 
    Hervé Bredin
                                    111 
                                    
                            Documents
                                Publications
                    
                    
                    27
                
                            
                    
                    
                    20
                
                            
                    
                    
                    15
                
                            
                    
                    
                    12
                
                            
                    
                    
                    8
                
                            
                    
                    
                    8
                
                            
                    
                    
                    8
                
                            
                    
                    
                    8
                
                            
                    
                    
                    8
                
                            
                    
                    
                    7
                
                            
                    
                    
                    7
                
                            
                    
                    
                    7
                
                            
                    
                    
                    6
                
                            
                    
                    
                    6
                
                            
                    
                    
                    6
                
                            
                    
                    
                    6
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    3
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                            
                    
                    
                    2
                
                    
                    
                    
                    9
                
                            
                    
                    
                    6
                
                            
                    
                    
                    3
                
                            
                    
                    
                    2
                
                            
                    
                    
                    7
                
                            
                    
                    
                    3
                
                            
                    
                    
                    5
                
                            
                    
                    
                    7
                
                            
                    
                    
                    7
                
                            
                    
                    
                    7
                
                            
                    
                    
                    8
                
                            
                    
                    
                    4
                
                            
                    
                    
                    10
                
                            
                    
                    
                    3
                
                            
                    
                    
                    4
                
                            
                    
                    
                    4
                
                            
                    
                    
                    5
                
                            
                    
                    
                    10
                
                            
                    
                    
                    6
                
                            
                    
                    
                    1
                
                    
                    
                    
                    9
                
                            
                    
                    
                    6
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    5
                
                            
                    
                    
                    4
                
                            
                    
                    
                    3
                
                            
                    
                    
                    1
                
                            
                    
                    
                    1
                
                            
                    
                    
                    1
                
                            
                    
                    
                    1
                
                            
                    
                    
                    1
                
                            
                    
                    
                    1
                
                    
                    
                    
                    76
                
                            
                    
                    
                    18
                
                            
                    
                    
                    16
                
                            
                    
                    
                    9
                
                            
                    
                    
                    7
                
                            
                    
                    
                    4
                
                            
                    
                    
                    2
                
                            
                    
                    
                    1
                
                            
                    
                    
                    1
                
                            
                    
                    
                    1
                
                    Publications
|  | IRIT-MFU Multi-modal systems for emotion classification for Odyssey 2024 challengeOdyssey 2024: The Speaker and Language Recognition Workshop, Jun 2024, Québec, Canada. pp.296-302, ⟨10.21437/odyssey.2024-42⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04594287
                                            v1 | 
|  | Specializing Self-Supervised Speech Representations for Speaker SegmentationInterSpeech 2024, Sep 2024, Kos International Convention Center, Kos Island, France. pp.3769 - 3773, ⟨10.21437/interspeech.2024-962⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04969566
                                            v1 | 
|  | Premier système IRIT-MyFamillyUp pour la compétition sur la reconnaissance des émotions Odyssey 202435èmes Journées d'Études sur la Parole (JEP 2024) 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024) 26ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL 2024), Université Toulouse 3 Paul Sabatier; Université Toulouse Jean Jaurès, Jul 2024, Toulouse, France. pp.502-511Communication dans un congrès
                    
        
        
            
                
                    hal-04594251
                                            v1 | 
|  | Multi-latency look-ahead for streaming speaker segmentationInterspeech 2024, Sep 2024, Kos, Greece. pp.1610-1614, ⟨10.21437/Interspeech.2024-923⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04734819
                                            v1 | 
|  | 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⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04683362
                                            v1 | 
|  | On the calibration of powerset speaker diarization models25th Interspeech Conference (INTERSPEECH 2024), ISCA: International Speech Communication Association, Sep 2024, Kos, Greece. pp.3764--3768, ⟨10.21437/Interspeech.2024-1060⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04696316
                                            v1 | 
|  | gryannote open-source speaker diarization labeling toolInterspeech 2024, Sep 2024, Kos, GreeceCommunication dans un congrès
                    
        
        
            
                
                    hal-04734839
                                            v1 | 
|  | 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⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04649858
                                            v1 | 
|  | pyannote.audio 2.1 speaker diarization pipeline: principle, benchmark, and recipe24th INTERSPEECH Conference (INTERSPEECH 2023), Aug 2023, Dublin, Ireland. pp.1983-1987, ⟨10.21437/Interspeech.2023-105⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04247212
                                            v1 | 
|  | Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimationIEEE Automatic Speech Recognition and Understanding (ASRU 2023 ), IEEE, Dec 2023, Taipei, Taiwan. pp.1--7Communication dans un congrès
                    
        
        
            
                
                    hal-04247647
                                            v1 | 
|  | Powerset multi-class cross entropy loss for neural speaker diarization24th Interspeech Conference (INTERSPEECH 2023), ISCA: International Speech Communication Association, Aug 2023, Dublin, Ireland. pp.3222--3226, ⟨10.21437/Interspeech.2023-205⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04233796
                                            v1 | 
|  | BabySLM: language-acquisition-friendly benchmark of self-supervised spoken language modelsINTERSPEECH 2023, Aug 2023, Dublin, Ireland. pp.4588-4592, ⟨10.21437/Interspeech.2023-978⟩Communication dans un congrès
                    
        
        
            
                
                    hal-04247612
                                            v1 | 
|  | Continual self-supervised domain adaptation for end-to-end speaker diarizationIEEE Spoken Language Technology Workshop (SLT 2022), IEEE Speech and Language Processing Technical Committee, Jan 2023, Doha, Qatar. pp.626 - 632, ⟨10.1109/SLT54892.2023.10023195⟩Communication dans un congrès
                    
        
        
            
                
                    hal-03824546
                                            v1 | 
|  | Bazinga! A Dataset for Multi-Party Dialogues Structuring13th Conference on Language Resources and Evaluation (LREC 2022), European Language Resources Association (ELRA), Jun 2022, Marseille, France. pp.3434-3441Communication dans un congrès
                    
        
        
            
                
                    hal-03737453
                                            v1 | 
|  | Analyzing BERT Cross-lingual Transfer Capabilities in Continual Sequence LabelingFirst Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models, Oct 2022, virtual, South KoreaCommunication dans un congrès
                    
        
        
            
                
                    hal-03824597
                                            v1 | 
|  | Overlap-Aware Low-Latency Online Speaker Diarization Based on End-To-End Local SegmentationIEEE Automatic Speech Recognition and Unserstanding Workshop, Dec 2021, Cartagena, Colombia. pp.1139-1146, ⟨10.1109/ASRU51503.2021.9688044⟩Communication dans un congrès
                    
        
        
            
                
                    hal-03375330
                                            v1 | 
|  | End-to-end speaker segmentation for overlap-aware resegmentationInterspeech 2021, Aug 2021, Brno, Czech RepublicCommunication dans un congrès
                    
        
        
            
                
                    hal-03257524
                                            v1 | 
|  | An open-source voice type classifier for child-centered daylong recordingsInterspeech 2020 - Conference of the International Speech Communication Association, Oct 2020, Shanghai / Virtual, China. pp.3072-3076, ⟨10.21437/Interspeech.2020-1690⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02989487
                                            v1 | 
|  | A Metric Learning Approach to Misogyny CategorizationWorkshop on Representation Learning for NLP, Jul 2020, Online, France. pp.89-94, ⟨10.18653/v1/2020.repl4nlp-1.12⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02989293
                                            v1 | 
|  | Speaker detection in the wild: Lessons learned from JSALT 2019Odyssey 2020: The Speaker and Language Recognition Workshop, Nov 2020, Tokyo, Japan. pp.415-422, ⟨10.21437/Odyssey.2020-59⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02417632
                                            v1 | 
|  | Pyannote.audio: neural building blocks for speaker diarizationIEEE International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain. pp.7124-7128, ⟨10.1109/ICASSP40776.2020.9052974⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02995345
                                            v1 | 
|  | Overlap-aware diarization: Resegmentation using neural end-to-end overlapped speech detectionIEEE International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain. pp.7114-7118, ⟨10.1109/ICASSP40776.2020.9053096⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02995367
                                            v1 | 
|  | A Comparison of Metric Learning Loss Functions for End-To-End Speaker VerificationInternational Conference on Statistical Language and Speech Processing, Oct 2020, Cardiff, United Kingdom. pp.137-148, ⟨10.1007/978-3-030-59430-5_11⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02989334
                                            v1 | 
|  | End-to-end Domain-Adversarial Voice Activity DetectionInterspeech 2020, Nov 2020, Shanghai, China. pp.3685-3689, ⟨10.21437/Interspeech.2020-2285⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02989502
                                            v1 | 
|  | Hé Manu, tu descends ?": identification nommée du locuteur dans les dialoguesConférence en Recherche d'Information et Applications, Mar 2019, Lyon, France. ⟨10.24348/coria.2019.CORIA_2019_paper_14⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02333298
                                            v1 | 
|  | LSTM based Similarity Measurement with Spectral Clustering for Speaker DiarizationAnnual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria. pp.366-370, ⟨10.21437/Interspeech.2019-1388⟩Communication dans un congrès
                    
        
        
            
                
                    hal-02189393
                                            v1 | 
|  | Low-latency speaker spotting with online diarization and detectionOdyssey 2018: The Speaker and Language Recognition Workshop, ISCA, Jun 2018, Les Sables d'Olonne, France. ⟨10.21437/Odyssey.2018-20⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01836490
                                            v1 | 
| ODESSA at Albayzin Speaker Diarization Challenge 2018IberSPEECH 2018, Nov 2018, Barcelona, Spain. pp.211--215, ⟨10.21437/IberSPEECH.2018-43⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987808
                                            v1 | |
|  | Neural speech turn segmentation and affinity propagation for speaker diarizationAnnual Conference of the International Speech Communication Association, Sep 2018, Hyderabad, India. ⟨10.21437/Interspeech.2018-1750⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01912236
                                            v1 | 
|  | IRIM at TRECVID 2018: Instance SearchTRECVid workshop 2018, Nov 2018, Gaithersburg, Maryland, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-01919901
                                            v1 | 
| ODESSA/PLUMCOT at Albayzin Multimodal Diarization Challenge 2018IberSPEECH 2018, Nov 2018, Barcelona, Spain. pp.194--198, ⟨10.21437/IberSPEECH.2018-39⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987807
                                            v1 | |
| Pyannote.metrics: a toolkit for reproducible evaluation, diagnostic, and error analysis of speaker diarization systemsAnnual Conference of the International Speech Communication Association , Aug 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-411⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01836450
                                            v1 | |
|  | Combining Speaker Turn Embedding and Incremental Structure Prediction for Low-Latency Speaker DiarizationInterspeech 2017, 18th Annual Conference of the International Speech Communication Association, Aug 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-1067⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01690162
                                            v1 | 
|  | IRIM at TRECVID 2017: Instance SearchTRECVid workshop 2017, Nov 2017, Gaithersburg, Maryland, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-01834223
                                            v1 | 
| TristouNet: Triplet Loss for Speaker Turn EmbeddingIEEE International Conference on Acoustics, Speech, and Signal Processing, Mar 2017, New Orleans, United States. pp.5430-5434, ⟨10.1109/ICASSP.2017.7953194⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01830421
                                            v1 | |
|  | Towards large scale multimedia indexing: A case study on person discovery in broadcast newsContent-Based Multimedia Indexing CBMI, Jun 2017, Firenze, Italy. ⟨10.1145/3095713.3095732⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01551690
                                            v1 | 
|  | Speaker Change Detection in Broadcast TV Using Bidirectional Long Short-Term Memory NetworksInterspeech 2017, Aug 2017, Stockholm, Sweden. ⟨10.21437/Interspeech.2017-65⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01690244
                                            v1 | 
|  | Benchmarking Multimedia Technologies with the CAMOMILE Platform: the Case of Multimodal Person Discovery at MediaEval 2015LREC 2016, May 2016, Portorož, SloveniaCommunication dans un congrès
                    
        
        
            
                
                    hal-01690277
                                            v1 | 
| Improving Speaker Diarization of TV Series using Talking-Face Detection and ClusteringACM Multimedia 2016, ACM, Oct 2016, Amsterdam, Netherlands. pp.157-161, ⟨10.1145/2964284.2967202⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01836453
                                            v1 | |
| Post-Hoc Interactive Analytics of Errors in the Context of a Person Discovery TaskIEEE International Symposium on Multimedia 2016, IEEE Computer Society, Dec 2016, San Jose, United States. pp.435-438, ⟨10.1109/ISM.2016.0100⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01701954
                                            v1 | |
|  | Multimodal Person Discovery in Broadcast TV at MediaEval 2016MediaEval 2016, Oct 2016, Hilversum, NetherlandsCommunication dans un congrès
                    
        
        
            
                
                    hal-01690330
                                            v1 | 
|  | IRIM at TRECVID 2016: Instance SearchTRECVid workshop 2016, National Institute of Standards and Technology (NIST), Nov 2016, Gaithersburg, Maryland, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-01416953
                                            v1 | 
|  | The CAMOMILE Collaborative Annotation Platform for Multi-modal, Multi-lingual and Multi-media DocumentsLREC 2016 Conference, May 2016, Portoroz, Slovenia. pp.1421-1425Communication dans un congrès
                    
        
        
            
                
                    hal-01350096
                                            v1 | 
|  | Multimodal Person Discovery in Broadcast TV at MediaEval 2015MediaEval 2015, Sep 2015, Wurzen, GermanyCommunication dans un congrès
                    
        
        
            
                
                    hal-01690332
                                            v1 | 
|  | Collaborative Annotation for Person Identification in TV ShowsInterspeech 2015 (short demo paper), Sep 2015, Dresden, GermanyCommunication dans un congrès
                    
        
        
            
                
                    hal-01170513
                                            v1 | 
|  | Structured Prediction for Speaker Identification in TV SeriesAnnual Conference of the International Speech Communication Association, Jan 2015, Dresden, Germany. ⟨10.21437/Interspeech.2015-83⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01635001
                                            v1 | 
|  | What Makes a Speaker Recognizable in TV Broadcast? Going Beyond Speaker Identification Error RateERRARE Workshop, a satellite event of Interspeech 2015., 2015, Sinaia, RomaniaCommunication dans un congrès
                    
        
        
            
                
                    hal-01433205
                                            v1 | 
| A Visual Analytics Approach to Finding Factors Improving Automatic Speaker IdentificationsInternational Conference on Multimodal Interaction, Nov 2015, Seattle, United States. pp.323-326, ⟨10.1145/2818346.2820769⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01836455
                                            v1 | |
|  | LIMSI at MediaEval 2015: Person Discovery in Broadcast TV TaskMediaEval 2015, Sep 2015, Wurzen, GermanyCommunication dans un congrès
                    
        
        
            
                
                    hal-01690333
                                            v1 | 
| Sheldon speaking, bonjour!": Leveraging Multilingual Tracks for (Weakly) Supervised Speaker IdentificationACM MM 2014, 22nd ACM International Conference on Multimedia, Nov 2014, Orlando, United States. pp.137-146, ⟨10.1145/2647868.2654929⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987812
                                            v1 | |
|  | TVD: a reproducible and multiply aligned TV series dataset9th International Conference on Language Resources and Evaluation (LREC 2014), May 2014, Reykjavik, IcelandCommunication dans un congrès
                    
        
        
            
                
                    hal-01690279
                                            v1 | 
| LIMSI @ MediaEval SED 2014MediaEval 2014, Oct 2014, Barcelone, SpainCommunication dans un congrès
                    
        
        
            
                
                    hal-01744264
                                            v1 | |
| Collaborative Annotation of Multimedia ResourcesCDVE 2014, 11th International Conference on Cooperative Design, Visualization and Engineering, Sep 2014, Seattle, United States. pp.163--166, ⟨10.1007/978-3-319-10831-5_23⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987813
                                            v1 | |
| A Web-based Tool for the Visual Analysis of Media AnnotationsInternational Conference Information Visualisation, Jul 2014, Paris, France. ⟨10.1109/IV.2014.28⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01837151
                                            v1 | |
|  | Person Instance Graphs for Named Speaker Identification in TV BroadcastOdyssey 2014: The Speaker and Language Recognition Workshop, Jun 2014, Joensuu, Finland. pp.179-186, ⟨10.21437/Odyssey.2014-28⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01690272
                                            v1 | 
|  | QCompere @ REPERE 2013SLAM 2013 - First Workshop on Speech, Language and Audio for Multimedia, Aug 2013, Marseille, France. pp.49-54Communication dans un congrès
                    
        
        
            
                
                    hal-00949320
                                            v1 | 
|  | Integer Linear Programming for Speaker Diarization and Cross-Modal Identification in TV Broadcastthe 14rd Annual Conference of the International Speech Communication Association, INTERSPEECH, 2013, Lyon, France. pp.1467-1471, ⟨10.21437/Interspeech.2013-381⟩Communication dans un congrès
                    
        
        
            
                
                    hal-00953095
                                            v1 | 
|  | Towards a better integration of written names for unsupervised speakers identification in videosFirst Workshop on Speech, Language and Audio in Multimedia, SLAM, 2013, Marseille, France. pp.84-89Communication dans un congrès
                    
        
        
            
                
                    hal-00953089
                                            v1 | 
| Integer Linear Programming for Speaker Diarization and Cross-Modal Identification in TV Broadcastthe 14rd Annual Conference of the International Speech Communication Association, INTERSPEECH, 2013, Lyon, France. pp.x-xCommunication dans un congrès
                    
        
        
            
                
                    hal-00953777
                                            v1 | |
|  | Fusion of Speech, Faces and Text for Person Identification in TV BroadcastECCV 2012 - 12th European Conference on Computer Vision, Oct 2012, Firenze, Italy. pp.385-394, ⟨10.1007/978-3-642-33885-4_39⟩Communication dans un congrès
                    
        
        
            
                
                    hal-00722884
                                            v1 | 
|  | Unsupervised Speaker Identification using Overlaid Texts in TV BroadcastInterspeech 2012 - Conference of the International Speech Communication Association, Sep 2012, Portland, OR, United States. pp.2650-2653, ⟨10.21437/Interspeech.2012-344⟩Communication dans un congrès
                    
        
        
            
                
                    hal-00767427
                                            v1 | 
| Segmentation of TV Shows into Scenes using Speaker Diarization and Speech RecognitionICASSP 2012, IEEE International Conference on Acoustics, Speech, and Signal Processing, Mar 2012, Kyoto, Japan. pp.2377-2380, ⟨10.1109/ICASSP.2012.6288393⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987818
                                            v1 | |
|  | IRIM at TRECVID 2012: Semantic Indexing and Instance SearchTRECVID - TREC Video Retrieval Evaluation workshop, Nov 2012, Gaithersburg, MD, United States. 12pCommunication dans un congrès
                    
        
        
            
                
                    hal-00770258
                                            v1 | 
| Community-driven Hierarchical Fusion of Numerous Classifiers: Application to Video Semantic IndexingICASSP 2012, IEEE International Conference on Acoustics, Speech, and Signal Processing, Mar 2012, Kyoto, Japan. pp.2329-2332, ⟨10.1109/ICASSP.2012.6288381⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987817
                                            v1 | |
| Hierarchical Framework for Plot De-interlacing of TV Series based on Speakers, Dialogues and ImagesAMVA 2012, 1st ACM International Workshop on Audio and Multimedia Methods for Large-Scale Video Analysis at ACM Multimedia 2012, Nov 2012, Nara, Japan. pp.3-8, ⟨10.1145/2390214.2390218⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987815
                                            v1 | |
|  | Hierarchical Late Fusion for Concept Detection in VideosECCV 2012 - 12th European Conference on Computer Vision, Oct 2012, Firenze, Italy. pp.335-344, ⟨10.1007/978-3-642-33885-4_34⟩Communication dans un congrès
                    
        
        
            
                
                    hal-00732740
                                            v1 | 
| Toward Plot De-Interlacing in TV Series using Scenes Clustering10th Workshop on Content-Based Multimedia Indexing (CBMI 2012), 2012, Annecy, France. pp.1-6, ⟨10.1109/CBMI.2012.6269836⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987816
                                            v1 | |
| StoViz: Story Visualization of TV Series20th ACM International Conference on Multimedia (ACM MM 2012), ACM Special Interest Group on Multimedia, Oct 2012, Nara, Japan. pp.1329-1330, ⟨10.1145/2393347.2396468⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987814
                                            v1 | |
|  | Segmenting TV Series into Scenes using Speaker Diarization12th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS 2011), Delft University of Technology, Apr 2011, Delft, Netherlands. pp.1-4Communication dans un congrès
                    
        
        
            
                
                    hal-01987819
                                            v1 | 
|  | IRIM at TRECVID 2011: Semantic Indexing and Instance SearchTRECVID 2011 - TREC Video Retrieval Evaluation Online, Nov 2011, Gaithersburg, MD, United States. 12pCommunication dans un congrès
                    
        
        
            
                
                    hal-00677651
                                            v1 | 
|  | IRIM at TRECVID 2010: Semantic Indexing and Instance SearchTRECVID 2010 - TREC Video Retrieval Evaluation workshop, Nov 2010, Gaithersburg, MD, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-00591099
                                            v1 | 
|  | IRIT at TRECVID HLF 2009: Audio to the RescueTRECVid 2009, TREC Video Retrieval Evaluation Online Proceedings, 2010, Gaithersburg, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-01987820
                                            v1 | 
|  | IRIM at TRECVID2009: High Level Feature ExtractionTRECVID 2009 - TREC Video Retrieval Evaluation, Nov 2009, Gaithersburg, MD, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-00468199
                                            v1 | 
| IRIM at TRECVID 2010: High Level Feature Extraction and Instance SearchTREC Video Retrieval Evaluation workshop, 2010, Gaithersburg, MD, United StatesCommunication dans un congrès
                    
        
        
            
                
                    hal-00953839
                                            v1 | |
| An Interactive and Multi-Level Framework for Summarising User-Generated VideosACM MM 2009, 17th ACM International Conference on Multimedia, 2009, New York, United States. pp.685--688, ⟨10.1145/1631272.1631388⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987821
                                            v1 | |
| IRIT @ TRECVid HLF 2009 Audio to the RescueTREC Video Retrieval Workshop, 2009, Unknown, Unknown RegionCommunication dans un congrès
                    
        
        
            
                
                    hal-01433917
                                            v1 | |
|  | Rushes Video Summarization using a Collaborative ApproachTRECVID 2008, ACM International Conference on Multimedia Information Retrieval, Oct 2008, Vancouver, Canada. pp.90-94, ⟨10.1145/1463563.1463579⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987824
                                            v1 | 
| Some results from the biosecure talking face evaluation campaignIEEE International Conference on Acoustics, Speech and Signal Processing, Mar 2008, Las Vegas, United States. ⟨10.1109/ICASSP.2008.4518565⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01315412
                                            v1 | |
| A Collaborative Approach to Video SummarizationSAMT 2008, 3rd International Conference on Semantic and Digital Media Technologies, 2008, Koblenz, GermanyCommunication dans un congrès
                    
        
        
            
                
                    hal-01987822
                                            v1 | |
| Making Talking-Face Authentication Robust to Deliberate ImpostureICASSP 2008, IEEE International Conference on Acoustics, Speech, and Signal Processing, Mar 2008, Las Vegas, United States. pp.1693-1696, ⟨10.1109/ICASSP.2008.4517954⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987825
                                            v1 | |
| Dublin City University at TRECVid 2008 BBC Rushes Summarisation TaskTRECVID 2008, ACM International Conference on Multimedia Information Retrieval 2008, Oct 2008, Vancouver, Canada. pp.45-49, ⟨10.1145/1463563.1463570⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987823
                                            v1 | |
| Audio-Visual Speech Synchrony Measure for Talking-Face Identity VerificationICASSP 2007, IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2007, Honolulu, United States. ⟨10.1109/ICASSP.2007.366215⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987829
                                            v1 | |
| Biometrics and Forensic Sciences: the Same Quest for Identification?2007 International Crime Science Conference, 2007, London, United KingdomCommunication dans un congrès
                    
        
        
            
                
                    hal-01987826
                                            v1 | |
| Vérification Audiovisuelle de l'IdentitéTraitement et Analyse de l'Information : Méthodes et Applications, 2007, Hammamet, TunisieCommunication dans un congrès
                    
        
        
            
                
                    hal-01987828
                                            v1 | |
| Aliveness Detection using Coupled Hidden Markov Models1st Spanish Workshop on Biometrics, 2007, Girona, SpainCommunication dans un congrès
                    
        
        
            
                
                    hal-01987827
                                            v1 | |
| Reconnaissance Audiovisuelle de la Parole par VMikeJEP 2006, Journées d'Etudes sur la Parole, 2006, Dinard, FranceCommunication dans un congrès
                    
        
        
            
                
                    hal-01987832
                                            v1 | |
| GMM-based SVM for Face RecognitionICPR 2006, IAPR International Conference on Pattern Recognition, Aug 2006, Hong-Kong, Hong Kong SAR China. pp.1111-1114, ⟨10.1109/ICPR.2006.611⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987831
                                            v1 | |
| The BioSecure Talking-Face Reference SystemMMUA 2006, Workshop on Multimodal User Authentication, 2006, Toulouse, FranceCommunication dans un congrès
                    
        
        
            
                
                    hal-01987833
                                            v1 | |
| Measuring Audio and Visual Speech Synchrony: Methods and ApplicationsVIE 2006, IEE International Conference on Visual Information Engineering, 2006, Bangalore, IndiaCommunication dans un congrès
                    
        
        
            
                
                    hal-01987830
                                            v1 | |
| Multi-Modal Biometric Authentication on the SecurePhone PDAMMUA 2006, Workshop on Multimodal User Authentication, 2006, Toulouse, FranceCommunication dans un congrès
                    
        
        
            
                
                    hal-01987834
                                            v1 | |
| Detecting Replay Attacks in Audiovisual Identity VerificationICASSP 2006, IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2006, Toulouse, France. ⟨10.1109/ICASSP.2006.1660097⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987835
                                            v1 | |
| Adapting a High Quality Audiovisual Database to PDA QualityISISPA 2005, International Symposium on Image and Signal Processing and Analysis, Sep 2005, Zaghreb, Croatia. pp.262-267, ⟨10.1109/ISPA.2005.195420⟩Communication dans un congrès
                    
        
        
            
                
                    hal-01987836
                                            v1 | 
| Hierarchical Late Fusion for Concept Detection in VideosFusion in Computer Vision: Understanding Complex Visual Content, Springer international publishing, pp.53-78, 2014, ⟨10.1007/978-3-319-05696-8_3⟩Chapitre d'ouvrage
                    
        
        
            
                
                    hal-00981688
                                            v1 | |
| Talking-Face AuthenticationDijana Petrovska and Gérard Chollet. Guide to Biometric Reference Systems and Performance Evaluation, Springer Verlag, 2009Chapitre d'ouvrage
                    
        
        
            
                
                    hal-01987799
                                            v1 | |
|  | Audio-Visual Identity Verification: an Introductory OverviewYannis Stylianou. Progress in Nonlinear Speech Processing, 4391, Springer Verlag, pp.118-134, 2007, 978-3-540-71503-0. ⟨10.1007/978-3-540-71505-4_8⟩Chapitre d'ouvrage
                    
        
        
            
                
                    hal-01987800
                                            v1 | 
| Some Experiments in Audio-Visual Speech ProcessingMohamed Chetouani. Non-Linear Speech Processing, Springer Verlag, 2007, ⟨10.1007/978-3-540-77347-4_2⟩Chapitre d'ouvrage
                    
        
        
            
                
                    hal-01987801
                                            v1 | 
|  | Statistical learning models of early phonetic acquisition struggle with child-centered audio data2023Pré-publication, Document de travail
                    
        
        
            
                
                    hal-03992297
                                            v1 | 
|  | The Speed Submission to DIHARD II: Contributions & Lessons Learned2019Pré-publication, Document de travail
                    
        
        
            
                
                    hal-02352840
                                            v2 | 
|  | pyannote.audio speaker diarization pipeline at VoxSRC 2023IRIT - Institut de Recherche en Informatique de Toulouse. 2023Rapport
                             (rapport technique)
                    
        
        
            
                
                    hal-04969548
                                            v1 | 
|  | Vérification de l'identité d'un visage parlant. Apport de la mesure de synchronie audiovisuelle face aux tentatives délibérées d'imposturedomain_other. Télécom ParisTech, 2007. English. ⟨NNT : ⟩Thèse
                    
        
        
            
                
                    pastel-00003123
                                            v1 | 
|  | Vérification de l'identité d'un visage parlant. Apport de la mesure de synchronie audiovisuelle face aux tentatives délibérées d'imposture.Traitement du signal et de l'image [eess.SP]. Ecole nationale supérieure des telecommunications - ENST, 2007. Français. ⟨NNT : ⟩Thèse
                    
        
        
            
                
                    tel-00265505
                                            v1 | 
                Chargement...
            
            Chargement...