A big vocabulary continuous speech recognizer with speaker independence, CMUSphinx was made available under a BSD-style license. Additionally, it is a collection of free and open-source materials and tools that help academics and developers create voice recognition systems.
The collective name for the series of voice recognition systems created at Carnegie Mellon University is CMU Sphinx, sometimes known as Sphinx for short. These contain an acoustic model trainer and a group of speech recognizers (Sphinx 2–4). (SphinxTrain).
Sphinx 2 and Sphinx 3 were two speech recognizer components that the Sphinx group at Carnegie Mellon promised to making available as open source in 2000. (in 2001). Sample applications and acoustic models are included with the speech decoders. Software for acoustic model training, language model compilation, and other resources are also available.
