Free download which receives input from a microphone and responds, either by voice output or executing Windows system command. Powered by the ALICE conversation engine and MS SAPI 5.1.

Minnesota based research startup. Exploring possibilities for people with disabilities through the research of speech technology.

The Applied Voice Input/Output Society (AVIOS) is a research group dedicated to "real world" applications using speech technology.

For speech researchers interested in a standard for phonetic sounds. From University College of London.

A multidisciplinary research centre that undertakes application-oriented speech research mainly in the areas of speech recognition and synthesis. Has implemented useful software, like the Festival speech synthesis system. Interested in collaborating

An MIT Spoken Language Systems research project which gives airplane flight arrival times in response to voice inquiries. Toll free number listed at site.

An MIT Spoken Language Systems research project which gives the weather in 500+ worldwide cities in response to voice inquiries. Toll free number listed at site.

The complete collection of MIT Spoken Language Systems Group conversational computers including ones that tell you about Boston area restaurants, Boston traffic conditions, automobile claasified ads, air flight prices etc.

From the Speech Recognition Group of the Technical University of Crete. Work in progress.

Concentrates on speech synthesis, speech perception.

Services, products and information to enable hearing in machines. Includes some demos and details of models of complex sound pattern recognition.

Provides the academic community world-wide with a notational standard for the phonetic representation of all languages: the International Phonetic Alphabet.

Carl Verner Skou markets a Windows based research tool, Qualitative Media Analyze, that helps tabulate occurrences of phrases and themes in audio and video file formats avoiding the need for manual transcription.

Engages in research and development of speech technologies in a wide range of applications, including speech recognition (Whisper) and speech synthesis (Whistler) and Dr. Who.

Outlines the opportunities to synergistically integrate physical and spoken input.

Boston University resource for experimantal and analyzed data (especially from native signers of ASL) to facilitate linguistic and computational research on signed languages and the gestural components of spoken languages.

Mostly signal processing of speech.

"Negotiating through SPOken Language in E-commerce" project aims at contributing to the promotion of economic growth in the e-commerce and e-service area by improving speech to speech translation systems. Italian based research project has

European research consortium investigating multisensorial interaction. Two year project examining technologies for speech-to-speech translation, the detection and expressions of emotional states, and core speech technologies for children begins Oct 2

Russian firm offering a large collection of .wav files containing Russian speaker samples on CD. Useful for voice and speech recognition research.

State of the art "Oxygen" project at MIT. Overview of the latest attempts to have useful conversations with a computer.

An unusual method of composing text by speech using shorthand command structures.

Site of the Leuven research group on speech technology (speech recognition, speech coding, speech modification, etc.)

A design for the speech recognition portion of a robot. Source code and theory.

Czech Technical University research focusing on enhancement of speech in the running car environment, speech recognition and to creating of databases of natural language. Demo available for doing spectral subtraction on your own data.

Doctoral research by Richard Stibbard at the University of Reading, England on emotions in human speech and its applicability to speech synthesis.

Links to research projects and publications of Alex Monaghan. Esoteric and sometimes homey.

List of web sites related to phonetics and speech sciences: meetings, research centers, electronic newsletters, journals and publishers

Project is investigating non-visual, speech only user interfaces, especially focusing on how the interface design can make up for errors in recognition. Primarily Finnish lanquage will be used.

Performs speech data collection and transcription in order to assist vendors and researchers in the training and evaluation of speech-recognition systems.

Recognition and synthesis of spoken Indian languages at Tata Institute of Fundamental Research. Speech workshop scheduled for Jan 2003.

An interesting research tool for displaying voice spectra as recorded in .WAV files.

University of Shefield "Moby" project. A public domain word list for several languages, thesaurus, pronunciation guide and the complete works of Shakespeare

Linguistic Data Consortium - an open consortium of labs, companies and universities. It creates, collects and distributes speech and text databases, lexicons, and other resources for speech research and development purposes. Founded by ARPA 1992.

Directory of sites, content, and user groups promoting voice on the web from VoiceXML to SALT.

VoiceXML Italian user group site where Italian VoiceXML developers will find and exchange information, solutions, read news and meet other developers and people interested in VoiceXML and Voice & Speech recognition technology. Mixed English/Itali