The ESCA Workshop on Speech Synthesis

September 25-28, 1990
Autrans, France

Automatic Inference of a Syllabic Prosodic Model

M. Giustiniani (2), Alessandro Falaschi (1), P. Pierucci (2)

(1) Universita di Roma "La Sapienza", INFO-COM Dpt.; (2) IBM Rome Scientific Center, Rome, Italy

A syllabic structure model is proposed, as a tool for defining a detailed phonemic transcription. The microprosodic features (duration and loudness) of the defined phonological units are estimated by statistical measures on an automatically segmented speech database. The use of these units in a text-to-speech concatenative synthesiser is discussed.


Full Paper

Bibliographic reference.  Giustiniani, M. / Falaschi, Alessandro / Pierucci, P. (1990): "Automatic inference of a syllabic prosodic model", In SSW1-1990, 197-200.