Free Limited Experimental Voice Recognition Software
By Dr. Jim on Sep 18, 2009 | In Welcome
Dr. Jim will be releasing a free version of his Voice Recognition software in the fourth quarter of 2009. It should run on any Parallax Propeller system.
Users will need to build the microphone amplifier and the Carrier Wave Removal hardware for this to work. Schematics will be provided.
Since memory on the Propeller is quite confined (32K RAM), this will be a limited, experimental version. There should be enough memory for about 10 spoken words.
Speaker independence is what we are striving for, so anyone should be able to speak to it and the Propeller respond on-screen.
It will be severely limited not only in terms of RAM and therefore number of words, but also, users will not be able to save new words.
It will be a binary release only.
There will be a page or two of instructions included to assist users. This will be bundled with the binary and the schematics and zipped. You will be downloading a single zipped file.
The free version of Dr. Jim's Voice Recognition software should allow users to observe that the technology works before purchasing the system (hardware and software combined).
The full version will require a modified Propeller Proto USB board, at least one 2MB memory expansion board (two would be better), a datalogger, and will be able to support multi-terrabyte hard drives for permanent storage.
This amount of storage should be enough to allow for most and possibly all the words in all the spoken languages on earth to be stored. The system should be able to learn and respond to multiple languages.
There is no time limit to the offer of the free version. Anyone may download and use this for as long as they like.
We will post again when we have the download link live.
Thanks for your interest.
Mark Allred
Machine Intelligence Technologies
support@machineinteltech.com
| « Spam Problems on the Blog | Dr. Jim Solicits Programming Talent » |