About audio feature extraction of Voxceleb1

[DaddyJin]

Thank you for the great work! I follow the instruction mentioned in First-Order to download the videos and crop them for train and test. However, in audio driven generation, the audio signal is needed. I am wondering if you could share the details of how you pre-process the audio signal of VoxCeleb videos, such as audio feature extraction, audio-visual feature correspondence，feature storage and so on. Thank you in advance!