Closed c8x1 closed 1 year ago
@c8x1 Could you provide the test audio samples you used?
sry i cant provide them because of privacy reasons. its just some real captured audio. But the audio itself is not special. I blame it on the lack of stability of the filter, maybe some post-processing.
I tried to reproduce your results, but I found that there are two phenomena (bad results) in some real sequences, both of which also appear in the model you provide.
Did you find anything like this?