Carnegie Mellon

Speech Software

Carnegie Mellon has developed speech software for all aspects of recognition, including signal processing, acoustic model training, language model training, decoding, spoken language parsing and interface building. We make this software available either through an industrial consortium program or to educational institutions as part of the Portable Speech Library.

The Carnegie Mellon Speech Group also makes available a variety of public domain speech resources, which is described elsewhere.

More information may be obtained from Alexander Rudnicky.