Speaker diarization is originally defined as the task of determining “who spoke when” given an audio track and no other prior knowledge of any kind. The following article sho...
We present a system to retrieve all clips from a meeting archive that show a particular individual speaking, using a single face or voice sample as the query. The system incorpora...
The Asynchronous Hidden Markov Model (AHMM) models the joint likelihood of two observation sequences, even if the streams are not synchronised. We explain this concept and how the...
Marc Al-Hames, Claus Lenz, Stephan Reiter, Joachim...
This paper describes experiments in automatic recognition of context-independent phoneme strings from meeting data using audiovisual features. Visual features are known to improve ...
Tracking speakers in multiparty conversations constitutes a fundamental task for automatic meeting analysis. In this paper, we present a probabilistic approach to jointly track th...
Daniel Gatica-Perez, Guillaume Lathoud, Jean-Marc ...