Publications
International conferences
Few-shot spoken language recognition under the TidyLang challenge
Yosra Jelassi, Raphaël Duroselle, Pierre Serrano, Jean-François Bonastre
Spoken Language Technology workshop, 2026
Segmentwise pruning in audio-language models
Marcel Gibier, Pierre Serrano, Olivier Boeffard, Raphaël Duroselle, Jean-François Bonastre
ICASSP, 2026
Data augmentations for audio deepfake detection for the ASVspoof5 closed condition
Raphaël Duroselle, Olivier Boeffard, Adrien Courtois, Hubert Nourtel, Champion Pierre, Heiko Agnoli, Jean-François Bonastre
The Automatic Speaker Verification Spoofing Countermeasures Workshop (ASVspoof 2024), 2024
Modeling and training strategies for language recognition systems
Raphaël Duroselle, Md Sahidullah, Denis Jouvet, Irina Illina
Interspeech, 2021
Language Recognition on Unknown Conditions: The LORIA-Inria-MULTISPEECH System for AP20-OLR Challenge
Raphaël Duroselle, Md Sahidullah, Denis Jouvet, Irina Illina
Interspeech, 2021
Unsupervised regularization of the embedding extractor for robust language identification
Raphaël Duroselle, Denis Jouvet, Irina Illina
Odyssey, The speaker and language recognition workshop, 2020
Metric learning loss functions to reduce domain mismatch in the x-vector space for language recognition
Raphaël Duroselle, Denis Jouvet, Irina Illina
Interspeech, 2020
National conferences
Identification de la langue par modélisation phonotactique de séquences en API
Murielle Iradukunda, Raphaël Duroselle, Clara Ponchard
Journées d'Études sur la Parole, 2026
Reconnaissance de la langue parlée explicable avec BA-LR
Yosra Jelassi, Raphaël Duroselle, Jean-François Bonastre
Journées d'Études sur la Parole, 2026
Evolution of BA-LR and application to explainable cross-domain speaker verification
Raphaël Duroselle, Yosra Jelassi, Jean-François Bonastre
Conference on Artificial Intelligence for Defence (CAID), 2025
Évaluation de la description automatique de scènes audio par la tâche d’Audio Question Answering
Marcel Gibier, Raphaël Duroselle, Pierre Serrano, Olivier Boëffard, Jean-François Bonastre
Actes de l'atelier Évaluation des modèles génératifs (LLM) et challenge 2025 (EvalLLM), 2025
Adaptation de domaine non supervisée pour la reconnaissance de la langue par régularisation d’un réseau de neurones
Raphaël Duroselle, Denis Jouvet, Irina Illina
Journées d'Études sur la Parole, 2020
Theses
Robustness of language recognition system to transmission channel
Raphaël Duroselle
Université de Lorraine, 2021
Preprints
Acoustic domain shift in spoken language identification from systematic domain generalization evaluation to real-world application
François Derrida, Raphaël Duroselle, Thomas Courtat, Jean-François Bonastre
arXiv preprint arXiv:2609.31759, 2026
Audio Question Answering with GRPO-Based Fine-Tuning and Calibrated Segment-Level Predictions
Marcel Gibier, Nolwenn Celton, Raphaël Duroselle, Pierre Serrano, Olivier Boeffard, Jean-François Bonastre
arXiv preprint arXiv:2511.14307, 2025
Improving Out-of-Domain Audio Deepfake Detection via Layer Selection and Fusion of SSL-Based Countermeasures
Pierre Serrano, Raphaël Duroselle, Florian Angulo, Jean-François Bonastre, Olivier Boeffard
arXiv preprint arXiv:2509.12003, 2025