georges linares
CV Georges Linares
28
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
- 28
- 12
- 9
- 9
- 7
- 7
- 6
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 26
- 2
- 1
- 4
- 4
- 3
- 2
- 3
- 1
- 2
- 3
- 1
- 1
- 1
- 1
- 1
- 1
Audio-Based Video Genre IdentificationIEEE/ACM Transactions on Audio, Speech and Language Processing, 2015, 23 (6), pp.1031 - 1041. ⟨10.1109/TASLP.2014.2387411⟩
Article dans une revue
hal-01320230v1
|
|
Compact Multiview Representation of Documents Based on the Total Variability SpaceIEEE/ACM Transactions on Audio, Speech and Language Processing, 2015, ⟨10.1109/TASLP.2015.2431854⟩
Article dans une revue
hal-01319808v1
|
|
Modeling nuisance variabilities with factor analysis for GMM-based audio pattern classificationComputer Speech and Language, 2011, ⟨10.1016/j.csl.2010.11.001⟩
Article dans une revue
hal-01318503v1
|
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
|
|
Audio-Based Video Genre IdentificationTASLP 2015 Transactions on Audio Speech and Language, 2015, Piscataway, United States. ⟨10.1109/TASLP.2014.2387411⟩
Communication dans un congrès
hal-01340017v1
|
|
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
|
|
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
|
|
Subspace Gaussian Mixture Models for Dialogues ClassificationInterspeech, May 2014, Singapore, Singapore
Communication dans un congrès
hal-01313132v1
|
|
LIA @ MediaEval 2013 MusiClef Task: A Combined Thematic and Acoustic ApproachMediaEval, Oct 2013, Barcelone, Spain
Communication dans un congrès
hal-01318668v1
|
|
LIA @ MediaEval 2013 Crowdsourcing Task: Metadata or not Metadata? That is a Fashion QuestionMediaEval, Oct 2013, Barcelone, Spain
Communication dans un congrès
hal-01318659v1
|
|
LIA @ MediaEval 2013 Spoken Web Search Task: An I-Vector based ApproachMediaEval, Oct 2013, Barcelone, Spain
Communication dans un congrès
hal-01313144v1
|
|
Acoustic modeling for under-resourced languages based on vectorial HMM-states representation using Subspace Gaussian Mixture ModelsIEEE Spoken Language Technology Workshop (SLT), Dec 2012, Miami, United States. ⟨10.1109/SLT.2012.6424245⟩
Communication dans un congrès
hal-01313103v1
|
|
Subspace Gaussian Mixture Models Based on Noise Compensation for Speech RecognitionInterspeech 2012, 2012, Unknown, Unknown Region
Communication dans un congrès
hal-01433477v1
|
|
A simplified Subspace Gaussian Mixture to compact acoustic models for speech recognitionIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , May 2011, Prague, Czech Republic. ⟨10.1109/ICASSP.2011.5947453⟩
Communication dans un congrès
hal-01313109v1
|
|
Subspace Gaussian Mixture Models for vectorial HMM-states representationIEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), Dec 2011, Waikoloa, United States. ⟨10.1109/ASRU.2011.6163984⟩
Communication dans un congrès
hal-01318611v1
|
|
On-the-fly video genre classification by combination of audio featuresIEEE International Conference on Acoustics, Speech and Signal Processing , Mar 2010, Dallas, United States. ⟨10.1109/ICASSP.2010.5496233⟩
Communication dans un congrès
hal-01320222v1
|
|
Robust Audio-based Classification of Video GenreINTERSPEECH, Sep 2009, Brighton, United Kingdom
Communication dans un congrès
hal-01320224v1
|
|
Factor Analysis for Audio-based Video Genre ClassificationINTERSPEECH, Sep 2009, Brighton, United Kingdom
Communication dans un congrès
hal-01320228v1
|
|
Combinaison de differents jeux de paramètres acoustiques pour la reconnaissance automatique de la paroleJournées d'Études sur la Parole (JEP'08), 2008, Avignon, France
Communication dans un congrès
hal-01434057v1
|
|
Combinaison de différents jeux de param etres acoustiques pour la reconnaissance de la paroleLes Journées d’Etude sur la Parole (JEP), Jun 2008, Avignon, France
Communication dans un congrès
hal-01312834v1
|
|
|
Frame-Based Acoustic Feature Integration for Speech UnderstandingIEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008., Mar 2008, Las Vegas, NV,, United States. pp.4997-5000, ⟨10.1109/ICASSP.2008.4518780⟩
Communication dans un congrès
hal-00424663v1
|
The LIA Speech Recognition System: From 10xRT to 1xRT10th International Conference, TSD, Sep 2007, Pilsen, Czech Republic
Communication dans un congrès
hal-01318280v1
|
|
Le système de transcription du LIA pour ESTER-2005ESTER 2005, Mar 2005, Avignon, France
Communication dans un congrès
hal-01318289v1
|
|
|
Segmentation en macro-classes acoustiques d'émissions radiophoniques dans le cadre d'ESTERJournée d'Etudes sur la Parole, JEP 04, Avril 2004, Apr 2004, Fès, Maroc
Communication dans un congrès
hal-00477753v1
|
Structural speaker adaptation using maximum a posteriori approach and a Gaussian distributions merging techniqueIEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP '03, Apr 2003, Hong-Kong, China. ⟨10.1109/ICASSP.2003.1202309⟩
Communication dans un congrès
hal-01312867v1
|
|
A Posteriori and a Priori Transformations for Speaker Adaptation in Large Vocabulary Speech Recognition SystemsEUROSPEECH 2001 Scandinavia, 7th European Conference on Speech Communication and Technology, 2nd INTERSPEECH Event, Sep 2001, Aalborg, Denmark
Communication dans un congrès
hal-01318489v1
|
|
Phone duration models for fast broadcast news transcriptions[Research Report] UAPV. 2006
Rapport
hal-01631340v1
|