IBM Donates Speech Translation Technology to Foster Better Communication and Humanitarian Efforts in Iraq

To add new languages beyond Arabic and Chinese, however, Yuging Gao, the chief researcher behind the project, estimates it would take ten man-years per language.  It is incredibly labor intensive because of the concept matching.  But with a few million dollars of additional funding to add more languages, this could easily find its way into a commercial product in a few years.  And if it could be made to work on a portable device like an iPod or cell phone, every traveler would want one.

Welcome to the Speech at CMU Web Page. Carnegie Mellon University is dedicated to speech technology research, development, and deployment, and we hope this page will be a vehicle to make our work available online. CMU has a historic position in computational speech research, and continues to test the limits of the art.

The goal of the Speech-to-Speech Translation (S2S) research is to enable real-time, interpersonal communication via natural spoken language for people who do not share a common language. The Multilingual Automatic Speech-to-Speech Translator (MASTOR) system is the first S2S system that allows for bidirectional (English-Mandarin) free-form speech input and output.