no code implementations • 23 Apr 2018 • Zied Elloumi, Laurent Besacier, Olivier Galibert, Juliette Kahn, Benjamin Lecouteux
In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs.
no code implementations • JEPTALNRECITAL 2016 • Olivier Galibert, Juliette Kahn, Sophie Rosset
Le travail que nous pr{\'e}sentons ici s{'}inscrit dans le domaine de l{'}{\'e}valuation des syst{\`e}mes de reconnaissance automatique de la parole en vue de leur utilisation dans une t{\^a}che aval, ici la reconnaissance des entit{\'e}s nomm{\'e}es.
no code implementations • JEPTALNRECITAL 2016 • Guillaume Bernard, Juliette Kahn, Olivier Galibert, R{\'e}mi Regnier, S{\'e}verine Demeyer
LNE-Visu : a tool to explore and visualize multimedia data LNE-Visu is a tool to explore and visualize multimedia data created for the LNE evaluation campaigns.
no code implementations • LREC 2016 • Olivier Galibert, Mohamed Ameur Ben Jannet, Juliette Kahn, Sophie Rosset
In the context of Automatic Speech Recognition (ASR) used as a first step towards Named Entity Recognition (NER) in speech, error seriousness is usually determined by their frequency, due to the use of the WER as metric to evaluate the ASR output, despite the emergence of more relevant measures in the literature.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • LREC 2016 • Moez Ajili, Jean-Fran{\c{c}}ois Bonastre, Juliette Kahn, Solange Rossato, Guillaume Bernard
A speech database has been collected for use to highlight the importance of {``}speaker factor{''} in forensic voice comparison.
no code implementations • LREC 2014 • Mohamed Ben Jannet, Martine Adda-Decker, Olivier Galibert, Juliette Kahn, Sophie Rosset
We then introduce a new metric, the Entity Tree Error Rate (ETER), to evaluate hierarchical and structured named entity detection, classification and decomposition.
no code implementations • LREC 2014 • Daniel Luzzati, Cyril Grouin, Ioana Vasilescu, Martine Adda-Decker, Eric Bilinski, Nathalie Camelin, Juliette Kahn, Carole Lailler, Lori Lamel, Sophie Rosset
This paper is concerned with human assessments of the severity of errors in ASR outputs.
no code implementations • JEPTALNRECITAL 2012 • Juliette Kahn, Aude Giraudel, Matthieu Carr{\'e}, Olivier Galibert, Ludovic Quintard
no code implementations • LREC 2012 • Aude Giraudel, Matthieu Carr{\'e}, Val{\'e}rie Mapelli, Juliette Kahn, Olivier Galibert, Ludovic Quintard
In this context, the REPERE corpus, a French videos corpus with multimodal annotation, has been developed.