Open KiAlexander opened 4 years ago
and the result calculated by pb_bss_eval
{'input_pesq': 1.5960057377815247,
'input_sar': 11.243911897495014,
'input_sdr': -0.5471245564855747,
'input_si_sdr': -0.7163815595640699,
'input_sir': 0.14099714373415928,
'input_stoi': 0.662681954751808,
'pesq': 2.596807837486267,
'sar': 6.761317115018516,
'sdr': 6.659954133819946,
'si_sdr': 5.684012353271584,
'sir': 23.99486035934128,
'stoi': 0.8663816779000003}
Hey thanks for reaching out. I am kind of trying to catch a deadline so I did not check my github issues. It seems that your code is fine. Surprisingly there is a bug probably with the uploaded sources. If you listen to both the estimates and the actual sources you could actually hear that the sources and the mixture sound very noisy. However, the estimation seems to be quite better quality with much less artifacts. Moreover, I have actually used this code to produce some audio examples https://github.com/mpariente/asteroid/tree/master/egs/wham/TwoStep which might also contain this noise because of the wham dataset. I am gonna take a look at this, hopefully in a few days.
I try to test my codes which calculate sdr with your separate samples(ex_18).
In my sdr codes, the result is about 6.47 while yours is 19.37.
can you help me find out anything wrong in my codes? Thx.
the codes are as follows.
And ouput: