CMU Sphinx is an Open Source Speech Recognition Engine software that allows users to convert spoken language into text.
If you're looking for an Open Source Speech Recognition Engine, look no further than CMU Sphinx. Developed by the Sphinx Group at Carnegie Mellon University, this tool is designed to help stimulate the creation of speech-using tools and applications while advancing the state of the art in speech recognition, dialog systems, and speech synthesis.
Supported by funding from the Defense Advanced Research Projects Agency, Sphinx is based on recognition engines that have been used for various DARPA projects and their respective evaluations. Recent support for the project comes from Telefnica I & D, Sun Microsystems, and Mitsubishi Electric Research Labs.
The licensing terms for Sphinx are derived from BSD and based on the license for the Apache web server, with no restriction against commercial use or redistribution. The packages that the CMU Sphinx Group is releasing are a set of mature, world-class speech components that provide a basic level of technology for creating speech-using applications without the prohibitive initial investment cost in research and development.
It's important to note that Sphinx is not a final product, and issues can arise. Users with a certain level of expertise can achieve great results with the versions of Sphinx available here, but a naive user will certainly need further help. In other words, this software is not meant for users with no experience in speech, but for expert users.
This site will be the go-to location for the release of the Sphinx trainers, recognizers, acoustic and language models, and documentation. Give it a try if you're looking for a powerful speech recognition tool.
Supported by funding from the Defense Advanced Research Projects Agency, Sphinx is based on recognition engines that have been used for various DARPA projects and their respective evaluations. Recent support for the project comes from Telefnica I & D, Sun Microsystems, and Mitsubishi Electric Research Labs.
The licensing terms for Sphinx are derived from BSD and based on the license for the Apache web server, with no restriction against commercial use or redistribution. The packages that the CMU Sphinx Group is releasing are a set of mature, world-class speech components that provide a basic level of technology for creating speech-using applications without the prohibitive initial investment cost in research and development.
It's important to note that Sphinx is not a final product, and issues can arise. Users with a certain level of expertise can achieve great results with the versions of Sphinx available here, but a naive user will certainly need further help. In other words, this software is not meant for users with no experience in speech, but for expert users.
This site will be the go-to location for the release of the Sphinx trainers, recognizers, acoustic and language models, and documentation. Give it a try if you're looking for a powerful speech recognition tool.
What's New
Version 1.0: N/A