I'm Clément, engineer in machine learning (mainly deep learning). I'm graduated from the UPSSITECH engineering school, in Robotic and Interactive Systems (SRI). I'm interested in the domains of AI, audio and image processing, weather, astronomy... I'm also a wildlife and nature photograph 📸.

• Freelance AI engineer, currently working with PyannoteAI
• I'm contributing on pyannote.audio, the most widely used python DNN-based toolkit for answering "who spoke when" question, and on gryannote, an open source audio labeling tool.
• I have founded sunbot, a discord bot providing current and forecast weather.

I have contributed to the following papers:

• Clément Pages, Hervé Bredin Gryannote open-source speaker diarization labeling tool. In Interspeech 2024 2024 (pp. 3650–3651). [link]
• Kalda Joonas, Clément Pages, Ricard Marxer, Tanel Alumäe, and Hervé Bredin. "PixIT: Joint Training of Speaker Diarization and Speech Separation from Real-world Multi-speaker Recordings." . In The Speaker and Language Recognition Workshop (Odyssey 2024) (pp. 115-122). ISCA, 2024. Best student paper award [link]
• Adrien Lafore, Clément Pagés, Leila Moudjari, Sebastião Quintas, Hervé Bredin, Thomas Pellegrini, Farah Benamara, Isabelle Ferrané, Jérôme Bertrand, Marie-Françoise Bertrand, Véronique Moriceau, Jérôme FarinasIRIT-MFU Multi-modal systems for emotion classification for Odyssey 2024 challenge. In The Speaker and Language Recognition Workshop (Odyssey 2024) 2024 (pp. 296–302). [link]
• Lafore Adrien, Clément Pagés, Leila Moudjari, Sebastiao Quintas, Isabelle Ferrané, Hervé Bredin, Thomas Pellegrini, Farah Benamara, Jérome Bertrand, Marie-Françoise Bertrand, Véronique Moriceau, and Jérôme Farinas. "Premier systeme IRIT-MyFamillyUp pour la competition sur la reconnaissance des émotions Odyssey 2024." . In Actes des 35èmes Journées d'Etudes sur la Parole (pp. 502–511). ATALA and AFPC, 2024. [link]