Ricard Marxer
- DYNamiques de l’Information (DYNI)
- International Laboratory on Learning Systems (ILLS)
Publications
Publications
|
|
SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and EvaluationProceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 3: System Demonstrations), Mar 2026, Rabat, France. pp.320-340, ⟨10.18653/v1/2026.eacl-demo.23⟩ |
|
|
Factorized RVQ-GAN For Disentangled Speech TokenizationInterspeech 2025, Aug 2025, Rotterdam (NL), Netherlands. ⟨10.21437/Interspeech.2025-2612⟩ |
|
|
Optimizing Underwater Robot Navigation: A Study of DRL Algorithms and Multi-Modal Sensor FusionIEEE International Conference on Robotics & Automation (ICRA), May 2025, Atlanta, GA, United States |
|
|
Depth Jitter: Seeing Through the DepthOCEANS 2025 - Great Lakes, Sep 2025, Chicago, France. pp.1-7, ⟨10.23919/OCEANS59106.2025.11245179⟩ |
Aligning Multimodal Representations through an Information BottleneckInternational Conference on Machine Learning (ICML), Jul 2025, Vancouver, Canada. ⟨10.48550/arXiv.2506.04870⟩ |
|
|
|
Scaling Properties of Speech Language ModelsProceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Nov 2024, Miami, United States. pp.351-361, ⟨10.18653/v1/2024.emnlp-main.21⟩ |
|
|
SUCRe: Leveraging Scene Structure for Underwater Color Restoration2024 International Conference on 3D Vision (3DV), Mar 2024, Davos, Switzerland. pp.1488-1497, ⟨10.1109/3DV62453.2024.00148⟩ |
|
|
Investigating self-supervised speech models' ability to classify animal vocalizations: The case of gibbon's vocal signaturesInterspeech 2024, Sep 2024, Kos / Greece, Greece. pp.132-136, ⟨10.21437/Interspeech.2024-1096⟩ |
|
|
TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 202425th Interspeech Conference (Interspeech 2024), Sep 2024, Kos, Greece. pp.1635--1639, ⟨10.21437/interspeech.2024-2462⟩ |
|
|
Transfer Learning from Whisper for Microscopic Intelligibility PredictionInterspeech 2024, Sep 2024, Kos, Greece. pp.3839-3843, ⟨10.21437/Interspeech.2024-2258⟩ |
|
|
From speech to primate vocalizations: self-supervised deep learning as a comparative approachProceedings of the 15th International Conference on the Evolution of Language (EVOLANG XV), Gary Lupyan, May 2024, Madison, United States. pp.64, ⟨10.17617/2.3587960⟩ |
|
|
ToTaTo System Descriptions for the NOTSOFAR1 Challenge8th International Workshop on Speech Processing in Everyday Environments (CHiME 2024), Sep 2024, Kos, Greece. pp.23-25, ⟨10.21437/CHiME.2024-5⟩ |
|
|
Speech Foundation Models on Intelligibility Prediction for Hearing-Impaired ListenersICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2024, Seoul, South Korea. pp.1421-1425, ⟨10.1109/ICASSP48485.2024.10447907⟩ |
|
|
PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker RecordingsThe Speaker and Language Recognition Workshop (Odyssey 2024), Jun 2024, Quebec City, Canada. pp.115-122, ⟨10.21437/odyssey.2024-17⟩ |
|
|
On the Benefits of Self-supervised Learned Speech Representations for Predicting Human Phonetic MisperceptionsINTERSPEECH 2023, Aug 2023, Dublin, Ireland. pp.1788-1792, ⟨10.21437/Interspeech.2023-1476⟩ |
|
|
1st Year of running MIR at UJIOCEANS 2023 - Limerick, Jun 2023, Limerick, Ireland. pp.1-5, ⟨10.1109/OCEANSLimerick52467.2023.10244270⟩ |
|
|
Progress and Prospects for Spoken Language Technology: Results from Five Sexennial SurveysINTERSPEECH 2023, Aug 2023, Dublin, Ireland. pp.401-405, ⟨10.21437/Interspeech.2023-235⟩ |
|
|
Long-term visual localization in deep-sea underwater environmentORASIS, Thanh Phuong Nguyen, May 2023, Carqueiranne, France |
|
|
Blind Speech Separation Through Direction of Arrival Estimation Using Deep Neural Networks with a Flexibility on the Number of Speakers2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP), Sep 2022, Shanghai, China. pp.1-5, ⟨10.1109/MMSP55362.2022.9949050⟩ |
|
|
Contrastive Prediction Strategies for Unsupervised Segmentation and Categorization of Phonemes and WordsICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, Singapore, Singapore. pp.3189-3193, ⟨10.1109/ICASSP43922.2022.9746102⟩ |
|
|
Variable-rate hierarchical CPC leads to acoustic unit discovery in speechAdvances in Neural Information Processing Systems 35 (NeurIPS 2022), Nov 2022, New Orleans, United States. pp.34995-35006 |
|
|
Marine and Maritime Intelligent Robotics (MIR)OCEANS 2021: San Diego – Porto, Sep 2021, San Diego, United States. ⟨10.23919/OCEANS44145.2021.9706122⟩ |
|
|
Information Retrieval for ZeroSpeech 2021: The Submission by University of WroclawInterspeech 2021, Aug 2021, Brno, Czech Republic. pp.971-975, ⟨10.21437/Interspeech.2021-1465⟩ |
|
|
Aligned Contrastive Predictive CodingInterspeech 2021, Aug 2021, Brno, Czech Republic. pp.976-980, ⟨10.21437/interspeech.2021-1544⟩ |
|
|
Voice Restoration with Silent Speech Interfaces (ReSSInt)IberSPEECH 2021, May 2021, Valladolid, Spain. pp.130-134, ⟨10.21437/IberSPEECH.2021-28⟩ |
|
|
Deep learning classification with noisy labelsICME Workshop, Jul 2020, Londres, United Kingdom |
|
|
3D diarization of a sperm whale click cocktail party by an ultra high sampling rate portable hydrophone array for assessing individual cetacean growth curves.Forum Acusticum, Dec 2020, Lyon, France. pp.3239-3243, ⟨10.48465/fa.2020.1097⟩ |
|
|
Robust Training of Vector Quantized Bottleneck ModelsIJCNN 2020, Jul 2020, Glasgow, United Kingdom |
|
|
DOCC10: Open access dataset of marine mammal transient studies and end-to-end CNN classificationInternational Joint Conference on Neural Networks (IJCNN) 2020, Jul 2020, Glasgow, United Kingdom. pp.1-8, ⟨10.1109/IJCNN48605.2020.9207085⟩ |
The "ScribbleLens" Dutch historical handwriting corpusInternational Conference on Frontiers of Handwriting Recognition (ICFHR), Sep 2020, Dortmund, Germany |
|
|
|
End to end raw audio deep learning of clickse-Forum Acusticum 2020, Dec 2020, Lyon, France. pp.3245-3247, ⟨10.48465/fa.2020.1096⟩ |
|
|
Deep Learning and Domain Transfer for Orca Vocalization DetectionInternational joint conference on neural networks, Jul 2020, glasgow, United Kingdom |
|
|
A Convolutional Deep Markov Model for Unsupervised Speech Representation LearningInterspeech 2020, Oct 2020, Shanghai, China |
|
|
Stereo to five-channels bombyx sonobuoys: from four years cetacean monitoring to real-time whale-ship anti-collision systeme-Forum Acusticum 2020, Dec 2020, Lyon, France. pp.3229-3231, ⟨10.48465/fa.2020.1089⟩ |
|
|
High-frequency Near-field Physeter macrocephalus Monitoring by Stereo-Autoencoder and 3D Model of Sonar OrganOCEANS 2019, Jun 2019, Marseille, France |
|
|
Wave Propagation in the Biosonar Organ of sperm whales using a Finite Difference Time Domain methodVIHAR, Aug 2019, Lodon, United Kingdom |
|
|
Unsupervised Neural Segmentation and Clustering for Unit Discovery in Sequential DataNeurIPS 2019 workshop - Perception as generative reasoning - Structure, Causality, Probability, Dec 2019, Vancouver, Canada |
|
|
Efficient artifacts filter by density-based clustering in long term 3D whale passive acoustic monitoring with five hydrophones fixed under an Autonomous Surface VehicleOCEANS 2019, Jun 2019, Marseille, France. pp.39, ⟨10.1109/OCEANSE.2019.8867416⟩ |
|
|
DNN Driven Speaker Independent Audio-Visual Mask Estimation for Speech SeparationInterspeech 2018, Sep 2018, Hybderabad, India. pp.2723-2727, ⟨10.21437/Interspeech.2018-2516⟩ |
Binary Mask Estimation Strategies for Constrained Imputation-Based Speech EnhancementInterspeech 2017, Aug 2017, Stockholm, Sweden. pp.1988-1992, ⟨10.21437/Interspeech.2017-1257⟩ |
|
Language Effects in Noise-Induced Word MisperceptionsInterspeech 2016, Sep 2016, San Francisco, United States. pp.640-644, ⟨10.21437/Interspeech.2016-330⟩ |
|
Progress and Prospects for Spoken Language Technology: Results from Four Sexennial SurveysInterspeech 2016, Sep 2016, San Francisco, United States. pp.3012-3016, ⟨10.21437/Interspeech.2016-948⟩ |
|
CloudCAST — Remote Speech Technology for Speech ProfessionalsInterspeech 2016, Sep 2016, San Francisco, United States. pp.1608-1612, ⟨10.21437/Interspeech.2016-148⟩ |
|
Exploiting synchrony spectra and deep neural networks for noise-robust automatic speech recognition2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Dec 2015, Scottsdale, United States. pp.490-495, ⟨10.1109/ASRU.2015.7404835⟩ |
|
|
|
The third `CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselines2015 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015), Dec 2015, Scottsdale, AZ, United States |
Knowledge transfer between speakers for personalised dialogue managementProceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Sep 2015, Prague, Czech Republic. pp.12-21, ⟨10.18653/v1/W15-4603⟩ |
|
A framework for the evaluation of microscopic intelligibility modelsInterspeech 2015, Sep 2015, Dresden, Germany. pp.2558-2562, ⟨10.21437/Interspeech.2015-551⟩ |
|
The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselines2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Dec 2015, Scottsdale, France. pp.504-511, ⟨10.1109/ASRU.2015.7404837⟩ |
|
A Tikhonov regularization method for spectrum decomposition in low latency audio source separationICASSP 2012 - 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2012, Kyoto, Japan. pp.277-280, ⟨10.1109/ICASSP.2012.6287871⟩ |
|
Combining a harmonic-based NMF decomposition with transient analysis for instantaneous percussion separationICASSP 2012 - 2012 IEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2012, Kyoto, Japan. pp.281-284, ⟨10.1109/ICASSP.2012.6287872⟩ |
|
|
Underwater behaviour of Globicephala melasIBAC 2025, Sep 2025, Kerteminde, France |
|
|
Modeling the effect of the prenatal acoustic environment on early phonetic learningSociety for Research in Child Development Biennal Meeting, May 2025, Minneapolis (Minnesota), United States. |
|
|
Sperm whales ultra high frequency near field multichannel analysisThe 8th International Workshop on Detection, Classification, Localization, and Density Estimation (DCLDE), Jun 2018, Paris, France |
Low-Latency Instrument Separation in Polyphonic Audio Using Timbre ModelsLVA/ICA, 7191, Springer Berlin Heidelberg, pp.314-321, 2012, Lecture Notes in Computer Science, ⟨10.1007/978-3-642-28551-6_39⟩ |
Vocal Interactivity in-and-between Humans, Animals and RobotsInteraction Studies, 24 (1), 2023, ⟨10.1075/is.24.1⟩ |
Proceedings of the 3rd International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots (VIHAR 2021)2021, 978-2-9562029-2-9 |
|
Proceedings of the 2nd International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots (VIHAR 2019), 2019, 978-2-9562029-1-2 |
|
Proceedings of the 1st International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots (VIHAR 2017)2017, 978-2-9562029-0-5 |
|
|
The CHiME challenges: Robust speech recognition in everyday environmentsNew era for robust speech recognition - Exploiting deep learning, Springer, pp.327-344, 2017 |
|
|
Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization2026 |
|
|
Late Fusion and Multi-Level Fission Amplify Cross-Modal Transfer in Text-Speech LMs2025 |
|
|
Universal Audio GenerationLIUM - Laboratoire d'Informatique de l'Université du Mans. 2026 |