Welcome to the AT&T Speech Mashup Manager website. This is where you register for an account to begin building speech mashups.
A speech mashup is a web service that implements speech technologies, including automatic speech recognition (ASR) and text to speech (TTS) for speech-enabled applications running on iPhones, BlackBerrys, or any other networked device. In a speech mashup application, audio and text from the client are forwarded to the AT&T network where servers running the AT&T WATSON (SM) ASR and the AT&T Natural Voices (TM) TTS - the same speech technology employed for enterprise customers of AT&T - perform the speech processing.
To begin building speech mashups, click the link to create a new account.
For further reading about speech mashups, click here.
Giuseppe Di Fabbrizio, Thomas Okken, Jay Wilpon, Speech
, Semantic Mashups - Intelligent Reuse of Web
, Springer Science+Business Media, New York, May,
Alistair Conkie, Yeon-Jun Kim, Thomas Okken, Giuseppe Di
Fabbrizio, Building Text-To-Speech Voices in the Cloud
eighth international conference on Language Resources and
, Istanbul, Turkey, May 21-27, 2012.
Michael Johnston, Giuseppe Di Fabbrizio, Simon Urbanek, mTalk - A Multimodal Browser for Mobile
Annual Conference of the International Speech Communication
Association (INTERSPEECH 2011)
, Florence, Italy, August
Yeon-Jun Kim, Thomas Okken, Alistair Conkie, Giuseppe Di
Fabbrizio, AT&T VoiceBuilder: A Cloud-based
Text-To-Speech Voice Builder Tool - demo paper
, 12th Annual Conference of the International
Speech Communication Association (INTERSPEECH 2011)
Florence, Italy, August 28-31, 2011.
Giuseppe Di Fabbrizio, Jay G. Wilpon, Thomas Okken, A Speech Mashup Framework for Multimodal
, The Eleventh
International Conference on Multimodal Interfaces and Workshop
on Machine Learning for Multi-modal Interaction (ICMI-MLMI
, Cambridge, MA, USA, November 2-6, 2009.
To download documentation and sample code or to ask questions or provide feedback, email firstname.lastname@example.org.
For demonstrations of applications built with speech mashups, see these links: