Contains ~22k real audio from the FMA medium dataset and 18k generated audio from the FakeMusicCaps dataset. All audios are preprocessed in .mp3 format. Sampling rate is 16k Hz and bit rate is 215 kb
This dataset is the development set of the Codecfake dataset, corresponding to the manuscript "The Codecfake Dataset and Countermeasures for Universal Deepfake Audio Detection". Abstract With the pr
