A little GNU/Linux software for vocal recognition and execution of arbitrary vocal commands
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
evilsocket 0058cbc913 Experimental implementation of FDCT. 13 years ago
include Experimental implementation of FDCT. 13 years ago
src Experimental implementation of FDCT. 13 years ago
INSTALL First Voxifera commit 13 years ago
LICENCE First Voxifera commit 13 years ago
Makefile Experimental implementation of FDCT. 13 years ago
README 13 years ago
TODO First Voxifera commit 13 years ago
neutral.ft First Voxifera commit 13 years ago

README

This is BlackLight's and evilsocket's vocal recognitor, and it's damn cool. You teach him
what to do, you say it with your voice, it does it.

Usage: vocal [-d <device>] [-a] [-c <file>] [-h]
-d <device> Use a different device instead the default one (/dev/dsp)
-a Append a new vocal sample with an associated command
-c <file> Use a different rc file (default: ~/.vocalrc)
-h This help

To teach the application a new vocal sample, just launch it with -a option.
You will be asked to say something (at most 2 seconds) and, after a pair of
seconds, the DCT will be calculated on that sample, saved and you will be
asked to type a command to associate to that sample. Then, you can launch
the program just typing ./vocal, and say again what you recorded *AS SIMILAR
AS POSSIBLE TO THE ORIGINAL SAMPLE*. If everything goes alright, your command
will be executed.