Marc Evrard
Publications
Publications
|
|
Computer modelling of innovations relative to Latin in contemporary Romance dialectsIsogloss. Open Journal of Romance Linguistics, 2025, 11 (3), pp.1 - 31. ⟨10.5565/rev/isogloss.423⟩ |
|
|
Paradigmatic variation of vowels in expressive speech: Acoustic description and dimensional analysisJournal of the Acoustical Society of America, 2018, 143 (1), pp.109-122. ⟨10.1121/1.5018433⟩ |
|
|
Robust Vocal Intensity Prediction: Overcoming Dataset Bias with Pretrained Deep ModelsInterspeech 2025, Odette Scharenborg; Catharine Oertel; Khiet Truong, Aug 2025, Rotterdam, Netherlands. pp.1728-1732, ⟨10.21437/Interspeech.2025-2311⟩ |
|
|
Impact de la parole expressive sur l'estimation de l'intensité vocaleCFA 2025 - 17e Congrès Français d'Acoustique, Société Française d'Acoustique (SFA), Apr 2025, Paris, France |
|
|
Variabilité du signal de parole en fonction de la Force de Voix en situation d’interaction oraleCFA 2025 - 17e Congrès Français d'Acoustique, Société Française d'Acoustique (SFA), Apr 2025, Paris, France |
|
|
New Methods for Exploring Intonosyntax: Introducing an Intonosyntactic Treebank for Nigerian PidginThe 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), ELRA Language Resource Association, May 2024, Turin, Italy. pp.12207-12216 |
|
|
De nouvelles méthodes pour l'exploration de l'interface syntaxe-prosodie : un treebank intonosyntaxique et un système de synthèse pour le pidgin nigérian31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024), Jul 2024, Toulouse, France. pp.376-383 |
|
|
SLAM 3: An Updated Stylization Model for Speech Melody20th International Congress of Phonetic Sciences (ICPhS2023), Aug 2023, Prague, Czech Republic |
|
|
NaijaTTS: A pitch-controllable TTS model for Nigerian PidginISCA Speech Synthesis Workshop, Aug 2023, Grenoble, France |
|
|
Annotation of expressive dimensions on a multimodal French corpus of political interviewsFirst Workshop on Natural Language Processing for Political Sciences (PoliticalNLP), Jun 2022, Marseille, France. pp.91-97 |
Evaluation of the Impact of Corpus Phonetic Alignment on the HMM-Based Speech Synthesis QualityInternational Conference on Statistical Language and Speech Processing (SLSP 2015), 2015, Budapest, Hungary. pp.62-72, ⟨10.1007/978-3-319-25789-1_7⟩ |
|
Comparison of chironomic stylization versus statistical modeling of prosody for expressive speech synthesisAnnual Conference of the International Speech Communication Association (INTERSPEECH 2015), 2015, Dresde, Germany. pp.3370-3374, ⟨10.21437/Interspeech.2015-142⟩ |
|
Objective evaluation of HMM-based speech synthesis system using Kullback-Leibler divergenceINTERSPEECH 2014, 15th Annual Conference of the International Speech Communication Association, Sep 2014, Singapour, Singapore. pp.2952-2956, ⟨10.21437/Interspeech.2014-203⟩ |
|
Object-Based Sound Re-Mix for Spatially Coherent Audio Rendering of an Existing Stereoscopic-3-D Animation MovieAudio Eng Soc Conv 131, Oct 2011, New York, United States. pp.8486:1--15 |
|
|
Cartografia di innovazioni rispetto al latino attraverso un atlante sonoro dell'EuropaErica Autelli. Il patrimonio linguistico storico della Liguria 2, InSedicesimo, pp.51-62, 2024 |
Transformers in Automatic Speech RecognitionHuman-Centered Artificial Intelligence, 13500, Springer International Publishing, pp.123-139, 2023, Lecture Notes in Computer Science, ⟨10.1007/978-3-031-24349-3_8⟩ |