Resum
In this paper we present a speech synthesis method for diphonebased text-to-speech systems. Its main goal is to achieve prosodic modifications that result in more natural-sounding synthetic speech. This improvement is especially useful for emotional speech synthesis, which requires high-quality prosodic modification. We present a hybrid method based on TD-PSOLA and the harmonic plus noise model, which incorporates a novel method to jointly modify pitch and time-scale. Preliminary results show an improvement in the synthetic speech quality when high pitch modification is required.
Idioma original | Anglès |
---|---|
Pàgines | 2953-2956 |
Nombre de pàgines | 4 |
Estat de la publicació | Publicada - 2003 |
Esdeveniment | 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 - Geneva, Switzerland Durada: 1 de set. 2003 → 4 de set. 2003 |
Conferència
Conferència | 8th European Conference on Speech Communication and Technology, EUROSPEECH 2003 |
---|---|
País/Territori | Switzerland |
Ciutat | Geneva |
Període | 1/09/03 → 4/09/03 |