I'm new to speech recognition. I would like to ask after generating
MFCC, we get the coefficients. What do these coefficients means? Do
they represent the amplitude of the speech signal accordingly?
Can LPC vocoder use for speech recognition? Is this method better than
LPC and LPCC? or even MFCC? bcos after trainned them with neural
network. THe result i got compared to MFCC, LPC vocoder showed better
result.
Can anyone pls clarify me as what i have found in the internet is too
complicated to understand. Thanks alot.