NeuroAI - Data-Driven Dynamical Systems Research Group

Hello hsuankai, You can find the list of videos included in the training dataset in the data.zip file. The filename is list_of_recital_videos.txt. You can find instruction on how to download...

Hello zhuhaozh, You can find the list of videos (audio and frames) included in the training dataset in the data.zip file. The filename is list_of_recital_videos.txt. You can find instruction on...

Hello chuangg, You can find the list of videos (audio and frames) included in the training dataset in the data.zip file. The filename is list_of_recital_videos.txt. You can find instruction on...

This is just a sample of videos. We cannot supply their raw data or references as this is third party data, but you have several alternatives: 1. Re-train the network...

We compute MFCC features on stereo 44.1Khz sample rate audio. For each audio source, we perform RMS normalization to 0 dB using FFMPEG and choose the window length as 1000/videofps...