The Sphinx Group

The Sphinx Group at Carnegie Mellon University released the DARPA-funded Sphinx projects in order to stimulate the creation of speech-using applications and tools. The projects mission was to advance the state of the art both directly in speech recognition, as well as in related areas including speech synthesis and dialog systems

The packages that the CMU Sphinx Group developed are a set of reasonably mature, world-class speech components that provide a basic level of technology to anyone interested in creating speech-using applications without carrying the burden of an initial investment cost in research and development. Moreover, the same components are open to review by all researchers in the field and are used for linguistic research as well

SPHINX is one of the best and most versatile recognition systems in the world today. It is an HMM-based system, like all other speech recognition systems, that functions by first learning the characteristics or parameters of a set of sound units, and then using what it has learned about the units to find the most probable sequence of sound units for a given speech signal. The process of learning about the sound units is called training. The process of using the knowledge acquired to infer the most probable sequence of units in a given signal is called decoding, or simply recognition

cmusphinx.sourceforge.net/html/cmusphinx.php