georges linares
CV Georges Linares
53
Documents
Présentation
Georges Linarès est enseignant-chercheur à l'Université d'Avignon depuis 1999 et professeur depuis 2011. Ses activités de recherche portent sur le traitement automatique de la parole, la recherche d'information multimédia, le traitement automatique du langage natureI. Il coordonne, avec Jonathan Grainger, l'axe *Neurocomputation and Language processing* du Labex BLRI. Il a dirigé, de 2010 à fin 2015, le laboratoire informatique d'Avignon. Il a ensuite été vice-président à la Recherche de l'Université d'Avignon jusqu'en décembre 2023. Il a été élu à la présidence d'Avignon Université en décembre 2023.
<a name="pres" style="font-family: 'Times New Roman'; font-size: medium;"></a>
### CV
<a name="pres" style="font-family: 'Times New Roman'; font-size: medium;"></a>1994 : Bachelor of Mathematics (University of Toulon)
1995 : Master of Mathematics and Computer Science (University of Marseille-Luminy).
1998 : Phd in Computer Science, "Model Breaking detection in Impulsive environments". (P. Nocéra, H. Méloni).
1999 : Assistant professor, LIA, University of Avignon.
2009 : HDR, "Speech recognition and audio indexing", (Habilitation à diriger les recherches), University of Avignon
2011 : Full Professor, LIA, University of Avignon.
---
<a name="resp" style="font-family: 'Times New Roman'; font-size: medium;"></a>
### Mandates & responsabilities
12/2023 - : Président of Avignon University
2016- 2023: Vice président for Research, Avignon University
2010 : Head of the LIA (Computer Science Laboratory of Avignon's University).
2010 : Deputy director of the [CERI](http://ceri.univ-avignon.fr) (Centre for Teaching and Research in Computer Sciences)
2011-2014 : Member of the managment council of the research federation [Agorantic](http://blogs.univ-avignon.fr/sfr-agorantic/) track *Social and cultural Networks*
2012 : Member of the Scientific council of Avignon's University
2012 : Member of the Management council of the [Brain and Language Research Institute](http://www.blri.fr), responsible of the track *NeuroComputation and language processing*.
---
<a name="topics" style="font-family: 'Times New Roman'; font-size: medium;"></a>
### Research Topics
<a name="topics" style="font-family: 'Times New Roman'; font-size: medium;"></a>
- Speech Processing
- Machine Learning for NLP
- Audio-video indexing
---
### Projects
- [GAFES (ANR 2014-2018) : Gallerie des Festivals, Web content analysis, the Web as cultural media, video Re-purposing ](http://rpm2.org)
Partners: Centre Norbert Elias, Eurecom, Syllabs \[Project Leader\]
- [CONTNOMINA (ANR Blanc 2013-2016) : Speech recognition system contextualisation ](http://rpm2.org)
Partners: LIA, LORIA \[Leader for the LIA\]
- [CONGAS (STREP EU 2012-2014) : COmplex Networks and GAmeS theory ](http://rpm2.org)
Partners: LIA, INRIA, Delft (Nederland), Imperial College (UK), Univ. of Pisa (Italy), Technion (Israel) \[Participant\]
- [RPM2 (ANR CONTINT 2008-2011) : Summarization of Multimedia documents ](http://rpm2.org)
Partners: LIA, Wikio, Sinequa, Syllabs, Eurecom \[Leader for the LIA\]
- [AVI-SON (ANR CONTINT 2008-2011) : Archiving and Indexing large video database by content extraction and analysis ](http://avison.univ-avignon.fr/)
Partners: LIA, IRCAD, Xtensive Technology \[Project leader\]
- [EPAC (ANR MDCA 2006-2010) : spontaneous speech transcription ](http://projet-epac.univ-lemans.fr/doku.php?id=accueil)
Partners: IRIT, LIUM,LI \[Participant\]
- [Decoda (ANR CONTINT 2010-2012) : analysis of spoken dialogues from call centers ](http://decoda.univ-avignon.fr/)
Partners: LIF, RATP, Sonear \[Participant\]
- [ASH (ANR BLANC 2010-2012) : speech recognition system harnessing ](http://projet-ash.univ-lemans.fr/doku.php)
Partners: LIA, LIUM, IRISA \[Leader for the LIA\]
- [Sumacc (ANR CONTINT 2011-2013) : concept discovering, modelling and tracking in multimedia web collections](http://sumacc.univ-avignon.fr/)
Partners: LIA, Eurecom, Wikio, Syllabs \[Project leader\]
- PERCOL (Defi ANR CONTINT 2011-2013) : Person identification on audiovisual streams
Partners: LIF, LIA, Univ. Lille, Orange Lab \[Participant\]
Compétences
Publications
- 53
- 34
- 13
- 9
- 9
- 9
- 7
- 6
- 5
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 51
- 3
- 1
- 1
- 1
- 1
- 1
- 1
- 2
- 2
- 5
- 7
- 8
- 15
- 10
- 1
- 1
- 1
- 1
- 1
|
WAC: A Corpus of Wikipedia Conversations for Online Abuse Detection12th International Conference on Language Resources and Evaluation (LREC), May 2020, Marseille, France. pp.1375-1383
Communication dans un congrès
hal-02497514v1
|
|
Tuning Graph2vec with Node Labels for Abuse Detection in Online Conversations11ème Conférence Modèles & Analyse de Réseaux : approches mathématiques et informatiques (MARAMI), Oct 2020, Montpellier, France
Communication dans un congrès
hal-02993571v1
|
|
Abusive Language Detection in Online Conversations by Combining Content- and Graph-based FeaturesICWSM International Workshop on Modeling and Mining Social-Media-Driven Complex Networks, Jun 2019, Munich, Germany. pp.8
Communication dans un congrès
hal-02130205v1
|
|
Impact Of Content Features For Automatic Online Abuse DetectionInternational Conference on Computational Linguistics and Intelligent Text Processing (CICLing), Apr 2017, Budapest, Hungary. pp.404-419, ⟨10.1007/978-3-319-77116-8_30⟩
Communication dans un congrès
hal-01505502v1
|
|
Détection de messages abusifs au moyen de réseaux conversationnels8ème Conférence Modèles et Analyse des Réseaux : Approches Mathématiques et Informatiques (MARAMI), Oct 2017, La Rochelle, France
Communication dans un congrès
hal-01614279v1
|
|
Graph-based Features for Automatic Online Abuse Detection5th International Conference on Statistical Language and Speech Processing (SLSP), Oct 2017, Le Mans, France. pp.70-81, ⟨10.1007/978-3-319-68456-7_6⟩
Communication dans un congrès
hal-01571639v1
|
|
Detection of abusive messages in an on-line community14ème Conférence en Recherche d'Information et Applications (CORIA), Mar 2017, Marseille, France. pp.153-168, ⟨10.24348/coria.2017.16⟩
Communication dans un congrès
hal-01505017v1
|
Quaternion Neural Networks for Spoken Language Understanding2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.362-368
Communication dans un congrès
hal-02107532v1
|
|
Deep Stacked Autoencoders for Spoken Language UnderstandingInterspeech 2016, Sep 2016, San Francisco, United States. pp.720-724, ⟨10.21437/Interspeech.2016-63⟩
Communication dans un congrès
hal-02356395v1
|
|
Parallel Long Short-Term Memory for multi-stream classification2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.218-223, ⟨10.1109/SLT.2016.7846268⟩
Communication dans un congrès
hal-02356410v1
|
|
Improving multi-stream classification by mapping sequence-embedding in a high dimensional space2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.224-231, ⟨10.1109/SLT.2016.7846269⟩
Communication dans un congrès
hal-02356420v1
|
|
|
Spoken Language Understanding in a Latent Topic-based SubspaceInterspeech 2016, Sep 2016, San Francisco, United States. ⟨10.21437/Interspeech.2016-50⟩
Communication dans un congrès
hal-02356390v1
|
A log-linear weighting approach in the Word2vec space for spoken language understanding2016 IEEE Spoken Language Technology Workshop (SLT), Dec 2016, San Diego, United States. pp.356-361, ⟨10.1109/SLT.2016.7846289⟩
Communication dans un congrès
hal-02356406v1
|
|
Identification de personnes dans des flux multimédiaCORIA 2015 - Conférence en Recherche d'Infomations et Applications - 12th French Information Retrieval Conference, Mar 2015, PARIS, France. pp.239-251
Communication dans un congrès
hal-01194234v1
|
|
Topic-space based setup of a neural network for theme identification of highly imperfect transcriptions2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) , Dec 2015, Scottsdale, United States. ⟨10.1109/ASRU.2015.7404815⟩
Communication dans un congrès
hal-01339956v1
|
|
Integration of word and semantic features for theme identification in telephone conversations6th International Workshop on Spoken Dialog Systems (IWSDS 2015), 2015, Busan, South Korea
Communication dans un congrès
hal-01433213v1
|
|
Latent Topic Model Based Representations for a Robust Theme Identification of Highly Imperfect Automatic Transcriptions16th International Conference, CICLing 2015, Apr 2015, Le Caire, Egypt. ⟨10.1007/978-3-319-18117-2_44⟩
Communication dans un congrès
hal-01293908v1
|
|
Improving dialogue classification using a topic space representation and a Gaussian classifier based on the decision ruleIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2014, Florence, Italy. ⟨10.1109/ICASSP.2014.6853571⟩
Communication dans un congrès
hal-01318674v1
|
|
Classification de transcriptions automatiques imparfaites : Doit-on adapter le calcul du taux d'erreur-mot ?JEP, Jun 2014, Le Mans, France
Communication dans un congrès
hal-01319782v1
|
|
Author-topic based representation of call-center conversations IEEE Spoken Language Technology Workshop (SLT) , Dec 2014, South Lake Tahoe United States. ⟨10.1109/SLT.2014.7078577⟩
Communication dans un congrès
hal-01318662v1
|
|
Modèles contextuels continus pour la reconnaissance des noms de personnes dans des transcriptions automatiquesJEP 2014, Jun 2014, Le Mans, France
Communication dans un congrès
hal-02356488v1
|
|
Sumacc Project's Corpus: A Topic-based Query Extention Approach to Retrieve Multimedia Documents17th International Conference, TSD, Sep 2014, Brno, Czech Republic
Communication dans un congrès
hal-01319787v1
|
|
An I-vector Based Approach to Compact Multi-Granularity Topic Spaces Representation of Textual Documentsthe 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP),, Oct 2014, Doha, Qatar. ⟨10.3115/v1/D14-1051⟩
Communication dans un congrès
hal-01318651v1
|
|
Theme Identification in Human-Human Conversations with Features from Specific Speaker Type Hidden SpacesINTERSPEECH, May 2014, Singapore, Singapore
Communication dans un congrès
hal-01318666v1
|
|
Characterizing and Predicting Bursty Events: The Buzz Case Study on TwitterLREC, May 2014, Reykjavik, Iceland
Communication dans un congrès
hal-01319806v1
|
|
A COMBINED THEMATIC AND ACOUSTIC APPROACH FOR A MUSIC RECOMMENDATION SERVICE IN TV COMMERCIALS ISMIR, Oct 2014, Tapei, Taiwan
Communication dans un congrès
hal-01319769v1
|
|
I-vector based Representation of Highly Imperfect Automatic TranscriptionsINTERSPEECH, May 2014, Singapore, Singapore
Communication dans un congrès
hal-01318657v1
|
|
Factor Analysis based Semantic Variability Compensation for Automatic Conversation RepresentationInterspeech, May 2014, Singapore, Singapore
Communication dans un congrès
hal-01313121v1
|
|
Multimodal understanding for person recognition in video broadcastsInterspeech, Singapore, 2014, Unknown, Unknown Region
Communication dans un congrès
hal-01194244v1
|
|
Subspace Gaussian Mixture Models for Dialogues ClassificationInterspeech, May 2014, Singapore, Singapore
Communication dans un congrès
hal-01313132v1
|
|
A LDA-Based Topic Classification Approach from Highly Imperfect Automatic TranscriptionsLREC, May 2014, Reykjavik, Iceland
Communication dans un congrès
hal-01319771v1
|
|
Person name spotting by combining acoustic matching and LDA topic modelsInterspeech 2013, Aug 2013, Lyon, France
Communication dans un congrès
hal-01340026v1
|
|
Person name recognition in ASR outputs using continuous context modelsIEEE International Conference on Acoustics, Speech and Signal Processing , May 2013, Vancouver, Canada. ⟨10.1109/ICASSP.2013.6639318⟩
Communication dans un congrès
hal-01314411v1
|
|
PERCOLI: a person identification system for the 2013 REPERE challengeSLAM 2013 : First Workshop on Speech, Language and Audio in Multimedia, Aug 2013, Marseille, France. pp.55-60
Communication dans un congrès
hal-00834204v1
|
|
LIA @ MediaEval 2013 Spoken Web Search Task: An I-Vector based ApproachMediaEval, Oct 2013, Barcelone, Spain
Communication dans un congrès
hal-01313144v1
|
|
Event detection from image hosting services by slightly-supervised multi-span context models2013 11TH INTERNATIONAL WORKSHOP ON CONTENT-BASED MULTIMEDIA INDEXING (CBMI), Jun 2013, VESZPREM,, Hungary. ⟨10.1109/CBMI.2013.6576563⟩
Communication dans un congrès
hal-01318645v1
|
|
Thematic Representation of Short Text Messages with Latent Topics: Application in the Twitter contextPACLING 2013, Sep 2013, Tokyo, Japan
Communication dans un congrès
hal-01319779v1
|
|
LIA @ MediaEval 2013 Crowdsourcing Task: Metadata or not Metadata? That is a Fashion QuestionMediaEval, Oct 2013, Barcelone, Spain
Communication dans un congrès
hal-01318659v1
|
|
Combinaison de thèmes latents pour la contextualisation de TweetsEGC'2013 13e Conférence Francophone sur l'Extraction et la Gestion des connaissances, Jan 2013, Toulouse, France
Communication dans un congrès
hal-01339909v1
|
|
|
Combining Acoustic Name Spotting and Continuous Context Models to improve Spoken Person Name Recognition in SpeechInterspeech 2013, Aug 2013, Lyon, France
Communication dans un congrès
hal-02102829v1
|
LIA @ MediaEval 2013 MusiClef Task: A Combined Thematic and Acoustic ApproachMediaEval, Oct 2013, Barcelone, Spain
Communication dans un congrès
hal-01318668v1
|
|
LIA @ MediaEval 2011 : Compact Representation of Heterogeneous Descriptors for Video Genre ClassificationMediaEval, Sep 2011, Pise, Italy
Communication dans un congrès
hal-01320178v1
|
|
A Language-identification inspired method for spontaneous speech detectionINTERSPEECH, Sep 2010, Makuhari, Japan
Communication dans un congrès
hal-01320176v1
|
|
Spontaneous Speech Characterization and Detection in Large Audio Database13-th International Conference on Speech and Computer (SPECOM 2009), 2009, St Petersburg, Russia
Communication dans un congrès
hal-01433943v1
|
An Author-Topic based Approach to Cluster Tweets and Mine their LocationPoster de conférence hal-01250549v1 |