First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

A Rule-Based Italian Text-to-Speech System

S. Barber(1), Rolf Carlson (2), Piero Cosi (3), Maria Gabriella Di Benedetto (4), Björn Granström (2), K. Vagges (3)

(1) INFOVOX AB, Solna, Sweden
(2) Dept. of Speech Comm. and Music Acoustics, KTH, Stockholm, Sweden
(3) Centro di Studio per le Ricerche di Fonetica - C.N.R., Padua, Italy
(4) infocom Dept., University of Rome "La Sapienza", Rome, Italy

An Italian text-to-speech system based on the INFOVOX architecture will be described- With respect to earlier versions of the system, the complete set of Italian vowels and diphthongs was taken into consideration. A set of specific rules for the assignment of word stress, entirely based on statistical considerations, as well as a complete set of grapheme-to-phoneme rules were implemented. Appropriate parameter definitions for the realisation of Italian phonemes were formulated and, on the basis of preliminary results on the study of Italian prosodic structure, appropriate phonetic changes were introduced. Finally, the results of perceptual experiments which were carried out in order to evaluate the system will be described.

Full Paper

Bibliographic reference.  Barbe, S. / Carlson, Rolf / Cosi, Piero / Benedetto, Maria Gabriella Di / Granström, Björn / Vagges, K. (1989): "A rule-based Italian text-to-speech system", In EUROSPEECH-1989, 2517-2520.