M
Mathieu Chollet
Researcher at University of Southern California
Publications - 48
Citations - 874
Mathieu Chollet is an academic researcher from University of Southern California. The author has contributed to research in topics: Public speaking & Multimodal interaction. The author has an hindex of 13, co-authored 47 publications receiving 743 citations. Previous affiliations of Mathieu Chollet include Télécom ParisTech & Japan Society for the Promotion of Science.
Papers
More filters
Proceedings ArticleDOI
Affect-LM: A Neural Language Model for Customizable Affective Text Generation
TL;DR: This paper proposes an extension to an LSTM (Long Short-Term Memory) language model for generation of conversational text, conditioned on affect categories, and enables us to customize the degree of emotional content in generated sentences through an additional design parameter.
Book ChapterDOI
The TARDIS Framework: Intelligent Virtual Agents for Social Coaching in Job Interviews
Keith M.K. Anderson,Elisabeth André,Tobias Baur,Sara Bernardini,Mathieu Chollet,Evi Chryssafidou,Ionut Damian,Cathy Ennis,Arjan Egges,Patrick Gebhard,Hazaël Jones,Magalie Ochs,Catherine Pelachaud,Kaśka Porayska-Pomsta,Paola Rizzo,Nicolas Sabouret +15 more
TL;DR: The general architecture of the TARDIS job interview simulator, and the serious game paradigm that is developing, are presented.
Proceedings ArticleDOI
Exploring feedback strategies to improve public speaking: an interactive virtual audience framework
TL;DR: The experiments show that the interactive virtual audience brings together the best of both worlds: increased engagement and challenge as well as improved public speaking skills as judged by experts.
Posted Content
Affect-LM: A Neural Language Model for Customizable Affective Text Generation
TL;DR: The authors proposed an extension to an LSTM (Long Short-Term Memory) language model for generating conversational text conditioned on affect categories, which enables the model to customize the degree of emotional content in generated sentences through an additional design parameter.
Proceedings ArticleDOI
Multimodal Public Speaking Performance Assessment
Torsten Wörtwein,Mathieu Chollet,Boris Schauerte,Louis-Philippe Morency,Rainer Stiefelhagen,Stefan Scherer +5 more
TL;DR: This work utilizes multimodal ensemble tree learners to automatically approximate expert judges' evaluations to provide post-hoc performance assessments to the speakers and finds that the multi-modality ensembles consistently outperform single modalities.