Publication Date:
2007
abstract:
A new sinusoidal model based engine for FESTIVAL
TTS system which performs the DSP (Digital Signal Pro-
cessing) operations (i.e. converting a phonetic input into
audio signal) of a diphone-based TTS concatenative sys-
tem, taking as input the NLP (Natural Language Process-
ing) data (a sequence of phonemes with length and into-
nation 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") repre-
sentation, 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).
Iris type:
04.01 Contributo in Atti di convegno
Keywords:
SMS; TTS; Sintesi Sinusoidale
List of contributors:
Sommavilla, Giacomo; Paci, Giulio; Drioli, Carlo; Cosi, Piero
Book title:
Models and analysis of vocal emissions for biomedical applications: 5th international workshop MAVEBA