Skip to Main content
New interface

Researcher identifiers

Social networks


Number of documents


Xavier Bost

Current positions

  • Data scientist in speech processing and multimedia retrieval, Orkis SAS.
  • Teaching assistant, Avignon University, CERI.
  • Teacher of philosophy on availability.

Short bio. With a background in philosophy, Xavier Bost received a PhD in computer science from Avignon University in 2016. Started at the Avignon Computer Science Laboratory (LIA), his research works mostly focus on analysing language interactions in a computational way, both from theirs contents and dynamics. His PhD thesis, in close collaboration with social scientists, focused on automatic summarization of narrative documents, especially fictional films. Since December 2016, he has been a data scientist at Orkis, an SME located in Aix-en-Provence working on multimedia retrieval. Before he moved to computer science, he had been teaching philosophy in high school (1997-2013) and took interest in computational linguistics when considering possible ways of automating procedures used in historical and comparative linguistics.

Research areas. Natural language processing (spoken/written), information retrieval within narrative documents, multimedia retrieval, social network analysis, machine learning.

Professional experience

2018--Present Teaching assistant, Avignon University, CERI.
2016--Present Data scientist in speech processing and multimedia retrieval, Orkis SAS, Aix-en-Provence.
2013--Present Philosophy teacher, on availability.
sept.--nov. 2015 Invited researcher, Delft University of Technology, The Netherlands.
2013--2016 PhD student in computer science, Avignon University, LIA/CERI.
2002--2013 Philosohy teacher, Aix-Marseille schools district.
1998--2002 Philosophy teacher, Clermont-Ferrand schools district.
1997--1998 Philosophy teacher, Orléans-Tours schools district.
1996--1997 Teaching assistant, École du Service de Santé des Armées, Lyon-Bron.



PhD in computer science, Avignon University.

Funding: Agorantic research federation.

Sujet : A storytelling machine? Automatic video summarization: the case of TV series.

Defense: 2016/11/23, Avignon.

Co-supervisors: Georges Linarès (LIA, dir.), Damien Malinas (CNE), Serigne Gueye (LIA).


MSc in computer science, Avignon University.

Master thesis: Multi-label categorization of dialogues.

Co-supervisors: Marc El-Bèze (LIA), Renato de Mori (LIA/McGill University).

2011--2012 MSc in computer science, 1st year, University of Franche-Comté.
2008--2011 BSc in computer science, Aix-Marseille University.
2003--2004 B.A. in classical studies, 1st year, University of Toulouse-Jean Jaurès.
2001--2002 M.A. in Philosophy, Clermont-Auvergne University.
1998--1999 Agrégation, philosophy (French advanced teaching qualification exam), Clermont-Ferrand schools district.
1995--1996 CAPES, philosophy (French teaching qualification exam), Paris schools district.
1994--1995 M.A. in Philosophy, 1st year, Sorbonne University.
1991--1994 B.A in Philosophy, Sorbonne University.


PhD students
  • Lucas Pascal, Optimization of Deep Multi-Task Networks. Co-supervising with Benoît Huet (Eurecom, dir. 2018-2019), Maria Zuluaga (Eurecom, 2019-2021) & Pietro Michiardi (Eurecom, dir. 2019-2021). PhD thesis (CIFRE funding). Aix-en-Provence and Sophia-Antipolis: Orkis and Eurecom. Defense: 2021/11/08.
  • Titouan Parcollet, Quaternion neural networks. Co-supervising with Georges Linarès (LIA, dir.)  & Mohamed Morchid (LIA), Avignon University. PhD thesis (CIFRE funding). Aix-en-Provence and Avignon: Orkis and Laboratoire Informatique d'Avignon (EA 4128), Avignon Univ. Defense: 2019/12/03.


PhD committee member
  • Lucas Pascal, Optimization of Deep Multi-Task Networks, Eurecom/Orkis. Nov. 2021, Sophia-Antipolis. Invited member.
  • Titouan Parcollet, Quaternion neural networks., Laboratoire Informatique d'Avignon/Orkis. Dec. 2019, Avignon. Examinor.
  • Killan Janod, Neural network representations for spoken documents understanding, Laboratoire Informatique d'Avignon/Orkis. Nov. 2017, Avignon. Invited member.
Reviewer for international journals
Reviewer for international conferences
Reviewer for national conferences

ANR projects


Invited talks

Journal articles4 documents

  • Titouan Parcollet, Mohamed Morchid, Xavier Bost, Georges Linarès, Renato de Mori. Real to H-space Autoencoders for Theme Identification in Telephone Conversations. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, 28, pp.198-210. ⟨10.1109/TASLP.2019.2950596⟩. ⟨hal-02402005⟩
  • Xavier Bost, Serigne Gueye, Vincent Labatut, Martha Larson, Georges Linarès, et al.. Remembering winter was coming: Character-oriented video summaries of TV series. Multimedia Tools and Applications, 2019, 78 (24), pp.35373-35399. ⟨10.1007/s11042-019-07969-4⟩. ⟨hal-02278188v2⟩
  • Vincent Labatut, Xavier Bost. Extraction and Analysis of Fictional Character Networks: A Survey. ACM Computing Surveys, 2019, 52 (5), pp.89. ⟨10.1145/3344548⟩. ⟨hal-02173918v5⟩
  • X. Bost, G. Senay, M. El-Bèze, R. de Mori. Multiple topic identification in human/human conversations. Computer Speech and Language, Elsevier, 2015, 34 (1), pp.18-42. ⟨10.1016/j.csl.2015.03.006⟩. ⟨hal-01956840v2⟩

Book sections1 document

  • Xavier Bost, Vincent Labatut, Serigne Gueye, Georges Linarès. Extraction and Analysis of Dynamic Conversational Networks from TV Series. Mehmet Kaya; Jalal Kawash; Suheil Khoury; Min-Yuh Day. Social Network Based Big Data Analysis and Applications, Springer, pp.55-84, 2018, Lecture Notes in Social Networks, 978-3-319-78195-2. ⟨10.1007/978-3-319-78196-9_3⟩. ⟨hal-01543938v3⟩

Conference papers13 documents

  • Lucas Pascal, Pietro Michiardi, Xavier Bost, Benoit Huet, Maria A Zuluaga. Maximum Roaming Multi-Task Learning. 35th AAAI Conference on Artificial Intelligence, Feb 2021, Virtuel, United States. pp.9331-9341. ⟨hal-03044386⟩
  • Xavier Bost, Vincent Labatut, Georges Linares. Serial Speakers: a Dataset of TV Series. 12th International Conference on Language Resources and Evaluation (LREC 2020), May 2020, Marseille, France. pp.4256-4264. ⟨hal-02477736⟩
  • Titouan Parcollet, Mohamed Morchid, Xavier Bost, Georges Linarès. M2H-GAN: A GAN-based Mapping from Machine to Human Transcripts for Speech Understanding. INTERSPEECH 2019, Sep 2019, Gratz, Austria. ⟨hal-02107674v2⟩
  • Lucas Pascal, Xavier Bost, Benoît Huet. Semantic and Visual Similarities for Efficient Knowledge Transfer in CNN Training. International Conference on Content-Based Multimedia Indexing (CBMI), Sep 2019, Dublin, Ireland. ⟨10.1109/CBMI.2019.8877391⟩. ⟨hal-02285234v2⟩
  • Xavier Bost, Vincent Labatut, Serigne Gueye, Georges Linares. Narrative Smoothing: Dynamic Conversational Network for the Analysis of TV Series Plots. DyNo: 2nd International Workshop on Dynamics in Networks, in conjunction with the 2016 IEEE/ACM International Conference ASONAM, Aug 2016, San Francisco, United States. pp.1111-1118, ⟨10.1109/ASONAM.2016.7752379⟩. ⟨hal-01276708v6⟩
  • Xavier Bost, Vincent Labatut, Serigne Gueye, Georges Linarès. Extraction de réseaux dynamiques conversationnels par lissage narratif. 7ème Conférence Modèles & Analyse de Réseaux : approches mathématiques et informatiques (MARAMI), Oct 2016, Cergy-Pontoise, France. ⟨hal-01385215⟩
  • Xavier Bost, Georges Linares. Détection de locuteurs dans les séries TV. Coria 2015, Mar 2015, Paris, France. ⟨hal-01313094⟩
  • Xavier Bost, Georges Linarès, Serigne Gueye. Audiovisual speaker diarization of TV series. 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Apr 2015, Brisbane, Australia. pp.4799-4803, ⟨10.1109/ICASSP.2015.7178882⟩. ⟨hal-01313080v2⟩
  • Xavier Bost, Georges Linares. Constrained speaker diarization of TV series based on visual patterns. 2014 IEEE Spoken Language Technology Workshop (SLT), Dec 2014, South Lake Tahoe, United States. pp.390-395, ⟨10.1109/SLT.2014.7078606⟩. ⟨hal-01957900v2⟩
  • Xavier Bost, Marc El-Bèze, Renato de Mori. Catégorisation multi-thématique de dialogues téléphoniques. XXXe édition des Journées d’Études sur la Parole (JEP 2014), Jun 2014, Le Mans, France. ⟨hal-01967848⟩
  • Xavier Bost, Ilaria Brunetti, Luis Adrian Cabrera Diego, Jean-Valère Cossu, Andréa Carneiro Linhares, et al.. Systèmes du LIA à DEFT'13. DEFT2013, Jun 2013, Les Sables d'Olonne, France. ⟨hal-01313065⟩
  • Jean Valère Cossu, Benjamin Bigot, Ludovic Bonnefoy, Mohamed Morchid, Xavier Bost, et al.. LIA@RepLab 2013. Replab: An evaluation campaign for Online Reputation Management Systems, Fourth International Conference of the CLEF initiative, Sep 2013, Valencia, Spain. ⟨hal-01967853⟩
  • Xavier Bost, Marc El Bèze, Renato de Mori. Multiple topic identification in telephone conversations. Interspeech, Aug 2013, Lyon, France. ⟨hal-01313070v2⟩

Theses1 document

  • Xavier Bost. A storytelling machine?: Automatic video summarization: the case of TV series. . Computer Science [cs]. Université d'Avignon et des Pays de Vaucluse, 2016. English. ⟨tel-01402549⟩

Preprints, Working Papers, ...1 document

  • Jean-Valère Cossu, Ludovic Bonnefoy, Xavier Bost, Marc El Bèze. How to merge three different methods for information filtering ?. 2015. ⟨hal-01220188⟩