Hello,
All modern Operating systems have a voice reco nowadays.
Although Vista got some issue with it, but anyhow.
http://www.zdnet.com/blog/ou/vista-s...te-exploit/416
Apple is also strong in this direction.
Linux has sphinx 2 into the repositories, and you can use wine with Dragon Naturally Speaking. It works but no so well, since the performances of the reco depends on the CPU.
Then there are few little projects for Linux, which could be discontinued in the future (requiring Kde, e.g. Symon, or others).
In a CLI method, for backend, how would you compare two files?
Here we go:
first one, I record a voice speech "Hello" with my usb mic
Code:
cd ; arecord -Dplughw:0,0 -f cd -vv hello.wav
and second one, saying "good morning!"
Code:
cd ; arecord -Dplughw:0,0 -f cd -vv secondwav.wav
How would you compare it with a CLI program that compares their amplitudes or that "hello" is into secondwav.wav yes or not ?
- Reply : no solutions. Wait 10-15 years.