First Workshop on Speech, Language and Audio in Multimedia (SLAM 2013)

Marseille, France
August 22-23, 2013

PERCOLI: A Person Identification System for the 2013 REPERE Challenge

Benoit Favre (1), Géraldine Damnati (4), Frederic Bechet (1), Meriem Bendris (1), Delphine Charlet (4), Rémi Auguste (3), Stéphane Ayache (1), Benjamin Bigot (3), Alexandre Deltei (4), Richard Dufour (3), Corinne Fredouille (3), Georges Linarès (3), Jean Martinet (2), Gregory Senay (3), Pierre Tirilly (2)

(1) Aix Marseille Université, LIF-CNRS; (2) Université de Lille, LIFL; (3) Université d’Avignon, LIA; (4) Orange Labs; France

The goal of the PERCOL project is to participate to the REPERE multimodal challenge by building a consortium combining different scientific fields (audio, text and video) in order to perform person recognition in video documents. The two main scientific issues addressed by the challenge are firstly multimodal fusion algorithms for automatic person recognition in video broadcast ; and secondly the improvement of information extraction from speech and images thanks to a combine decoding using both modalities to reduce decoding ambiguities. This paper describes the system PERCOLI that participated to the REPERE 2013 challenge and presents the results obtained on the main person recognition tasks. Index Terms : multimodal fusion, person identification, video processing.

Full Paper

Bibliographic reference.  Favre, Benoit / Damnati, Géraldine / Bechet, Frederic / Bendris, Meriem / Charlet, Delphine / Auguste, Rémi / Ayache, Stéphane / Bigot, Benjamin / Deltei, Alexandre / Dufour, Richard / Fredouille, Corinne / Linarès, Georges / Martinet, Jean / Senay, Gregory / Tirilly, Pierre (2013): "PERCOLI: a person identification system for the 2013 REPERE challenge", In SLAM-2013, 55-60.