Master thesis presentation Jules Sintes, MPCAS

Abstract: This thesis aims at developing emotion recognition and speaker diarization models for real-life data. We create a new conversational dataset in French language based on real-life recordings containing a large plurality of speakers in various contexts. We conduct a comparative study of various approaches and models for emotion recognition and leverage state of the art speaker diarization methods. This contributes to the development of an end-to-end multitask speech analysis tool for the French language.

Supervisor: Nhut Doan Nguyen (La Javaness)
Examiner: Mohsen Mirkhalaf
Opponent: Philip Gard