Index to "Real-time articulatory speech-synthesis-by-rules"

Published in the Proceedings of AVIOS '95
San Jose, September 11 -14 1995, AVIOS: San Jose, pp 27-44


David Hill
Leonard Manzara
Craig Schock
(c) The Authors 1995
Everyone is permitted to copy and distribute verbatim copies of this scientific paper, with this copyright notice, but changing it is not allowed.

Download a .pdf version:

Table of Contents

Note: Speech samples are linked at the end of this menu

An historical perspective
Origins of machine synthesis in Electrical Engineering and Computer Science
Modern articulatory synthesis
A tube model
Using a tube model
The control and computation problems
Distinctive Regions and Modes: the Distinctive Region Model (DRM)
Acoustical basis
A DRM-based control system and its advantages/A>
Building a real-time articulatory-synthesis-based text-to-speech system
Basic tasks
The synthesiser
Parameter target and rule data management-MONET
Building the databases
The complete system
Discussion and future work

Male-Female-Child “Hello”synthesis comparison (sound files all ~3 MB)
(Composed by Leonard Manzara as a demonstration)

.aiff file
.au file
.snd file
.wav file

Additional examples illustrating full articulatory text-to-speech synthesis for male voice (examples chosen for interest rather than flattery)
Pat-a-pan Lumberjack The Chaos

Page created 06-08-13

Last modified: Sun Nov 17 15:17:54 PST 2013