Skip to Main content


European projects

Number of documents


Marie Tahon

Marie Tahon is currently Associate Professor at Le Mans University and conducts her research at LIUM. She graduated in engineering from the Ecole Centrale de Lyon in 2007 and received the M.S. degree in acoustics from the Ecole Centrale & INSA Lyon, in 2007. She received the Ph.D. degree in computer science from the University of Paris-Sud (Orsay) in 2012. She has been with the LIMSI-CNRS (Orsay) working on affective computing (post-doctoral position), with the LMSSC, CNAM (Paris) working on acoustics (ATER position) and also the IRISA (Lannion) in the team “Expression’’ (post-doctoral position).

Her research interests concern expressive speech processing, mainly in the fields of speech synthesis, emotion recognition and speaker identification. She has also developed strong skills in musical acoustics for automatic songs analysis and organology.

Journal articles8 documents

  • Marie Tahon, Silvio Montrésor, Pascal Picart. Deep Learning Network for Speckle De-Noising in Severe Conditions. Journal of Imaging, MDPI, 2022, 8 (6), pp.165. ⟨10.3390/jimaging8060165⟩. ⟨hal-03696072⟩
  • Marie Tahon, Pascal Picart, Silvio Montresor. Towards Reduced CNNs for De-Noising Phase Images Corrupted with Speckle Noise. Photonics, MDPI, 2021, 8 (7), ⟨10.3390/photonics8070255⟩. ⟨hal-03277712⟩
  • Silvio Montrésor, Marie Tahon, Antoine Laurent, Pascal Picart. Computational de-noising based on deep learning for phase data in digital holographic interferometry. APL Photonics, AIP Publishing LLC, 2020, 5 (3), ⟨10.1063/1.5140645⟩. ⟨hal-02499209⟩
  • Marie Tahon, Gwénolé Lecorvé, Damien Lolive. Can we Generate Emotional Pronunciations for Expressive Speech Synthesis?. IEEE Transactions on Affective Computing, Institute of Electrical and Electronics Engineers, 2020, 11 (4), pp.684-695. ⟨10.1109/TAFFC.2018.2828429⟩. ⟨hal-01802463⟩
  • Marie Tahon, Pierre-Eugène Sitchet. The transmission of voicing in traditional Gwoka: Between identity and memory. Journal of Interdisciplinary Voice Studies, 2017, 2 (2), pp.157-175. ⟨10.1386/jivs.2.2.157_1⟩. ⟨hal-01593445⟩
  • Marie Tahon, Laurence Devillers. Towards a Small Set of Robust Acoustic Features for Emotion Recognition: Challenges. IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2016, IEEE/ACM Transactions on Audio, Speech and Language Processing, 24, pp.16 - 28. ⟨10.1109/TASLP.2015.2487051⟩. ⟨hal-01404146⟩
  • Laurence Devillers, Marie Tahon, Mohamed El Amine Sehili, Agnes Delaborde. Inference of Human Beings' Emotional States from Speech in Human-Robot Interactions.. International Journal of Social Robotics, Springer, 2015. ⟨hal-01926670⟩
  • Laurence Devillers, Marie Tahon, Mohamed El Amine Sehili, Agnes Delaborde. Détection des états affectifs lors d'interactions parlées: robustesse des indices non verbaux. Revue TAL, ATALA (Association pour le Traitement Automatique des Langues), 2015. ⟨hal-01926676⟩

Conference papers31 documents

  • Martin Lebourdais, Marie Tahon, Antoine Laurent, Sylvain Meignier, Anthony Larcher. Overlaps and Gender Analysis in the Context of Broadcast Media. LREC 2022, Jun 2022, Marseille, France. ⟨hal-03660323⟩
  • Manon Macary, Marie Tahon, yannick Estève, Anthony Rousseau. On the use of Self-supervised Pre-trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition. IEEE Spoken Language Technology Workshop, Jan 2021, Virtual, China. ⟨hal-03003469⟩
  • Anthony Larcher, Ambuj Mehrish, Marie Tahon, Sylvain Meignier, Jean Carrive, et al.. SPEAKER EMBEDDINGS FOR DIARIZATION OF BROADCAST DATA IN THE ALLIES CHALLENGE. ICASSP, Jun 2021, Toronto, Canada. ⟨hal-03262914⟩
  • Alexandre Flucha, Anthony Larcher, Ambuj Mehrish, Sylvain Meignier, Florian Plaut, et al.. The LIUM Human Active Correction Platform for Speaker Diarization. interspeech, Aug 2021, Brno, Czech Republic. ⟨hal-03262976⟩
  • Manon Macary, Marie Tahon, yannick Estève, Anthony Rousseau. Prédiction continue de la satisfaction et de la frustration dans des conversations de centre d’appels. 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 1 : Journées d'Études sur la Parole, Jun 2020, Nancy, France. pp.379-387. ⟨hal-02798561v3⟩
  • Jane Wottawa, Marie Tahon, Apolline Marin, Nicolas Audibert. Towards Interactive Annotation for Hesitation in Conversational Speech. LREC 2020, May 2020, Marseille, France. ⟨hal-02505333⟩
  • Manon Macary, Marie Tahon, yannick Estève, Anthony Rousseau. AlloSat: A New Call Center French Corpus for Satisfaction and Frustration Analysis. Language Resources and Evaluation Conference, LREC 2020, May 2020, Marseille, France. ⟨hal-02506086⟩
  • Manon Macary, Martin Lebourdais, Marie Tahon, yannick Estève, Anthony Rousseau. Multi-corpus Experiment on Continuous Speech Emotion Recognition: Convolution or Recurrence?. 22ND INTERNATIONAL CONFERENCE ON SPEECH AND COMPUTER SPECOM 2020, Oct 2020, St Petersburg, Russia. ⟨hal-02945644⟩
  • Silvio Montrésor, Marie Tahon, Antoine Laurent, Pascal Picart. Deep learning-based speckle decorrelation denoising for wide-field optical metrology. Optics and Photonics for Advanced Dimensional Metrology, International Society for Optics and Photonics (SPIE), Apr 2020, Strasbourg, France. ⟨hal-02434956⟩
  • Marie Tahon, Zaher Belghith, Jean-Marc Chouvel, Pierre Michel. SEGMENTATION AUTOMATIQUE DE CATÉGORIES MUSICALES: ÉTUDE EXPLORATOIRE SUR LE FREE JAZZ. Journées d'Informatique Musicale, May 2019, Bayonne, France. ⟨hal-02138608⟩
  • Marie Tahon, Damien Lolive. Discourse phrases classification: direct vs. narrative audio speech. Speech Prosody, Jun 2018, Poznan, Poland. ⟨hal-01790910⟩
  • Aghilas Sini, Damien Lolive, Gaëlle Vidal, Marie Tahon, Elisabeth Delais-Roussarie. SynPaFlex-Corpus: An Expressive French Audiobooks Corpus Dedicated to Expressive Speech Synthesis. Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), May 2018, Miyazaki, Japan. ⟨hal-01826690⟩
  • Damien Lolive, Pierre Alain, Nelly Barbot, Jonathan Chevelu, Gwénolé Lecorvé, et al.. The IRISA Text-To-Speech System for the Blizzard Challenge 2017. Blizzard Challenge, Aug 2017, Stockholm, Sweden. ⟨hal-01662361⟩
  • Marie Tahon, Gwénolé Lecorvé, Damien Lolive, Raheel Qader. Perception of expressivity in TTS: linguistics, phonetics or prosody?. Statistical Language and Speech Processing, Oct 2017, Le Mans, France. pp.262-274, ⟨10.1007/978-3-319-68456-7_22⟩. ⟨hal-01623916v3⟩
  • Raheel Qader, Gwénolé Lecorvé, Damien Lolive, Marie Tahon, Pascale Sébillot. Statistical Pronunciation Adaptation for Spontaneous Speech Synthesis. Text, Speech and Dialogue (TSD), Aug 2017, Prague, Czech Republic. ⟨hal-01532035⟩
  • Marie Tahon, Pierre-Eugène Sitchet. La nasalité dans le répertoire Gwoka de la Guadeloupe. Congrès Français d'Acoustique (CFA), Apr 2016, Le Mans, France. ⟨hal-02308874⟩
  • Marie Tahon, Raheel Qader, Gwénolé Lecorvé, Damien Lolive. Optimal feature set and minimal training size for pronunciation adaptation in TTS. International Conference on Statistical Language and Speech Processing (SLSP), Oct 2016, Pilsen, Czech Republic. ⟨hal-01338853⟩
  • Marie Tahon, Raheel Qader, Gwénolé Lecorvé, Damien Lolive. Improving TTS with corpus-specific pronunciation adaptation. Interspeech, Sep 2016, San Francisco, United States. ⟨hal-01338111⟩
  • Pierre-Eugène Sitchet, Marie Tahon. LE VOISEMENT DANS LE GWOKA : ENTRE LE PARLÉ ET LE CHANTÉ. Journées d'Informatique Musicale (JIM), Mar 2016, Albi, France. ⟨hal-02308865⟩
  • Marie Tahon, Pierre-Eugène Sitchet. From Transcription to Signal representation : Pitch, Rhythm and Performance. International Conference on Technologies for Music Notation and Representation (TENOR), May 2016, Cambridge, United Kingdom. ⟨hal-02434847⟩
  • Marie Tahon, Laurence Devillers. LAUGHTER DETECTION FOR ON-LINE HUMAN-ROBOT INTERACTION. Interdisciplinary Workshop on Laughter and Non-verbal Vocalisations in Speech, Apr 2015, Enschede, Netherlands. ⟨hal-02308884⟩
  • Marie Tahon, Laurence Devillers, Mohamed El Amine Sehili. Cross-Corpus Experiments on Laughter and Emotion Detection in HRI with Elderly People. International Conference on Social Robotics (ICSR), Oct 2015, Paris, France. pp.633-642, ⟨10.1007/978-3-319-25554-5_63⟩. ⟨hal-02434858⟩
  • Marie Tahon, Eric Bavu, Manuel Melon, Alexandre Garcia. Attack transient exploration on sopranino recorder with time-domain Near-Field Acoustic Holography method. International Symposium on Musical Acoustics (ISMA), Jul 2014, Le Mans, France. ⟨hal-02308903⟩
  • Amit Kumar Pandey, Rodolphe Gelin, Rachid Alami, Renaud Viry, Axel Buendia, et al.. Romeo2 Project: Humanoid Robot Assistant and Companion for Everyday Life: I. Situation Assessment for Social Intelligence. AIC: Artificial Intelligence and Cognition, Nov 2014, Torino, Italy. pp.140-147. ⟨hal-01096094⟩
  • Tom Giraud, Marie Soury, Jiewen Hua, Agnes Delaborde, Marie Tahon, et al.. Multimodal Expressions of Stress during a Public Speaking Task: Collection, Annotation and Global Analyses. 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction (ACII 2013), Sep 2013, Genève, Switzerland. ⟨10.1109/ACII.2013.75⟩. ⟨hal-01443842⟩
  • Marie Tahon, Gilles Degottex, Laurence Devillers. Usual voice quality features and glottal features for emotional valence detection. Speech Prosody, May 2012, Shanghai, China. ⟨hal-01404163⟩
  • Marie Tahon, Agnes Delaborde, Laurence Devillers. Corpus of Children Voices for Mid-level Markers and Affect Bursts Analysis. Language Ressource and Evaluation Conference (LREC), 2012, Istanbul, Turkey. ⟨hal-01768827⟩
  • Marie Tahon, Agnes Delaborde, Laurence Devillers. Real-life Emotion Detection from Speech in Human-Robot Interaction: Experiments across Diverse Corpora with Child and Adult Voices. Interspeech, 2011, Firenze, Italy. ⟨hal-01404151⟩
  • Marie Tahon, Laurence Devillers. Acoustic measures characterizing anger across corpora collected in artificial or natural context. Speech Prosody, 2010, Chicago, United States. ⟨hal-01768783⟩
  • Marie Tahon, Agnes Delaborde, Claude Barras, Laurence Devillers. A corpus for identification of speakers and their emotions. Language Ressources and Evaluation Conference (LREC), 2010, Valleta, Malta. ⟨hal-01768819⟩
  • Agnès Delaborde, Marie Tahon, Claude Barras, Laurence Devillers. A Wizard-of-Oz game for collecting emotional audio data in a children-robot interaction. International Workshop on Affective-Aware Virtual Agents and Social Robots, Nov 2009, Boston, United States. ⟨10.1145/1655260.1655265⟩. ⟨hal-01837116⟩

Poster communications1 document

  • Thomas Granjon, Marie Tahon. Comparaison et évaluation de vocodeurs pour la synthèse neuronale en Français. Journées Jeunes Chercheurs en Audition, Acoustique musicale et Signal audio, Jun 2019, Le Mans, France. ⟨hal-02173829⟩

Theses1 document

  • Marie Tahon. Analyse acoustique de la voix émotionnelle de locuteurs lors d’une interaction humain-robot. Autre [cond-mat.other]. Université Paris Sud - Paris XI, 2012. Français. ⟨NNT : 2012PA112275⟩. ⟨tel-00780341⟩