Sahar Ghannay
Sahar Ghannay
Associate professor at Université Paris-Saclay, CNRS, LIMSI
Verified email at - Homepage
Cited by
Cited by
TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation
F Hernandez, V Nguyen, S Ghannay, N Tomashenko, Y Esteve
International conference on speech and computer, 198-208, 2018
Word embedding evaluation and combination
S Ghannay, B Favre, Y Esteve, N Camelin
Proceedings of the Tenth International Conference on Language Resources and …, 2016
End-to-end named entity and semantic concept extraction from speech
S Ghannay, A Caubrière, Y Estève, N Camelin, E Simonnet, A Laurent, ...
2018 IEEE Spoken Language Technology Workshop (SLT), 692-699, 2018
ASR error management for improving spoken language understanding
E Simonnet, S Ghannay, N Camelin, Y Estève, R De Mori
arXiv preprint arXiv:1705.09515, 2017
Simulating ASR errors for training SLU systems
E Simonnet, S Ghannay, N Camelin, Y Estève
Proceedings of the Eleventh International Conference on Language Resources …, 2018
Combining continuous word representation and prosodic features for asr error prediction
S Ghannay, Y Esteve, N Camelin, C Dutrey, F Santiago, M Adda-Decker
International Conference on Statistical Language and Speech Processing, 84-95, 2015
Word embeddings combination and neural networks for robustness in ASR error detection
S Ghannay, Y Estève, N Camelin
2015 European Signal Processing Conference (EUSIPCO 2015), Nice(France), 2015
Acoustic Word Embeddings for ASR Error Detection.
S Ghannay, Y Esteve, N Camelin, P Deléglise
INTERSPEECH, 1330-1334, 2016
End-to-end named entity extraction from speech
S Ghannay, A Caubriere, Y Esteve, A Laurent, E Morin
arXiv preprint arXiv:1805.12045, 2018
Evaluation of acoustic word embeddings
S Ghannay, Y Esteve, N Camelin, P Deleglise
1st Workshop on Evaluating Vector-Space Representations for NLP : RepEval …, 2016
Étude sur les représentations continues de mots appliquées à la détection automatique des erreurs de reconnaissance de la parole
S Ghannay
Le Mans, 2017
What is best for spoken language understanding: small but task-dependant embeddings or huge but out-of-domain embeddings?
S Ghannay, A Neuraz, S Rosset
ICASSP 2020-2020 IEEE international conference on acoustics, speech and …, 2020
Neural networks approaches focused on French spoken language understanding: application to the MEDIA evaluation task
S Ghannay, C Servan, S Rosset
Proceedings of the 28th International Conference on Computational …, 2020
A comparison of metric learning loss functions for end-to-end speaker verification
JM Coria, H Bredin, S Ghannay, S Rosset
International Conference on Statistical Language and Speech Processing, 137-148, 2020
Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation
JM Coria, H Bredin, S Ghannay, S Rosset
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2021
Evaluating the carbon footprint of NLP methods: a survey and analysis of existing tools
N Bannour, S Ghannay, A Névéol, AL Ligozat
EMNLP, Workshop SustaiNLP, 2021
Where are we in semantic concept extraction for Spoken Language Understanding?
S Ghannay, A Caubrière, S Mdhaffar, G Laperrière, B Jabaian, Y Estève
International Conference on Speech and Computer, 202-213, 2021
Lifelong learning and task-oriented dialogue system: what does it mean?
M Veron, S Ghannay, AL Ligozat, S Rosset
Increasing Naturalness and Flexibility in Spoken Dialogue Interaction, 347-356, 2021
LIMSI_UPV at SemEval-2020 Task 9: Recurrent convolutional neural network for code-mixed sentiment analysis
S Banerjee, S Ghannay, S Rosset, A Vilnat, P Rosso
arXiv preprint arXiv:2008.13173, 2020
A metric learning approach to misogyny categorization
JM Coria, S Ghannay, S Rosset, H Bredin
Workshop on Representation Learning for NLP, 89-94, 2020
The system can't perform the operation now. Try again later.
Articles 1–20