External Links
Google Scholar
provided by
German Research Center for Artificial Intelligence
with support by
as well as by


abbreviation(s): TTS
definition: The generation of synthetic speech from text. Typically, a text-to-speech synthesis system performs a text analysis using natural language processing techniques; determines the appropriate phonetic string and prosodic features; and generates a speech signal by employing a concatenative or rule-based synthesis method.
See also the corresponding HLT Survey chapter: http://www.lt-world.org/hlt_survey/ltw-chapter5-2.pdf
related project(s):
  • HMM-based Speech Synthesis System (HTS)
  • Modular Architecture For Research On Speech Synthesis (MARY)
  • Festvox
  • The Festival Speech Synthesis System (Festival)
related organisation(s):
  • Center for Spoken Language Understanding (CSLU)
related person(s):
  • Tokuda
  • Jan van Santen
  • Alan W. Black
  • Thierry Dutoit
  • Bernd Möbius
  • Gérard Bailly
  • Nick Campbell
related system(s) / resource(s):
  • SVOX Embedded TTS
  • Speechify
  • rVoice
  • Natural Voices
  • Elan TTS
relevant source(s):
related publication(s):

An Introduction to Text-to-Speech Synthesis.
Thierry Dutoit.
Kluwer Academic Publishers. Dordrecht. 1997.

Progress in Speech Synthesis.
Jan van Santen and Richard W. Sproat and Joseph Olive and Julia Hirschberg.
Springer Verlag. New York. 1996.

Automatically clustering similar units for unit selection in speech synthesis.
Alan W. Black and Paul Taylor.
Proceedings Eurospeech, Rhodes, Greece.1997. 601--604.

Optimising selection of units from speech databases for concatenative synthesis.
Alan W. Black and Nick Campbell.
Proceedings Eurospeech, Madrid, Spain. 1995. 581--584.