Closed yannhan closed 5 years ago
Change the timit path to your own location, then run run.sh
, you will get the 41-dim log-mel filter-bank feature with anergy.
feature_transform.sh
here is to calculate the global cmvn stats using 3 window context on 41-dim feature with delta and delta-delta.
So I need to install Kaldi first?
Yeah, kaldi is necessary to reproduce the results exactly. But it only used for feature extraction, maybe librosa is easier to use.
Thanks, HawkAaron, I have extracted the features, but during trainning, I came across this bug : I used the other datasets, maybe this is the problem. But I can't use TIMIT since this dataset is not free. I don't know why the dimension is not correct. The batch size is 1, the input feature dimension of one sample is 199x90, the label dimension is 21x1. Both type are np.array.
The batch dimension for input and label should be the same. For your example, the input should be shaped [1, 199, 90], the label should be shaped [1, 21]. Both are mxnet ndarray.
I modified the type, but the bug still exists.
Could you show me the inputs' shapes before the loss function call ?
Okay, the first figure is the corresponding code, the second is the output. Is that you wa
nt?
BTW, I also found another thing. In the code, f and g should have the same size except the last dim, right? But I found f and g are same size including the last dim....
I have updated the code, you can try it now.
Thanks very much!
Hi, I'm very new in this field. Could you please help me how can I download the TIMIT dataset? I tried to download the dataset from (https://catalog.ldc.upenn.edu/LDC93S1), but unfortunately I can't find the download link. Could you please help me Thanks in advance Atefeh
Excuse me, could you show how to use the Kaldi-timit scripts in your source code?