5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

SABLE: A Standard For TTS Markup

Richard Sproat (1), Andrew Hunt (2), Mari Ostendorf (3), Paul Taylor (4), Alan W. Black (4), Kevin Lenzo (5), Mike Eddington (6)

(1) Bell Labs, Lucent Technologies, USA
(2) Sun Microsystems, Inc, USA
(3) Boston University, USA
(4) CSTR, University of Edinburgh, UK
(5) Carnegie Mellon University, USA
(6) BT Labs, UK

Currently, speech synthesizers are controlled by a multitude of proprietary tag sets. These tag sets vary substantially across synthesizers and are an inhibitor to the adoption of speech synthesis technology by developers. SABLE is an XML/SGML-based markup scheme for text-to-speech synthesis, developed to address the need for a common TTS control paradigm. This paper presents an overview of the SABLE v0.2 specification, and provides links to websites with further information on SABLE.

Full Paper

Bibliographic reference.  Sproat, Richard / Hunt, Andrew / Ostendorf, Mari / Taylor, Paul / Black, Alan W. / Lenzo, Kevin / Eddington, Mike (1998): "SABLE: a standard for TTS markup", In ICSLP-1998, paper 0040.