An informal poll of practitioners is likely to reveal a ‘pre-acceptance’ of voice recognition technology in medicine. Doesn’t the open source model fail in such a prorietary area with high lucrative potential? How does open source do on this important technology? Very well, thank you. Carnegie Mellon’s voice-recognition Sphinx project is open source. The currently available Sphinx2 is described as a ‘…candidate for handheld, portable, and embedded devices, and telephone and desktop
systems that require short response times.’ Sphinx3 which should be available ‘in 2000’ is described as a ‘…slower, yet more accurate recognizer used, for example, for broadcast news transcription…