Conference Papers 

Acoustic word embeddings for ASR error detection by Sahar Ghannay, Yannick Estève, Nathalie Camelin, Paul Deléglise | Interspeech 2016, San Francisco, USA

Word embedding evaluation and combination by Sahar Ghannay, Benoit Favre, Yannick Estève, Nathalie Camelin | LREC 2016, Portorož, Slovenia

Evaluation of acoustic word embeddings by Sahar Ghannay, Yannick Estève, Nathalie Camelin, Paul Deléglise | RepEval@ACL 2016, Berlin, Germany

Face tracking system used for video analysis within EUMSSI by Nam Le, Alexander Heili, Di Wu, Jean-Marc Odobez (IDIAP) | ICPR 2016, Mexico

System to detect dubbing situation in broadcast news, which benefits the multimodal naming system used in EUMSSI by Nam Le, Jean-Marc Odobez  (IDIAP) | ACM Multimedia 2016, The Netherlands 

EUMSSI: Multilayered analysis of multimedia content using UIMA, MongoDB and Solr by Jens Grivolla, Maite Melero, Toni Badia (UPF) | MMDA 2016, The Netherlands 

CRIM and LIUM approaches for multi-genre broadcast media transcription by Vishwa Gupta, Paul Deléglise, Gilles Boulianne, Yannick Estève, Sylvain Meignier, Anthony Rousseau (LIUM) | MGB 2015 / ASRU 2015, USA

Combining continous word representation and prosodic features for ASR error prediction by Sahar Ghannay, Yannick Estève, Nathalie Camelin, Camille Dutrey, Fabian Santiago, Martine Adda-Decker (LIUM) | SLSP 2015, Hungary

Joint Graphical Models for Date Selection in Timeline Summarization by Giang Binh Tran, Eelco Herder, Katja Markert | ACL 2015, Beijing, China

Detecting Filter Bubbles in Ongoing News Stories by Giang Binh Tran, Eelco Herder | UMAP 2015, Dublin, Ireland

Timeline Summarization from Relevant Headlines by Giang Binh Tran, Mohammad Alrifai, Eelco Herder | ECIR 2015, Vienna, Austria

Face identification from overlaid texts using Local Face Recurrent Patterns and CRF models by Paul Gay, Elie Khoury, Sylvain Meignier, Jean-Marc Odobez, Paul Deleglise | IEEE International Conference on Image Processing (ICIP 2014), Paris, France

Is Incremental Cross-Show Speaker Diarization Efficient to Process Large Volumes of Data? by Grégor Dupuy, Sylvain Meignier and Yannick Estève | 15th Annual Conference of the International Speech Communication Association (ISCA 2014), Singapore

Metadata as Linked Open Data: mapping disparate XML metadata registries into one RDF/OWL registry by Marta Villegas, Maite Melero, Núria Bel | LREC 2014, Reykjavik, Iceland

A Conditional Random Field Approach for Audio-Visual People Diarization by Gay Paul, Khoury Elie, Meignier Sylvain, Odobez Jean-Marc, Deleglise Paul | IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2014, Florence, Italy

A hybrid recommender combining user, item and interaction data by Jens Grivolla, Diego Campo, Miquel Sonsona, Jose-Miguel Pulido, Toni Badia | CSCI’14, Las Vegas, USA


Workshop Papers

Joint EUMSI-MULTISENSOR Workshop on Multimodal Media Data Analytics at ECAI 2016 | MMDA Conference 2016, The Netherlands

EUMSSI team at the MediaEval Person Discovery Challenge by Nam Le, Di Wu, Sylvain Meignier, Jean-Marc Odobez | MediaEval 2015, Wurzen, Germany

International Workshop on Spoken Language Translation by Mercedes García-Martínez, Loïc Barrault, Anthony Rousseau, Paul Deléglise, Yannick Estève | IWSLT 2015, Vietnam

Demonstration of the EUMSSI Platform for Multimodal Analysis and Annotation by Jens Grivolla, Maite Melero, Yannick Estève, Eelco Herder, Peggy van der Kreeft, Raul Marin, Jean-Marc Odobez, Susanne Preuß | KESA2015, Barcelona, Spain

Comparison of Two Methods for Unsupervised Person Identification in TV Shows by Paul Gay, Grégor Dupuy, Carole Lailler, Jean-Marc Odobez, Sylvain Meignier, and Paul Deléglise | CBMI 2014 International Workshop on Content-Based Multimedia Indexing, Klagenfurt, Austria

Recent Improvements on ILP-based Clustering for Broadcast News Speaker Diarization by Grégor Dupuy, Sylvain Meignier, Paul Deléglise, Yannick Estève | ISCA Speaker and Language Recognition Workshop, Joensuu, Finland



CRF-Based Context Modeling for Person Identification in Broadcast Videos by Paul Gay, Sylvain Meignier, Paul Deléglise and Jean-Marc Odobez | frontiers in ICT, June 2016



2nd EUMSSI-MULTISENSOR User Day (22.9.2016) | Barcelona 2016, Spain

EUMSSI presented at IBC 2016 by VSN (9-13.9.2016) | IBC 2016, The Netherlands

EUMSSI presented at METAFORUM 2016 by UPF | METAFORUM, Portugal

EUMSSI presented at European Data Forum EDF 2016 by Toni Badia (UPF) | EDF 2016, The Netherlands

EUMSSI presented at BIT Broadcast 2016 by Gonzalo Acha, Jordi Capdevilla (VSN) | BIT Broadcast, Spain

EUMSSI presented at ICASSP 2016 by Gaël Le Lan, Sylvain Meignier, Delphine Charlet, Paul Deléglise (LIUM) | ICASSP 2016, China

EUMSSI presented at LREC2016 by Maite Melero, Jens Grivolla (UPF) | LREC2016, Slovenia

EUMSSI presented at CABSAT 2015 by VSN | CABSAT 2015, United Arab Emirates

EUMSSI presented at NAT Expo 2015 by VSN | NAT Expo 2015, Russia

1st EUMSSI-MULTISENSOR User Day | Bonn 2015, Germany

EUMSSI presented at IBC 2015 by Raúl Marín, Jordi Capdevilla (VSN) | IBC 2015, The Netherlands

EUMSSI team at the Person Discovery Challenge by Nam Le, Di Wu, Sylvain Meignier, Jean-Marc Odobez | MediaEval 2015, Wurzen, Germany

Challenges and Needs for Language Technologies for International Broadcasters by Peggy van der Kreeft | Riga Summit 2015, Riga, Latvia

This is a unique website which will require a more modern browser to work! Please upgrade today!