EXPRESSION is involved in 3 research directions :
Expressive gesture synthesis and recognition
Our line of research focuses specifically on the study of variability in motion captured data, linked to different forms of expressiveness, or to the sequencing of semantic actions in selected scenarios. Motion capture is used for finding relevant features that encode the main spatio-temporal characteristics of gestures: low-level features are extracted from the raw data, whereas high-level features reflect structural patterns encoding linguistic aspects of gestures.
Expressive speech synthesis
Expressiveness within speech is crucial in everyday spoken communication and is considered to be linked to intention and emotion. Current speech synthesis systems, mainly concatenative ones, suffer from fine control of the output which implies a lack of expressiveness in the generated speech. The main goal of this research axis is to understand, analyse and reproduce expressiveness in speech so as to be able to produce high-quality expressive speech. Thus, it will enable new applications such as high-quality audiobook generation, online learning and in particular autonomous language learning or even device personalization for disabled.
Expressiveness in text and language