track the location and speaking activity of multiple speakers in a multisensor meeting room, equipped with a small microphone array and multiple uncalibrated cameras. Our framework is based on a mixed-state dynamic graphical model defined on a multiperson state-space, which includes the explicit definition of a proximity-based interaction model. The model integrates audio-visual (AV) data through a novel observation model. Audio observations are derived from a source localization algorithm. Visual observations are based on models of the shape and spatial structure of human heads. Approximate inference in our model, needed given its complexity, is performed with a Markov Chain Monte Carlo particle filter (MCMC-PF,',','),
 which results in high sampling efficiency. We present results -based on an objective evaluation procedure- that show that our framework (1) is capable of locating and tracking the position and speaking activity of multiple meeting participants engaged in real conversations with good accuracy; (2) can deal with cases of visual clutter and partial occlusion; and (3) significantly outperforms a traditional sampling-based approach.},
                         pdf = {https://publications.idiap.ch/attachments/reports/2005/rr-05-27.pdf},
                  postscript = {ftp://ftp.idiap.ch/pub/reports/2005/rr-05-27.ps.gz},
ipdmembership={speech, vision},
language={English},
}