Fifth International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications (MAVEBA 2007)

Florence, Italy
December 13-15, 2007

SMS-FESTIVAL: a New TTS Framework

Giacomo Sommavilla, Piero Cosi, Carlo Drioli, Giulio Paci

Istituto di Scienze e Tecnologie della Cognizione - Sede di Padova “Fonetica e Dialettologia”, Consiglio Nazionale delle Ricerche, Padova, Italy

A new sinusoidal model based engine for FESTIVAL TTS system which performs the DSP (Digital Signal Processing) operations (i.e. converting a phonetic input into audio signal) of a diphone-based TTS concatenative system, taking as input the NLP (Natural Language Processing) data (a sequence of phonemes with length and intonation values elaborated from the text script) computed by FESTIVAL is described.
   The engine aims to be an alternative to MBROLA and makes use of SMS (“Spectral Modeling Synthesis”) representation, implemented with the CLAM (C++ Library for Audio and Music) framework.
   This program will be released with open source license (GPL), and will compile everywhere gcc and CLAM do (i.e.: Windows, Linux and Mac OS X operating systems).
Index Terms. TTS, SMS, MBROLA, FESTIVAL, GPL.

Full Paper (reprinted with permission from Firenze University Press)

Bibliographic reference.  Sommavilla, Giacomo / Cosi, Piero / Drioli, Carlo / Paci, Giulio (2007): "SMS-FESTIVAL: a new TTS framework", In MAVEBA-2007, 89-92.