|  | Factorized RVQ-GAN For Disentangled Speech TokenizationSameer Khurana
                                                                ,
                                                                                                                                Dominik Klement
                                                                ,
                                                                                                                                Antoine Laurent
                                                                ,
                                                                                                                                Dominik Bobos
                                                                ,
                                                                                                                                Juraj Novosad
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-05233295
                                            v1
 | 
                                                                                
    |  | Optimizing Underwater Robot Navigation: A Study of DRL Algorithms and Multi-Modal Sensor FusionMd Ether Deowan
                                                                ,
                                                                                                                                Md Shamin Yeasher Yousha
                                                                ,
                                                                                                                                Tihan Mahmud Hossain
                                                                ,
                                                                                                                                Shahriar Hassan
                                                                ,
                                                                                                                                Ricard Marxer
 IEEE International Conference on Robotics & Automation (ICRA), May 2025, Atlanta, GA, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-05004039
                                            v1 | 
                                                                                
    |  | Aligning Multimodal Representations through an Information BottleneckAntonio Almudévar
                                                                ,
                                                                                                                                José Miguel Hernández-Lobato
                                                                ,
                                                                                                                                Sameer Khurana
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Alfonso OrtegaCommunication dans un congrès
                    
        
        
            
                
                    hal-05265540
                                            v1
 | 
                                                                                
    |  | SUCRe: Leveraging Scene Structure for Underwater Color RestorationClémentin Boittiaux
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Claire Dune
                                                                ,
                                                                                                                                Aurélien Arnaubec
                                                                ,
                                                                                                                                Maxime Ferrera
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-04613193
                                            v1
 | 
                                                                                
    |  | Scaling Properties of Speech Language ModelsSantiago Cuervo
                                                                ,
                                                                                                                                Ricard Marxer
 Proceedings of the 2024 Conference on Empirical Methods in Natural Language ProcessingCommunication dans un congrès
                    
        
        
            
                
                    hal-04832692
                                            v1, Nov 2024, Miami, United States. pp.351-361, ⟨10.18653/v1/2024.emnlp-main.21⟩ | 
                                                                                
    |  | Transfer Learning from Whisper for Microscopic Intelligibility PredictionPaul Best
                                                                ,
                                                                                                                                Santiago Cuervo
                                                                ,
                                                                                                                                Ricard MarxerCommunication dans un congrès
                    
        
        
            
                
                    hal-04683361
                                            v1
 | 
                                                                                
    |  | Investigating self-supervised speech models' ability to classify animal vocalizations: The case of gibbon's vocal signaturesJules Cauzinille
                                                                ,
                                                                                                                                Benoît Favre
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Dena Clink
                                                                ,
                                                                                                                                Abdul Hamid Ahmad
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-04693119
                                            v1
 | 
                                                                                
    |  | TalTech-IRIT-LIS Speaker and Language Diarization Systems for DISPLACE 2024Joonas Kalda
                                                                ,
                                                                                                                                Tanel Alumae
                                                                ,
                                                                                                                                Martin Lebourdais
                                                                ,
                                                                                                                                Hervé Bredin
                                                                ,
                                                                                                                                Séverin Baroudi
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-04683362
                                            v1
 | 
                                                                                
    |  | From speech to primate vocalizations: self-supervised deep learning as a comparative approachJules Cauzinille
                                                                ,
                                                                                                                                Benoît Favre
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Arnaud Rey
 Proceedings of the 15th International Conference on the Evolution of Language (EVOLANG XV)Communication dans un congrès
                    
        
        
            
                
                    hal-04608044
                                            v1, Gary Lupyan, May 2024, Madison, United States. pp.64, ⟨10.17617/2.3587960⟩ | 
                                                                                
    |  | PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker RecordingsJoonas Kalda
                                                                ,
                                                                                                                                Clément Pagés
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Tanel Alumäe
                                                                ,
                                                                                                                                Hervé Bredin
 The Speaker and Language Recognition Workshop (Odyssey 2024)Communication dans un congrès
                    
        
        
            
                
                    hal-04649858
                                            v1, Jun 2024, Quebec City, Canada. pp.115-122, ⟨10.21437/odyssey.2024-17⟩ | 
                                                                                
    |  | ToTaTo System Descriptions for the NOTSOFAR1 ChallengeJoonas Kalda
                                                                ,
                                                                                                                                Tanel Alumae
                                                                ,
                                                                                                                                Séverin Baroudi
                                                                ,
                                                                                                                                Martin Lebourdais
                                                                ,
                                                                                                                                Hervé Bredin
                                                                                            et al.
 8th International Workshop on Speech Processing in Everyday Environments (CHiME 2024)Communication dans un congrès
                    
        
        
            
                
                    hal-04936707
                                            v1, Sep 2024, Kos, Greece. pp.23-25, ⟨10.21437/CHiME.2024-5⟩ | 
                                                                                
    |  | Speech Foundation Models on Intelligibility Prediction for Hearing-Impaired ListenersSantiago Cuervo
                                                                ,
                                                                                                                                Ricard Marxer
 ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)Communication dans un congrès
                    
        
        
            
                
                    hal-04592508
                                            v1, Apr 2024, Seoul, South Korea. pp.1421-1425, ⟨10.1109/ICASSP48485.2024.10447907⟩ | 
                                                                                
    |  | On the Benefits of Self-supervised Learned Speech Representations for Predicting Human Phonetic MisperceptionsSantiago Cuervo
                                                                ,
                                                                                                                                Ricard MarxerCommunication dans un congrès
                    
        
        
            
                
                    hal-04194225
                                            v1
 | 
                                                                                
    |  | 1st Year of running MIR at UJIPedro Sanz
                                                                ,
                                                                                                                                Raúl Marín
                                                                ,
                                                                                                                                Salvador López-Barajas
                                                                ,
                                                                                                                                Alejandro Solis
                                                                ,
                                                                                                                                Ricard Marxer
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-04208111
                                            v1
 | 
                                                                                
    |  | Long-term visual localization in deep-sea underwater environmentClémentin Boittiaux
                                                                ,
                                                                                                                                Claire Dune
                                                                ,
                                                                                                                                Aurélien Arnaubec
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Maxime Ferrera
                                                                                            et al.
 ORASIS, Thanh Phuong Nguyen, May 2023, Carqueiranne, FranceCommunication dans un congrès
                    
        
        
            
                
                    hal-04108737
                                            v1 | 
                                                                                
    |  | Progress and Prospects for Spoken Language Technology: Results from Five Sexennial SurveysRoger K Moore
                                                                ,
                                                                                                                                Ricard MarxerCommunication dans un congrès
                    
        
        
            
                
                    hal-04194224
                                            v1
 | 
                                                                                
    |  | Blind Speech Separation Through Direction of Arrival Estimation Using Deep Neural Networks with a Flexibility on the Number of SpeakersMohammed Hafsati
                                                                ,
                                                                                                                                Kamil Bentounes
                                                                ,
                                                                                                                                Ricard MarxerCommunication dans un congrès
                    
        
        
            
                
                    hal-03948355
                                            v1
 | 
                                                                                
    |  | Contrastive Prediction Strategies for Unsupervised Segmentation and Categorization of Phonemes and WordsSantiago Cuervo
                                                                ,
                                                                                                                                Maciej Grabias
                                                                ,
                                                                                                                                Jan Chorowski
                                                                ,
                                                                                                                                Grzegorz Ciesielski
                                                                ,
                                                                                                                                Adrian Lancucki
                                                                                            et al.
 ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)Communication dans un congrès
                    
        
        
            
                
                    hal-03824772
                                            v1, May 2022, Singapore, Singapore. pp.3189-3193, ⟨10.1109/ICASSP43922.2022.9746102⟩ | 
                                                                                
    |  | Variable-rate hierarchical CPC leads to acoustic unit discovery in speechSantiago Cuervo
                                                                ,
                                                                                                                                Adrian Łańcucki
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Paweł Rychlikowski
                                                                ,
                                                                                                                                Jan Chorowski
 Advances in Neural Information Processing Systems 35 (NeurIPS 2022), Nov 2022, New Orleans, United States. pp.34995-35006Communication dans un congrès
                    
        
        
            
                
                    hal-04093636
                                            v1 | 
                                                                                
    |  | Aligned Contrastive Predictive CodingJan Chorowski
                                                                ,
                                                                                                                                Grzegorz Ciesielski
                                                                ,
                                                                                                                                Jarosław Dzikowski
                                                                ,
                                                                                                                                Adrian Łańcucki
                                                                ,
                                                                                                                                Ricard Marxer
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-03408618
                                            v1
 | 
                                                                                
    | 
                        
                     | Voice Restoration with Silent Speech Interfaces (ReSSInt)Inma Hernaez
                                                                ,
                                                                                                                                Jose Andrés González-López
                                                                ,
                                                                                                                                Eva Navas
                                                                ,
                                                                                                                                Jose Luis Pérez Córdoba
                                                                ,
                                                                                                                                Ibon Saratxaga
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-03599182
                                            v1
 | 
                                                                                
    |  | Marine and Maritime Intelligent Robotics (MIR)Ricard Marxer
                                                                ,
                                                                                                                                Vincent Hugel
                                                                ,
                                                                                                                                Kalliopi Pediaditi Prud'Homme
                                                                ,
                                                                                                                                Pedro Batista
                                                                ,
                                                                                                                                Jose Vicente Marti Aviles
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-03583552
                                            v1
 | 
                                                                                
    |  | Information Retrieval for ZeroSpeech 2021: The Submission by University of WroclawJan Chorowski
                                                                ,
                                                                                                                                Grzegorz Ciesielski
                                                                ,
                                                                                                                                Jarosław Dzikowski
                                                                ,
                                                                                                                                Adrian Łańcucki
                                                                ,
                                                                                                                                Ricard Marxer
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-03408592
                                            v1
 | 
                                                                                
    |  | Stereo to five-channels bombyx sonobuoys: from four years cetacean monitoring to real-time whale-ship anti-collision systemPaul Best
                                                                ,
                                                                                                                                Sebastian Marzetti
                                                                ,
                                                                                                                                Marion Poupard
                                                                ,
                                                                                                                                Maxence Ferrari
                                                                ,
                                                                                                                                Sébastien Paris
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-03230839
                                            v1
 | 
                                                                                
    |  | DOCC10: Open access dataset of marine mammal transient studies and end-to-end CNN classificationMaxence Ferrari
                                                                ,
                                                                                                                                Hervé Glotin
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Mark AschCommunication dans un congrès
                    
        
        
            
                
                    hal-02866091
                                            v1
 | 
                                                                                
    |  | Robust Training of Vector Quantized Bottleneck ModelsAdrian Łańcucki
                                                                ,
                                                                                                                                Jan Chorowski
                                                                ,
                                                                                                                                Guillaume Sanchez
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Nanxin Chen
                                                                                            et al.
 IJCNN 2020, Jul 2020, Glasgow, United KingdomCommunication dans un congrès
                    
        
        
            
                
                    hal-02912027
                                            v1 | 
                                                                                
    |  | Deep learning classification with noisy labelsGuillaume Sanchez
                                                                ,
                                                                                                                                Vincente Guis
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Frederic Bouchara
 ICME Workshop, Jul 2020, Londres, United KingdomCommunication dans un congrès
                    
        
        
            
                
                    hal-02552375
                                            v1 | 
                                                                                
    |  | 3D diarization of a sperm whale click cocktail party by an ultra high sampling rate portable hydrophone array for assessing individual cetacean growth curvesMaxence Ferrari
                                                                ,
                                                                                                                                Hervé Glotin
                                                                ,
                                                                                                                                Marina Oger
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Mark Asch
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-03230843
                                            v1
 | 
                                                                                
    |  | The "ScribbleLens" Dutch historical handwriting corpusHans J G A Dolfing
                                                                ,
                                                                                                                                Bellegarda Jérome
                                                                ,
                                                                                                                                Jan Chorowski
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Antoine Laurent
 International Conference on Frontiers of Handwriting Recognition (ICFHR), Sep 2020, Dortmund, GermanyCommunication dans un congrès
                    
        
        
            
                
                    hal-02877520
                                            v1 | 
                                                                                
    |  | End to end raw audio deep learning of transients, application to bioacousticsMaxence Ferrari
                                                                ,
                                                                                                                                Hervé Glotin
                                                                ,
                                                                                                                                Ricard MarxerCommunication dans un congrès
                    
        
        
            
                
                    hal-03230842
                                            v1
 | 
                                                                                
    |  | Deep Learning and Domain Transfer for Orca Vocalization DetectionPaul Best
                                                                ,
                                                                                                                                Maxence Ferrari
                                                                ,
                                                                                                                                Marion Poupard
                                                                ,
                                                                                                                                Sébastien Paris
                                                                ,
                                                                                                                                Ricard Marxer
                                                                                            et al.
 International joint conference on neural networks, Jul 2020, glasgow, United KingdomCommunication dans un congrès
                    
        
        
            
                
                    hal-02865300
                                            v1 | 
                                                                                
    |  | A Convolutional Deep Markov Model for Unsupervised Speech Representation LearningSameer Khurana
                                                                ,
                                                                                                                                Antoine Laurent
                                                                ,
                                                                                                                                Wei-Ning Hsu
                                                                ,
                                                                                                                                Jan Chorowski
                                                                ,
                                                                                                                                Adrian Łańcucki
                                                                                            et al.
 Interspeech 2020, Oct 2020, Shanghai, ChinaCommunication dans un congrès
                    
        
        
            
                
                    hal-02912029
                                            v1 | 
                                                                                
    |  | Wave Propagation in the Biosonar Organ of sperm whales using a Finite Difference Time Domain methodMaxence Ferrari
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Mark Asch
                                                                ,
                                                                                                                                Hervé Glotin
 VIHAR, Aug 2019, Lodon, United KingdomCommunication dans un congrès
                    
        
        
            
                
                    hal-02445408
                                            v1 | 
                                                                                
    |  | High-frequency Near-field Physeter macrocephalus Monitoring by Stereo-Autoencoder and 3D Model of Sonar OrganMaxence Ferrari
                                                                ,
                                                                                                                                Hervé Glotin
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Valentin Barchasz
                                                                ,
                                                                                                                                Véronique Sarano
                                                                                            et al.
 OCEANS 2019, Jun 2019, Marseille, FranceCommunication dans un congrès
                    
        
        
            
                
                    hal-02313898
                                            v1 | 
                                                                                
    |  | Unsupervised Neural Segmentation and Clustering for Unit Discovery in Sequential DataJan Chorowski
                                                                ,
                                                                                                                                Nanxin Chen
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Hans J G A Dolfing
                                                                ,
                                                                                                                                Adrian Łańcucki
                                                                                            et al.
 NeurIPS 2019 workshop - Perception as generative reasoning - Structure, Causality, Probability, Dec 2019, Vancouver, CanadaCommunication dans un congrès
                    
        
        
            
                
                    hal-02399138
                                            v1 | 
                                                                                
    |  | Efficient artifacts filter by density-based clustering in long term 3D whale passive acoustic monitoring with five hydrophones fixed under an Autonomous Surface VehicleMaxence Ferrari
                                                                ,
                                                                                                                                Marion Poupard
                                                                ,
                                                                                                                                Pascale Giraudet
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Jean-Marc Prévot
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-02313922
                                            v1
 | 
                                                                                
    |  | DNN Driven Speaker Independent Audio-Visual Mask Estimation for Speech SeparationMandar Gogate
                                                                ,
                                                                                                                                Ahsan Adeel
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Jon Barker
                                                                ,
                                                                                                                                Amir HussainCommunication dans un congrès
                    
        
        
            
                
                    hal-01868604
                                            v1
 | 
                                                                                
    |  | Binary Mask Estimation Strategies for Constrained Imputation-Based Speech EnhancementRicard Marxer
                                                                ,
                                                                                                                                Jon BarkerCommunication dans un congrès
                    
        
        
            
                
                    hal-04931722
                                            v1
 | 
                                                                                
    |  | Language Effects in Noise-Induced Word MisperceptionsMaria Luisa Garcia Lecumberri
                                                                ,
                                                                                                                                Jon Barker
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Martin CookeCommunication dans un congrès
                    
        
        
            
                
                    hal-04931724
                                            v1
 | 
                                                                                
    |  | Progress and Prospects for Spoken Language Technology: Results from Four Sexennial SurveysRoger Moore
                                                                ,
                                                                                                                                Ricard MarxerCommunication dans un congrès
                    
        
        
            
                
                    hal-04931727
                                            v1
 | 
                                                                                
    |  | CloudCAST — Remote Speech Technology for Speech ProfessionalsPhil Green
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Stuart Cunningham
                                                                ,
                                                                                                                                Heidi Christensen
                                                                ,
                                                                                                                                Frank Rudzicz
                                                                                            et al.Communication dans un congrès
                    
        
        
            
                
                    hal-04931723
                                            v1
 | 
                                                                                
    |  | The third ‘CHiME’ speech separation and recognition challenge: Dataset, task and baselinesJon Barker
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Emmanuel Vincent
                                                                ,
                                                                                                                                Shinji Watanabe
 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)Communication dans un congrès
                    
        
        
            
                
                    hal-04931731
                                            v1, Dec 2015, Scottsdale, France. pp.504-511, ⟨10.1109/ASRU.2015.7404837⟩ | 
                                                                                
    |  | Exploiting synchrony spectra and deep neural networks for noise-robust automatic speech recognitionNing Ma
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Jon Barker
                                                                ,
                                                                                                                                Guy Brown
 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)Communication dans un congrès
                    
        
        
            
                
                    hal-04931730
                                            v1, Dec 2015, Scottsdale, United States. pp.490-495, ⟨10.1109/ASRU.2015.7404835⟩ | 
                                                                                
    |  | The third `CHiME' Speech Separation and Recognition Challenge: Dataset, task and baselinesJon Barker
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Emmanuel Vincent
                                                                ,
                                                                                                                                Shinji Watanabe
 2015 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015), Dec 2015, Scottsdale, AZ, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-01211376
                                            v1 | 
                                                                                
    |  | A framework for the evaluation of microscopic intelligibility modelsRicard Marxer
                                                                ,
                                                                                                                                Martin Cooke
                                                                ,
                                                                                                                                Jon BarkerCommunication dans un congrès
                    
        
        
            
                
                    hal-04931738
                                            v1
 | 
                                                                                
    |  | Knowledge transfer between speakers for personalised dialogue managementIñigo Casanueva
                                                                ,
                                                                                                                                Thomas Hain
                                                                ,
                                                                                                                                Heidi Christensen
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Phil Green
 Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and DialogueCommunication dans un congrès
                    
        
        
            
                
                    hal-04931740
                                            v1, Sep 2015, Prague, Czech Republic. pp.12-21, ⟨10.18653/v1/W15-4603⟩ | 
                                                                                
    |  | A Tikhonov regularization method for spectrum decomposition in low latency audio source separationRicard Marxer
                                                                ,
                                                                                                                                Jordi Janer
 ICASSP 2012 - 2012 IEEE International Conference on Acoustics, Speech and Signal ProcessingCommunication dans un congrès
                    
        
        
            
                
                    hal-04931735
                                            v1, Mar 2012, Kyoto, Japan. pp.277-280, ⟨10.1109/ICASSP.2012.6287871⟩ | 
                                                                                
    |  | Combining a harmonic-based NMF decomposition with transient analysis for instantaneous percussion separationJordi Janer
                                                                ,
                                                                                                                                Ricard Marxer
                                                                ,
                                                                                                                                Keita Arimoto
 ICASSP 2012 - 2012 IEEE International Conference on Acoustics, Speech and Signal ProcessingCommunication dans un congrès
                    
        
        
            
                
                    hal-04931736
                                            v1, Mar 2012, Kyoto, Japan. pp.281-284, ⟨10.1109/ICASSP.2012.6287872⟩ |