The SIMPÆX project aims at the automatic segmentation and identification of expressive styles and speakers in a speech corpus. Indeed the extraction of features concerning the speaker, his emotional state and the social context, offers very relevant clues for various applications such as audio indexing, automatic speech recognition, speech synthesis or human-machine interactions.

The project focuses on three main topics :

– Modeling of expressive styles in a multi-speaker context,
– The development of a hybrid system answering the problematic “who speaks, when and how? »,
– Unsupervised recognition of the expressive style by extracting linguistic, acoustic and phonetic clues from the audio speech signal, as well as automatic prediction of emotion.