selected publications
-
blog posting
- Inserting faces inside captions: image captioning with attention guided merging. . 2024
- Multimodal chaptering for long-form TV newscast video. . 2024
- Home monitoring for frailty detection through sound and speaker diarization analysis. arXiv (Cornell University). 2023
- The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description. arXiv (Cornell University). 2023
- Towards Measuring and Scoring Speaker Diarization Fairness. arXiv (Cornell University). 2023
-
conference paper
- Privacy Preserving Personal Assistant with On-Device Diarization and Spoken Dialogue System for Home and Beyond. HAL (Le Centre pour la Communication Scientifique Directe). 2024
- Privacy Preserving Personal Assistant with On-Device Diarization and Spoken Dialogue System for Home and beyond. AHFE international. 2024