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:  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  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
Steps to reproduce
This dataset can be used to train a machine learning system to classify original and fake voice recordings obtained with the imitation algorithm.