akojimaslp / neural-mask-estimation Goto Github PK

Hello, great work.
I would like to know if it is possible to load multichannel audio and perform model prediction and beamforming. For example can i load at the same time 3 audio files which are recorded from different mics on microphone array or can i make wav file with 3 channels in it and then do the prediction. Thank you.

Hi, is there a way to create the training dataset? I mean the approach that you take to get seperate speech and noise data?

Hi @AkojimaSLP ,
When I am exploring the repo, I found that the number of input samples and output samples are different, for example, if I got a 50-second wav audio (800000 samples) and the output will be only 799744 samples. I see it's related to the MVDR beamforming part, do you know why it's happening?
Thank you very much!

Hi,
I tried running the generate_validate_data.py as in the instructions.
it exits with an error: in line 131 the call to "augment.SNR_adjusting" is expecting two input arguments - speech and noise. but only speech is supplied. Perhaps it is a matter of the package's version, I added the noise and it finished running successfully, and i see that some files were created.

It would be very useful if you could specify the versions of the packages you used, and the outputs that should be expected from each of the running stages.
Thank you.