Fake voice recordings (Imitation)

This data set consists of recordings of original voice and fake voice recordings obtained by imitation [1, 2]. The voice recordings provided in this dataset can be used to train a machine learning system to classify original and fake voice recordings obtained with the imitation algorithm.
Each directory has the following composition:

Fake_audios: 50 voice recordings of fake audios obtained by imitation
Key_fake_audios: 50 keys to reverse the process and obtain the original voice recording
Original_audios: 50 original voice recordings
readme.txt: this Matlab code allows recovering the original voice recording from the fake voice recording.

References:
[1] DM Ballesteros L, JM Moreno A. Highly transparent steganography model of speech signals using Efficient Wavelet Masking. Expert Systems with Applications 39 (10), 2012, 9141-9149, https://doi.org/10.1016/j.eswa.2012.02.066
[2] DM Ballesteros L, JM Moreno A. On the ability of adaptation of speech signals and data hiding, Expert Systems with Applications 39 (16), 2012, 12574-12579, https://doi.org/10.1016/j.eswa.2012.05.027