Denoising Demo not working
Closed this issue · 5 comments
Hi, it seems like the code in the denoising folder is not up to date. First I received an error that the model file was not found so I renamed that file. Then I received an error that the formulate_data_test function is missing. If I add it (from the timit or TSP folder) I get yet another error:
Error using -
Matrix dimensions must agree.Error in test_denoising_general_kl_bss3 (line 56)
output.source_noise= spectrum.mix-output.source_signal;
The previous error looked like this:
run_test_single_model
Warning: Name is nonexistent or not a directory: ......\codes\denoising\Data
In path (line 109)
In addpath (line 88)
In run_test_single_model (line 7)
Warning: Name is nonexistent or not a directory: ......\codes\denoising\drnn
In path (line 109)
In addpath (line 88)
In run_test_single_model (line 8)
Undefined function or variable 'formulate_data_test'.Error in test_denoising_general_kl_bss3 (line 14)
formulate_data_test(mixture, eI, testmode);Error in run_test_single_model (line 38)
output = test_denoising_general_kl_bss3(x', theta, eI, 'testall', 0);
I will try to fix it myself but if you have time I would appreciate your help. Thank you.
Looks like some path issue. Let me check it later today. Thanks for reporting!
yes I'm still stuck. I can run the other demos though, seems only the denoising does not work. Thanks for looking into it!
Thank you very much. The demo runs and I can also test it on my own sound files. Two more things:
In run_test_single_model you use audiowrite(...,16000) to write the output. I think you should use fs instead of 16000. Otherwise my input files (fs=42000) get messed up.
Is it possible to train a denoising model in an unsupervised fashion (I don't have any labels)? Should I look at the other demos to find out how? I would like to do that because right now the separation from the 870 model is okay but not really that great...
- Thanks. I fixed it: 81bcc53
- It is still a research topic. In the mismatch condition, the performance is worse in the papers.