Speech Synthesis Links

Speech Synthesizers

• Bell Laboratories (Lucent Technologies) TTS system. Sound examples and an advanced interactive demo (Requires Java).
• Telia Promotor Infovox (Sweden). Sound examples in 11 languages (16bit wav-format). Demo version of Infovox 210 available.
• Digital DECtalk TTS system.
• AT&T TTS System. Sound examples and an interactive demo. Contains also some recent publications for download.
• Bellcore (Bell Communications Research) ORATOR TTS System. Sound examples in au- and wav-format.
• BT-Laboratories (British Telecom)  Laureate TTS System. Sound examples and interactive demo available.
• Eurovocs multilingual text-to-speech synthesizer from Technologie & Relevalidatie. Sound examples in five languages (au-format).
• SoftVoice, Inc. SVTTS speech synthesizer. Sound examples with five different voices.
• Apple PlainTalk Speech Synthesis System. Several sound examples and free version of PlainTalk for Macintosh computers.
• The MBROLA project homepage, TCTS Lab of the Faculté Polytechnique de Mons (Belgium). Sound examples in wav-format.
• Multilingual ProVerbe Speech Engine from ELAN Informatique (based on France Telecom CNET PSOLA). Sound examples in five languages, free evaluation version, and free demonstration CD-ROM available from here.
• Eloquent Technology, Inc. ETI Eloquence TTS system. Sound examples in wav-format.
• AcuVoice, Inc. TTS software. Sound examples in 8-Bit Mu Law PCM Wave format at 8 kHz.
• Panasonic CyberTalk TTS system.
• Microsoft WHISTLER Trainable TTS System.
• SPRUCE High-Level TTS system. Developed at the Universities of Bristol and Essex. Interactive weather forecast demo.
• ASEL ModelTalker, University of Delaware, USA. Interactive demo with three voices and seven emotions.
• CSLU Speech Synthesis Research Group. Festival TTS System and Lyricos singing system demonstrations.
• SVOX German text-to-speech system, Speech Processing Group at TIK, ETH in Zurich. Sound examples and interactive demo.
• German speech synthesis system HADIFIX, University of Bonn. Sound examples and interactive demo in German.
• CHATR (Generic Speech Synthesis System), ATR Interpreting Telecommunications Research Laboratories, Japan. Sound examples in several languages. (Some of the text in Japanese)
• Lernout & Hauspie’s TTS/3000 Text-To-Speech product line.
• YorkTalk speech generation system under development at the University of York UK.
• IPOX All Prosodic Speech Synthesis Architecture, Institute for Perception Research (IPO) and Oxford University Phonetics Laboratory (OUPL). Sound examples.
• Mikropuhe synthesizer for Finnish, Timehouse Corporation.
• Sanosse synthesis system for Finnish

Links with Sound Examples

• Historical demonstrations by Dennis Klatt. (See: Dennis H. Klatt (1987) Review of text-to-speech conversion for English, Journal of the Acoustical Society of America, 82 (3), pp.737-793.)
• Speech Synthesis Museum in Grenoble, France. Sound examples, Audio-Visual TTS examples, and several links to different TTS systems.
• List of Speech Synthesis Systems in the University of Birmingham, England.
• Speech Synthesis Examples in the University of Stuttgart, Germany. Sound examples in 15 languages.

Link Collections

• School of Computer Science, Cernegie Mellon University (CMU), USA. Speech Technology Hyperlinks Page. WWW references, FTP-sites, and newsgroups.
• Same kind of link collection in Japan. (ATR Interpreting Telecommunications Research Laboratories)
• Collection of the speech related web-sites at the University of Essex, England.
• Speech synthesis jumpstation, Institute for Perception Research, Netherlands.

On-Line Publications and Texts

• IEEE/IEE Electronic Library Online.
• Speech Group Archive in Essex. Publications between 1969-1994.
• International Conference on Spoken Language Processing, ICSLP 96 CDROM. Papers in PDF-format.

Other Links

• Laboratory of Acoustics and Acoustic Signal Processing at Helsinki University of Technology, Finland.
• Laboratory of Computational Engineering at Helsinki University of Technology and their Talking Head.
• Cognitive Science department (Cognitiewetenschap) at Nijmegen University, Netherlands.
• Resources for Studying Human Speech, University of Washington. Phonetics, synthesizers, links etc.
• International Phonetic Association home page. International Phonetic Alphabet (IPA) for the phonetic representation of all languages.
• Speech Synthesis Markup Languages, SSML, CSTR.
• Extensible Markup Language, XML, W3C.

To speech synthesis literature.
To my laboratory home page.
To my personal home page (in Finnish)

Last update: 10.3.1999    <sami.lemmetty@hut.fi>