RAMCESS framework 2.0 Realtime and Accurate Musical Control of Expression in Singing Synthesis

In this paper we present the investigations realized in the context of the eNTERFACE 3rd summer worshop on multimodal interfaces. It concerns the development of a new release of the RAMCESS framework (2.x), preserving the accurate and expressive control of voice quality dimensions available in the existing system (from 2006), but adding coarticulated speech possibilities. This work will be achieved by the analysis, separation and modeling of the glottal source component from a limitedsize and adapted singing voice database.