I currently work as Head of Science for Moments Lab, a company that develops AI solutions for the sports, media and entertainment industries.
I have a PhD in artificial intelligence from Institut Polytechnique de Paris, and my current research interests include video understanding, multimodal learning, and AI fairness.
Recent News
- 2024-04: We launched an AI Research Program with Moments Lab, focusing on video understanding.
- 2023-03: I was invited to give a TEDx talk. I talked about disability biases in the society and how it propagates in AI systems. You can watch it here!
- 2023-12: Successfully defended my PhD thesis on speaker diarization.
- Guetari K., Tevissen Y., Petitpont F., “Multimodal Chaptering for Long-Form TV Newscast Video”, preprint, 2024. [[pdf]]
- Tevissen Y., Guetari K., Tassel M., Kerleroux E., Petitpont F., “Inserting Faces inside Captions: Image Captioning with Attention Guided Merging”, preprint, 2024. [[pdf]]
- Chollet, G., Sansen, H., Tevissen, Y., Boudy, J., Hariz, M., Lohr, C., & Yassa, F. (2024). Privacy Preserving Personal Assistant with On-Device Diarization and Spoken Dialogue System for Home and Beyond. Proceedings of IHIET 2024. [[pdf]]
- Tevissen, Y., Istrate D., Zalc V., Boudy, J. Chollet G., Petitpont F., and Boutamine S., Home monitoring for frail detection through sound and speaker diarization analysis, JETSAN 2023. [[pdf]]
- Tevissen, Y., Boudy, J., & Petitpont, F. The Newsbridge-Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description. [[pdf]]
- Tevissen, Y., Boudy, J., Chollet, G., and Petitpont, F., Towards Measuring and Scoring Speaker Diarization Fairness, arXiv e-prints, 2023. doi:10.48550/arXiv.2302.09991. [[pdf]]
- Yannis Tevissen, Des médias à la santé: nouveaux usuages de la diarisation du locuteur, May 2023, Webinaire IMT [[video]]
- Yannis Tevissen, Jérôme Boudy, Gérard Chollet. Multi-stream voice activity detection for robust speaker diarization. GDR ISIS 2022: Information, Signal, Image et ViSion: Traitement du signal pour la voix, Oct 2022, Paris, France. ffhal-03937815f [[pdf]]