
Présentation
I hold a PhD in Linguistics, specializing in Computer Science, from the University of Aix-Marseille, where I was affiliated with both the Laboratoire Parole et Langage and the Laboratoire d'Informatique et Systèmes, with funding from the ILCB. My doctoral research was supervised by Dr. Philippe Blache, Dr. Magalie Ochs, Dr. Roxane Bertrand, and Dr. Stéphane Rauzy. I also collaborated with Dr. Louis-Philippe Morency during a research stay at Carnegie Mellon University.
My research adopts an interdisciplinary approach to the study of human-to-human and human-computer interactions. During my PhD, I focused on conversational feedback and its role in communication. I developed expertise in creating and annotating multimodal corpora, computational modeling, statistical and clustering analyses, linguistic interpretation, experimental study design, as well as neurophysiological data collection and preprocessing.
My research centers on understanding the mechanisms of communication and mutual comprehension, exploring both behavioral and cognitive dimensions to identify factors that enhance the quality of conversations. Currently, I am interested in exploring individual variability and adaptability in conversation, particularly from the perspective of speaker style and alignment mechanisms, integrating a multimodal and interdisciplinary approach.
I would be delight to connect with anyone interested in discussing my research or exploring collaboration opportunities. Please don't hesitate to reach out to me at auriane.boudin@univ-amu.fr
Publications
Publications
|
How is your feedback perceived? An experimental study of anticipated and delayed conversational feedbackJASA Express Letters, 2024, 4 (7), ⟨10.1121/10.0026448⟩
Article dans une revue
hal-04687738
v1
|
|
A multimodal model for predicting feedback position and type during conversationSpeech Communication, 2024, 159, pp.103066. ⟨10.1016/j.specom.2024.103066⟩
Article dans une revue
hal-04551398
v1
|
|
A multimodal approach for modeling engagement in conversationFrontiers in Computer Science, 2023, 5, ⟨10.3389/fcomp.2023.1062342⟩
Article dans une revue
hal-04011927
v1
|
|
A Forum Theatre Corpus for Discrimination AwarenessFrontiers in Computer Science, 2023, 5, ⟨10.3389/fcomp.2023.1081586⟩
Article dans une revue
hal-03922947
v1
|
|
Principes et outils pour l'annotation des corpusTravaux Interdisciplinaires sur la Parole et le Langage, 2022, Panorama des recherches au Laboratoire Parole et Langage, 38, ⟨10.4000/tipa.5424⟩
Article dans une revue
hal-03917814
v1
|
|
The Distracted Ear: How Listeners Shape Conversational DynamicsLREC-COLING 2024, May 2024, Torino, Italy
Communication dans un congrès
hal-04569106
v1
|
|
OUTCOME Virtual: a tool for automatically creating virtual character animations’ from human videosIVA '24: ACM International Conference on Intelligent Virtual Agents, Sep 2024, GLASGOW United Kingdom, United Kingdom. pp.1-3, ⟨10.1145/3652988.3696196⟩
Communication dans un congrès
hal-04859028
v1
|
|
SMYLE: A new multimodal resource of talk-in-interaction including neuro-physiological signalINTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION (ICMI ’23 Companion), Oct 2023, Paris, France. ⟨10.1145/3610661.3616188⟩
Communication dans un congrès
hal-04195031
v1
|
|
Are you Smiling When I am Speaking?Proceedings of the Smiling and Laughter across Contexts and the Life-span Workshop @LREC2022, Jun 2022, Marseille, France
Communication dans un congrès
hal-03713867
v1
|
|
Interdisciplinary Corpus-based Approach for Exploring Multimodal Conversational FeedbackICMI '22: International Conference on Multimodal Interfaces, Nov 2022, Bengaluru, India. pp.705-710, ⟨10.1145/3536221.3557029⟩
Communication dans un congrès
hal-04688897
v1
|
|
A Multimodal Model for Predicting Conversational FeedbacksInternational Conference on Text, Speech, and Dialogue (TSD ), 2021, Olomouc, Czech Republic. ⟨10.1007/978-3-030-83527-9_46⟩
Communication dans un congrès
hal-03331446
v2
|
|
Exploring Conversation Through Feedback: A cross-disciplinary approachLinguistics. Aix-Marseile Université, 2024. English. ⟨NNT : ⟩
Thèse
tel-04969570
v1
|