I'm working on an honors contract for school to make a neural network that can recognize a word when spoken - I've got the network as prepared as I can without understanding how to get audio input.

I've looked some stuff up already, but most of it either doesn't actually relate or has answers that are drowning in acronyms and concepts that I don't understand yet. Could anyone provide me with a link or file that has sample verilog code for basic input from the mic in port of a Cyclone V board?

Preferably it would also show how to properly format the output of that for the input of an FFT, but really any part of it or even a good starting point would be greatly appreciated!