Unit selection (US) TTSs generate quite natural speech but highly variable in quality. Statistical parametric (SP) systems offer far more consistent quality but reduced naturalness due to its vocoding nature. We present a hybrid approach (HA) that tries to improve the overall naturalness combining both synthesis methods. Contrary to other works, the fusion of methods is performed both in prosody and acoustic modules yielding a more robust prosody prediction and achieving greater naturalness. Objective and subjective experiments show the validity of our procedure.
Bibliographic reference. Sainz, Iñaki / Erro, Daniel / Navas, Eva / Hernáez, Inma (2011): "A hybrid TTS approach for prosody and acoustic modules", In INTERSPEECH-2011, 333-336.