Run./scripts/dowloads.shin order to download 3 utility files, which is necessary to preprocess AVA-ActiveSpeaker dataset. Download AVA videosfromhttps://github.com/cvdfoundation/ava-dataset. Extract the audio tracksfrom every video in the dataset. Go to ./data/extract_audio_tracks.py inmainada...
The absence of a large, carefully labeled audio-visual active speaker dataset has limited algorithm evaluation in terms of data diversity, environments, and accuracy. In this paper, we present the AVA Active Speaker detection dataset (AVA-ActiveSpeaker) which has been publicly released to facilitate...