How deepfake is your voice? Understanding the linguistic foundations of deepfakes is a research project (grant PID2021-124995OA-l00 funded by MICIU/AEI/10.13039/501100011033 and by ERDF/EU).
We investigate how to bridge the gap between:
(1) the latest research in Artificial Intelligence and automatic system design to avoid spoofing attacks, and (2) the linguistic-phonetic knowledge that can be used to distinguish real voices from fake voices.
Our aim is to help detect fake audios, which have a negative impact on forensic contexts.