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

2 次查看（过去 30 天）

sai susmitha 2016-12-28

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/318366-regarding-training-ann-bpnn-rnn-with-13-inputs-about-target-vector-format

评论： sai susmitha 2017-1-3

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

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

sai susmitha 2017-1-3

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

请先登录，再进行评论。

请先登录，再回答此问题。