Giters

andrewowens / multisensory

Code for the paper: Audio-Visual Scene Analysis with Self-Supervised Multisensory Features

Home Page:http://andrewowens.com/multisensory/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How to calculate SDR?

ruizewang opened this issue · comments

commented

Hi Andrew,
What tool did you use to calculate SDR?
Thank you :)

commented

There is another question about calculating SDR.
For example, given a video, the mixed audio shape is (173774, 1). However, your sep model outputs a audio with shape (173040, 1). The length of these two audios is not the same (173774!=173040). So this causes difficulties when calculating SDR. May I ask how you solved it?