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
It has been commented that the transformation to image lacks low frequencies.
This is completely true, and a really tedious flaw.
However, the problem is quite clear. mel_scale_norm off removes bass and keep treble (Default). ON, less treble and keep bass. There is no middle ground.
And that is the question. Isn't there a way for the spectrogram to just keep both halves of the image at the same dynamic range? I mean, such a distortion has no useful reason to exist in the first place.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
It has been commented that the transformation to image lacks low frequencies.
This is completely true, and a really tedious flaw.
However, the problem is quite clear. mel_scale_norm off removes bass and keep treble (Default). ON, less treble and keep bass. There is no middle ground.
And that is the question. Isn't there a way for the spectrogram to just keep both halves of the image at the same dynamic range? I mean, such a distortion has no useful reason to exist in the first place.
Beta Was this translation helpful? Give feedback.
All reactions