Regarding Training ANN(BPNN,RNN) with 13 inputs about target vector format

for speech recognition,in training phase we get mfcc coefficients but what is the target vector we use if we have to classify into 3 different classes ,please can anyone help me out of this i.e for each time for each 13 coefficients as 13 input layers then for each 13 coefficients what is the target vector format or else how to train the classifier

[sai susmitha]

I wanted to ask that when we extract mfcc's for a wave(audio) file then it gives a matrix of [no.of frames x 13]if each frame has 13 mfcc's now if to train a classifier using these(here Ann) then what is the input of BPNN classifier should i convert this matrix(what i got after extraction) into 1 x 13 then for each wav file we finally have only this one representation(1x13)and for training the target vector format would be [1 0 0] if i am classifying it into 3 classes each wav file i put target vector as 1 in the desired class and 0 in others if input is not 1x13 i.e (no.of framesx13) then what is target vector format