Neurally-Encoded ASVspoof2019-LA (NE-ASVspoof2019-LA)

NE-ASVspoof2019-LA contains neurally encoded variants of the ASVspoof2019-LA dataset. The dataset accompanies the following paper: L. Cuccovillo, X. Wang, M. Gerhardt, and P. Aichroth, "Neural Encoding Detection is Not All You Need for Synthetic Speech Detection," in IEEE International Workshop on Biometrics and Forensics (IWBF), Sophia Antipolis, France, 2026. The files can be used to replicate the results reported within it, also available online at https://neural-isnt-deepfake.github.io/. The archive is self-contained: it includes neurally encoded variants of all partitions (train, dev, eval), as well as the original and resampled ASVspoof2019-LA trials. Scripts are provided for convenience to recreate the directory splits used in the paper if needed. If you use this dataset, we kindly ask you to cite the paper accordingly: @inproceedings{cuccovillo2026iwbf, author = {Cuccovillo, Luca and Wang, Xin and Gerhardt, Milica and Aichroth, Patrick}, title = {Neural Encoding Detection is Not All You Need for Synthetic Speech Detection}, booktitle = {IEEE International Workshop on Biometrics and Forensics (IWBF)}, location = {Sophia Antipolis, France}, year = {2026},}