You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
By checking the data generation scripts it appears to me that the noise and RIRs are not splitted between train, validation and test.
I may be wrong though.
If this is the case this should be corrected.
EARS is a great work and it is very useful to the community but EARS-WHAM and EARS-reverberant right now should not be used IMO because of the potential overfitting of reverb and noises ?
Again, I could be wrong I am just looking at the scripts.
The text was updated successfully, but these errors were encountered:
By checking the data generation scripts it appears to me that the noise and RIRs are not splitted between train, validation and test.
I may be wrong though.
If this is the case this should be corrected.
EARS is a great work and it is very useful to the community but EARS-WHAM and EARS-reverberant right now should not be used IMO because of the potential overfitting of reverb and noises ?
Again, I could be wrong I am just looking at the scripts.
The text was updated successfully, but these errors were encountered: