This project develops the new model Harmonic Plus Noise applied for the concatenative speech synthesis. The software is composed of an analysis part (off-line process) applied on the first initial database and a synthesis part (real time process) applied on the HNM database and the prododic modifications from FESTIVAL. The future work consists of the integretion into the HMM-based speech synthesis.
Sabine Süsstrunk, Majed El Helou
Volkan Cevher, Paul Thierry Yves Rolland
Luc Thévenaz, Marcelo Alfonso Soto Hernandez, Zhisheng Yang, Sheng Wang, Jian Wu