Search Results for author:
Found 22 papers, 0 papers with code
Are Embedding Spaces Interpretable? Results of an Intrusion Detection Evaluation on a Large French Corpus
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.
Impact Analysis of the Use of Speech and Language Models Pretrained by Self-Supersivion for Spoken Language Understanding
Pretrained models through self-supervised learning have been recently introduced for both acoustic and language modeling.
The Spoken Language Understanding MEDIA Benchmark Dataset in the Era of Deep Learning: data updates, training and evaluation tools
In this paper, we focus on the French MEDIA SLU dataset, distributed since 2005 and used as a benchmark dataset for a large number of research works.
ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks
We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed speech.
End2End Acoustic to Semantic Transduction
In this paper, we propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism.
Toward Qualitative Evaluation of Embeddings for Arabic Sentiment Analysis
This work presents a study that compares embeddings based on words and lemmas in SA frame.
A Multimodal Educational Corpus of Oral Courses: Annotation, Analysis and Case Study
The use cases concern scientific fields from both speech and text processing, with language model adaptation, thematic segmentation and transcription to slide alignment.
Plongements lexicaux sp\'ecifiques \`a la langue arabe : application \`a l'analyse d'opinions (Arabic-specific embedddings : application in Sentiment Analysis)
Nous nous int{\'e}ressons, dans cet article, {\`a} la t{\^a}che d{'}analyse d{'}opinions en arabe.
Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability
We present an end-to-end approach to extract semantic concepts directly from the speech audio signal.
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)
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, .
ASR error management for improving spoken language understanding
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
Utilisation des repr\'esentations continues des mots et des param\`etres prosodiques pour la d\'etection d'erreurs dans les transcriptions automatiques de la parole (Combining continuous word representation and prosodic features for ASR error detection)
Dans cet article, nous proposons d{'}{\'e}tudier leur utilisation dans une architecture neuronale pour la t{\^a}che de d{\'e}tection des erreurs au sein de transcriptions automatiques de la parole.
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 )
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.
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)
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.
Word Embedding Evaluation and Combination
Different approaches have been introduced to calculate word embeddings through neural networks.
Segmentation et Titrage Automatique de Journaux T\'el\'evis\'es
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.
Human annotation of ASR error regions: Is ``gravity'' a sharable concept for human annotators?
This paper is concerned with human assessments of the severity of errors in ASR outputs.
Leveraging study of robustness and portability of spoken language understanding systems across languages and domains: the PORTMEDIA corpora
The PORTMEDIA project is intended to develop new corpora for the evaluation of spoken language understanding systems.
