From: dalius on
Hello

I want to know, how to recognize voice by using NN using back-propagation.
My majoring problem is in what term the voice input should be for input layer?
If in image recognition, the input should be in term of pixel, but for voice/audio, what kind of input should i use for input layer in NN.

Please help me on this matter. Thank you :)
From: Greg Heath on
On Apr 15, 2:07 am, "dalius " <fikrulhakimoth...(a)yahoo.com> wrote:
> Hello
>
> I want to know, how to recognize voice by using NN using
> back-propagation. My majoring problem is in what term the
> voice input should be for input layer?
> If in image recognition, the input should be in term of pixel,
> but for voice/audio, what kind of input should i use for input
> layer in NN.
>
> Please help me on this matter. Thank you :)

Correct me if I'm wrong:

Posting this question is easier than wallowing
through the 46 hits you get when you search this
groups archives using the keywords

voice recognition neural
voice recognition nn

Greg