How to align video audio with text data?
mrFocusXin opened this issue · 0 comments
mrFocusXin commented
I have been paying close attention to your research trends. You and your team did a lot of excellent related work and gave me a lot of inspiration. I would like to ask you that How do you align video audio with text data? Because I found that the length of audio features and video features had been pre-processed to be the same length as text.