Search Results for author: Nathalie Camelin

Found 22 papers, 0 papers with code

Are Embedding Spaces Interpretable? Results of an Intrusion Detection Evaluation on a Large French Corpus

no code implementations LREC 2022 Thibault Prouteau, Nicolas Dugué, Nathalie Camelin, Sylvain Meignier

It is operated using a large French corpus, and is thus, as far as we know, the first large-scale experiment regarding word embedding interpretability on this language.

Intrusion Detection

End2End Acoustic to Semantic Transduction

no code implementations1 Feb 2021 Valentin Pelloin, Nathalie Camelin, Antoine Laurent, Renato de Mori, Antoine Caubrière, Yannick Estève, Sylvain Meignier

In this paper, we propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism.

Language Modelling Spoken Language Understanding

A Multimodal Educational Corpus of Oral Courses: Annotation, Analysis and Case Study

no code implementations LREC 2020 Salima Mdhaffar, Yannick Est{\`e}ve, Antoine Laurent, Hern, Nicolas ez, Richard Dufour, Delphine Charlet, Geraldine Damnati, Solen Quiniou, Nathalie Camelin

The use cases concern scientific fields from both speech and text processing, with language model adaptation, thematic segmentation and transcription to slide alignment.

Language Modelling

Des repr\'esentations continues de mots pour l'analyse d'opinions en arabe: une \'etude qualitative (Word embeddings for Arabic sentiment analysis : a qualitative study)

no code implementations JEPTALNRECITAL 2018 Amira Barhoumi, Nathalie Camelin, Yannick Est{\`e}ve

Ces derni{\`e}res ann{\'e}es, l{'}utilisation de l{'}apprentissage profond a am{\'e}lior{\'e} des performances de nombreux syst{\`e}mes automatiques dans une grande vari{\'e}t{\'e} de domaines (analyse d{'}images, reconnaissance de la parole, traduction automatique, .

Arabic Sentiment Analysis Word Embeddings

ASR error management for improving spoken language understanding

no code implementations26 May 2017 Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève, Renato de Mori

This paper addresses the problem of automatic speech recognition (ASR) error detection and their use for improving spoken language understanding (SLU) systems.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Des R\'eseaux de Neurones avec M\'ecanisme d'Attention pour la Compr\'ehension de la Parole (Exploring the use of Attention-Based Recurrent Neural Networks For Spoken Language Understanding )

no code implementations JEPTALNRECITAL 2016 Edwin Simonnet, Paul Del{\'e}glise, Nathalie Camelin, Yannick Est{\`e}ve

L{'}{\'e}tude porte sur l{'}apport d{'}un r{\'e}seau de neurones r{\'e}current (Recurrent Neural Network RNN) bidirectionnel encodeur/d{\'e}codeur avec m{\'e}canisme d{'}attention pour une t{\^a}che de compr{\'e}hension de la parole.

Spoken Language Understanding

Estimation de la qualit\'e d'un syst\`eme de reconnaissance de la parole pour une t\^ache de compr\'ehension (Quality estimation of a Speech Recognition System for a Spoken Language Understanding task)

no code implementations JEPTALNRECITAL 2016 Olivier Galibert, Nathalie Camelin, Paul Del{\'e}glise, Sophie Rosset

Nous comparons ici diff{\'e}rentes m{\'e}triques, notamment le WER, NE-WER et ATENE m{\'e}trique propos{\'e}e r{\'e}cemment pour l{'}{\'e}valuation des syst{\`e}mes de reconnaissance de la parole {\'e}tant donn{\'e} une t{\^a}che de reconnaissance d{'}entit{\'e}s nomm{\'e}es.

speech-recognition Speech Recognition +1

Segmentation et Titrage Automatique de Journaux T\'el\'evis\'es

no code implementations JEPTALNRECITAL 2015 Abdessalam Bouchekif, G{\'e}raldine Damnati, Nathalie Camelin, Yannick Est{\`e}ve, Delphine Charlet

Dans cet article, nous nous int{\'e}ressons au titrage automatique des segments issus de la segmentation th{\'e}matique de journaux t{\'e}l{\'e}vis{\'e}s. Nous proposons d{'}associer un segment {\`a} un article de presse {\'e}crite collect{\'e} le jour m{\^e}me de la diffusion du journal.

Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.