A Tutorial on Text-Independent Speaker Verification

Autor: Frédéric Bimbot, Jean-François Bonastre, Corinne Fredouille, Guillaume Gravier, Ivan Magrin-Chagnolleau, Sylvain Meignier, Teva Merlin, Javier Ortega-García, Dijana Petrovska-Delacrétaz, Douglas A. Reynolds

Publikováno v: EURASIP Journal on Advances in Signal Processing, Vol 2004, Iss 4, Pp 430-451 (2004)

This paper presents an overview of a state-of-the-art text-independent speaker verification system. First, an introduction proposes a modular scheme of the training and test phases of a speaker verification system. Then, the most commonly speech para

Externí odkaz: https://doaj.org/article/25ca6e24b24746e2bf1765c3bf65355b

Hierarchical multi-label propagation using speaking face graphs for multimodal person discovery

Autor: Guillaume Gravier, Gabriel Barbosa da Fonseca, Zenilton Kleber Gonçalves do Patrocínio, Silvio Jamil Ferzoli Guimarães, Gabriel Sargent, Ronan Sicre

Publikováno v: Multimedia Tools and Applications
Multimedia Tools and Applications, Springer Verlag, In press, pp.1-27. ⟨10.1007/s11042-020-09692-x⟩
Multimedia Tools and Applications, In press, pp.1-27. ⟨10.1007/s11042-020-09692-x⟩

International audience; TV archives are growing in size so fast that manually indexing becomes unfeasible. Automatic indexing techniques can be applied to overcome this issue, and this work proposes an unsupervised technique for multimodal person dis

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::929c159bb1f113927f68c066c8e93b55
https://doi.org/10.1007/s11042-020-09692-x

Rethinking deep active learning: Using unlabeled data at model training

Autor: Oriane Siméoni, Yannis Avrithis, Guillaume Gravier, Mateusz Budnik

Publikováno v: ICPR 2020-25th International Conference on Pattern Recognition
ICPR 2020-25th International Conference on Pattern Recognition, Jan 2021, Milan, Italy. pp.1-12
International Conference on Pattern Recognition
International Conference on Pattern Recognition, 2020, Milan, Italy
ICPR

International audience; Active learning typically focuses on training a model on few labeled examples alone, while unlabeled ones are only used for acquisition. In this work we depart from this setting by using both labeled and unlabeled data during

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::12e0a0266c90869a4299232993c0d8b9
https://inria.hal.science/hal-02372102

Rennes - une IA souveraine au service de la vie publique

Autor: Guillaume Gravier, Elisa Fromont, Nicolas Courty, Teddy Furon, Christine Guillemot, Paolo Robuffo Giordano

Publikováno v: Bulletin de l'Association Française pour l'Intelligence Artificielle
Bulletin de l'Association Française pour l'Intelligence Artificielle, AFIA
Bulletin de l'Association Française pour l'Intelligence Artificielle, 2021
Bulletin de l'Association Française pour l'Intelligence Artificielle, AFIA, 2021
HAL

National audience

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::dafe9871e1249c07a2942e394e99835a
https://hal.science/hal-03313161

A correlation-based entity embedding approach for robust entity linking

Autor: Cheikh Brahim El Vaigh, Robin Allesiardo, François Torregrossa, Guillaume Gravier, Pascale Sébillot

Publikováno v: ICTAI 2020-IEEE 32nd International Conference on Tools with Artificial Intelligence
ICTAI 2020-IEEE 32nd International Conference on Tools with Artificial Intelligence, Nov 2020, Virtual, United States. pp.1-6
ICTAI

International audience; Entity alignment is a crucial tool in knowledge discovery to reconcile knowledge from different sources. Recent state-of-the-art approaches leverage joint embedding of knowledge graphs (KGs) so that similar entities from diffe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::feff48882385bfb6b7a72dd341f25399
https://hal.inria.fr/hal-02999303/document