-
Notifications
You must be signed in to change notification settings - Fork 34
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Difference between kaldifeat mfcc feature and torchaudio mfcc feature #87
Comments
Is there a reason to not use |
I think torchaudio receives input in the range [-1,1]. But with |
Is there a reason to not use the same parameters for Also, you are using If you want to produce the same features for the same input, please ensure
|
@csukuangfj, I just updated the python code as above, adding those arguments. The result is unchanged. |
|
Also, have you read and checked the following two points?
|
I strongly suggest that you have a look at You need to find all the arguments of MFCC and compare them with kaldifeat and You need to spend time figuring out the reason by yourself. For instance, you use the default value |
Currently, I am using
torchaudio.transforms.MFCC
to compute features. Now I need to use C++ API of kaldifeat. But I see that the results of the extracted features are different. Here is a script I used:The result is:
The result from
torchaudio.compliance.kaldi.mfcc
is the same as that of kaldifeat, but different fromtorchaudio.transforms.MFCC
.Is there a way to configure kaldifeat so that the result is the same as that of
torchaudio.transforms.MFCC
. Thanks in advance.The text was updated successfully, but these errors were encountered: