Carnegie Mellon make its speech recognition software available to industrial partners through the Speech Consortium. We provide royalty-free source code for all components of a speech recognition system, including decoding, spoken language parsing, training of acoustic and language models, as well as robust signal processing. All material produced in ongoing research projects are available to Consortium members. You may be interested in a short overview of our research program; but for a more up to date glimpse at our activities, browse our website.
We have a flyer that describes the current organization of the Consortium. Recently, in response to the needs of smaller start-up companies, we have developed a royalty-based option for Consortium membership.Please contact us for details.
Depending upon the circumstances, we may also be interested in pursuing joint projects with industrial groups.
If you're interested in obtaining more information, please send us your mail address and we will send you some materials that describe the Consortium. You may also reach us as follows:
Dr. Alexander Rudnicky
Director, Speech Consortium
School of Computer Science
Carnegie Mellon University
5000 Forbes Avenue
Pittsburgh PA 15218
+1 412 268 2622 [voice]
+1 412 268 5576 [fax]