Publications

Laperrière G., Nguyen H., Ghannay S., Jabaian B., Estève Y. (2023). Semantic enrichment towards efficient speech representations. arXiv preprint arXiv:2307.01323.

Adjali Omar, Grimal Paul, Ferret Olivier, Ghannay Sahar, Le Borgne Hervé (2023). Explicit Knowledge Integration for Knowledge-Aware Visual Question Answering about Named Entities. Proceedings of the 2023 ACM International Conference on Multimedia Retrieval.

Laperrière G., Nguyen H., Ghannay S., Jabaian B., Estève Y. (2023). Specialized Semantic Enrichment of Speech Representations. 2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW).

Juan Manuel Coria, Herv{’e} Bredin, Sahar Ghannay, Sophie Rosset (2023). Continual self-supervised domain adaptation for end-to-end speaker diarization. 2022 IEEE Spoken Language Technology Workshop (SLT).

OralieCattan, Sahar Ghannay, Christophe Servan, Sophie Rosset (2022). Benchmarking Transformers-based models on French Spoken Language Understanding tasks. INTERSPEECH 2022.

Laperrière Gaëlle, Pelloin Valentin, Caubrière Antoine, Mdhaffar Salima, Camelin Nathalin, Ghannay Sahar, Jabaian Bassam, Estève Yannick (2022). The Spoken Language Understanding {MEDIA} Benchmark Dataset in the Era of Deep Learning: data updates, training and evaluation tools. Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC 2022).

Mdhaffar Salima, Pelloin Valentin, Caubrière Antoine, Laperrière Gaëlle, Ghannay Sahar, Jabaian Bassam, Camelin Nathalin, Estève Yannick (2022). Impact Analysis of the Use of Speech and Language Models Pretrained by Self-Supersivion for Spoken Language Understanding. Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC 2022).

Laperrière Gaëlle, Pelloin Valentin, Caubrière Antoine, Mdhaffar Salima, Camelin Nathalin, Ghannay Sahar, Jabaian Bassam, Estève Yannick (2022). Le benchmark MEDIA revisité : données, outils et évaluation dans un contexte d'apprentissage profond. I34e Journées d’Etudes sur la Parole (JEP2022) 2022.

OralieCattan, Sahar Ghannay, Christophe Servan, Sophie Rosset (2022). Étude comparative de modèles Transformers en compréhension de la parole en français. I34e Journées d’Etudes sur la Parole (JEP2022) 2022.

Juan Manuel Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset (2021). OVERLAP-AWARE LOW-LATENCY ONLINE SPEAKER DIARIZATION BASED ON END-TO-END LOCAL SEGMENTATION. IEEE Automatic Speech Recognition and Unserstanding Workshop (ASRU 2021).

PDF Slides

Nesrine Bannour, Sahar Ghannay, Aurélie Névéol, Anne-Laure Ligozat (2021). Evaluating the carbon footprint of NLP methods: a survey and analysis of existing tools. Association for Computational Linguistics, SustaiNLP 2021 workshop.

PDF Slides

Sahar Ghannay, Antoine Caubrière, Salima Mdhaffar, Gaëlle Laperrière, Bassam Jabaian, Yannick Estève (2021). Where Are We in Semantic Concept Extraction for Spoken Language Understanding?. International Conference on Speech and Computer SPECOM 2021.

PDF Slides

Sahar Ghannay, Christophe Servan, Sophie Rosset (2020). Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation Task. International Committee on Computational Linguistics (COLING) 2020.

PDF Slides

Coria Juan Manuel, Veron Mathilde, Ghannay Sahar, Bernard Guillaume, Bredin Hervé, Galibert Olivier, Rosset Sophie (2020). Analyzing BERT Cross-lingual Transfer Capabilities in Continual Sequence Labeling. First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models.

Sahar Ghannay, Antoine Neuraz, Sophie Rosset (2020). What is best for spoken language understanding: small but task-dependant embeddings or huge but out-of-domain embeddings?. CASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

PDF Slides

Antoine Caubrière, Sahar Ghannay, Nathalia Tomashenko, Renato De Mori, Emmanuel Morin, Yannick Estève (2020). Error Analysis Applied to End-to-End Spoken Language Understanding. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

PDF Slides

Juan Manuel Coria, Sahar Ghannay, Herv{’e} Bredin, Sophie Rosset (2020). A Metric Learning Approach to Misogyny Categorization. Proceedings of the 5th Workshop on Representation Learning for NLP (RepL4NLP-2020).

PDF Slides

Veron Mathilde, Penas Anselmo, Echegoyen Guillermo, Banerjee Somnath, Ghannay Sahar, Rosset Sophie (2020). A Cooking Knowledge Graph and Benchmark for Question Answering Evaluation in Lifelong Learning Scenarios. Natural Language Processing and Information Systems: 25th International Conference on Applications of Natural Language to Information Systems, NLDB 2020, Saarbr{“u}cken, Germany, June 24-26, 2020, Proceedings.

Juan Manuel Coria, Herv{’e} Bredin, Sahar Ghannay, Sophie Rosset (2020). A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification. arXiv preprint arXiv:2003.14021.

PDF

Sahar Ghannay, Yannick Estève, Nathalie Camelin (2020). A study of continuous space word and sentence representations applied to ASR error detection. Speech Communication Journal.

PDF

Mathilde Veron, Ghannay Sahar, Anne-Laure Ligozat, Sophie Rosset (2019). Lifelong learning and task-oriented dialogue system: what does it mean?. International Workshop on Spoken Dialogue Systems Technology.

PDF

Sahar Ghannay, Antoine Caubrière, Yannick Estève, Nathalie Camelin, Edwin Simonnet, Antoine Laurent, Emmanuel Morin (2018). End-to-end named entity and semantic concept extraction from speech. IEEE Spoken Language Technology Workshop.

PDF Poster

François Hernandez, Vincent Nguyen, Sahar Ghannay, Natalia Tomashenko, Yannick Estève (2018). TED-LIUM 3: Twice as Much Data and Corpus Repartition for Experiments on Speaker Adaptation. Speech and Computer: 20th International Conference, SPECOM 2018.

PDF

Sahar Ghannay, Yannick Estève, Nathalie Camelin (2018). Task Specific Sentence Embeddings for ASR Error Detection. Interspeech 2018.

PDF Poster

Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève (2018). Simulation d'erreurs de reconnaissance automatique dans un cadre de compréhension de la parole. XXXIIe Journ{’e}es d’Etudes sur la Parole (JEP 2018).

PDF

Sahar Ghannay, Yannick Estève, Nathalie Camelin (2018). Représentations de phrases dans un espace continu spécifiques à la tâche de détection d'erreurs. XXXIIe Journées d’Etudes sur la Parole (JEP 2018).

PDF

Sahar Ghannay, Antoine Caubrière, Yannick Estève, Antoine Laurent, Emmanuel Morin (2018). End-to-end named entity extraction from speech. arXiv preprint arXiv:1805.12045.

PDF

Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève (2018). Simulating ASR errors for training SLU systems. 11th edition of the Language Resources and Evaluation Conference (LREC 2018).

PDF Poster

Sahar Ghannay, Yannick Estève, Nathalie Camelin (2017). Enriching confusion networks for post-processing. Statistical Language and Speech Processing 2017.

PDF Slides

Ghannay Sahar (2017). A study of continuous word representations applied to the automatic detection of speech recognition errors. PHD theses.

PDF

Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève, Renato De Mori (2017). ASR Error Management for Improving Spoken Language Understanding. 18th Annual Conference of the International Speech (Interspeech 2017).

PDF Poster

Sahar Ghannay, Loïc Barrault (2017). Using Hypothesis Selection Based Features for Confusion Network MT System Combination. Third Workshop on Hybrid Approaches to Translation (HyTra), EACL 2014.

PDF Slides

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Paule Deléglise (2016). Acoustic word embeddings for ASR error detection. 17th Annual Conference of the International Speech (Interspeech 2016).

PDF Slides

Yannick Estève, Sahar Ghannay, Nathalie Camelin (2016). Recent improvements on error detection for automatic speech recognition. 1st International Workshop on Multimodal Media Data Analytics (MMDA 2016), in Conjunction with the 22nd European Conference on Artificial Intelligence.

PDF

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Paule Deléglise (2016). Evaluation of acoustic word embeddings. RepEval@ACL 2016: The 1st Workshop on Evaluating Vector-Space Representations for NLP.

PDF Poster

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Camille Dutrey, Fabian Santiago, Martine Adda-Decker (2016). Utilisation des représentations continues des mots et des paramètres prosodiques pour la détection d'erreurs dans les transcriptions automatiques de la parole. 31 ème Journées d’Ètudes sur la Parole.

PDF

Sahar Ghannay, Benoit Favre, Yannick Estève, Nathalie Camelin (2016). Word embedding evaluation and combination. 10th edition of the Language Resources and Evaluation Conference (LREC 2016).

PDF Poster

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Camille Dutrey, Fabian Santiago, Martine Adda-Decker (2015). Combining continous word representation and prosodic features for ASR error prediction. 3rd International Conference on Statistical Language and Speech Processing (SLSP 2015).

PDF Slides

Sahar Ghannay, Nathalie Camelin, Yannick Estève (2015). Which ASR errors are hard to detect?. Workshop Errors by Humans and Machines in multimedia, multimodal and multilingual data processing (ERRARE 2015).

PDF Slides

Sahar Ghannay, Yannick Estève, Nathalie Camelin (2015). Word embeddings combination and neural networks for robustness in ASR error detection. European Signal Processing Conference (EUSIPCO 2015).

PDF Slides