Technical discussions about the implementation and research of speech recognition algorithms.
I'm new in this.i would like to ask a simple question here which i couldn't find in the internet. After generating the MFCC, we get the coefficients. Wat do all the coefficients represent? Do they represent the amplitude of the sound signal accordingly? If i wan to do a speech recognition, can i use a LPC vocoder? Is LPC vocoder better than LPC or LPCC? I hope someone can clarify me as what i found in the internet is too complicated for me to understand. Thanks alot..