Juntae, Kim

1. you mean `./speech/timit_coretest` ? It's just one of timit test set. 2. No you don't need to resample the v_addnoise function will resample automatically (but I used 16000.) 3....

@MayMiao0923 The aug parameter adjust the data size, is you set aug larger, you can obtain various types of training data. Because the noise addition and snr selection are randomly...

:) 300 is too much. I usually set 20 for aug value. However, If you have much more dataset than I introduced, 300 will be appropriate.

Yes, In TIMIT document, I found the list of coretest, from the whole TEST, I just selected that coretest files.

@MayMiao0923 Yes. you are correct. The 10 is just for small test dataset. Originally, length(~) you mentioned is correct.

Thank you for your interest to my project, I just used already existed code so that I didn't carefully concern about the difference between the implementation that I used and...

In order to treat memory error you should reduce the length of training wav (.raw file). The default setting is for 64G ram setting.

I think it is because lack of explanation about code structure. As you said, 1 : data feature extraction include preprocess, data input : datareader.py 2 : model for NN...

About your question, 2. Just use your previous produced norm file (not very sensitive to new dataset) 3. I have not met that error before plz compare original code. 4....

Please read readme carefully you can solve that problem from https://kr.mathworks.com/help/matlab/matlab_external/install-the-matlab-engine-for-python.html Thank you