An RFP Dataset for Real, Fake, and Partially Fake Audio Detection

Recent advances in deep learning have enabled the creation of natural-sounding synthesised speech. However, attackers have also utilised these technologies to conduct attacks such as phishing. Numerous public datasets have been created to facilitate the development of effective detection models. However, available datasets contain only entirely fake audio; therefore, detection models may miss attacks that replace a short section of the real audio with fake audio. In recognition of this problem, the current paper presents the RFP dataset, which comprises five distinct audio types: partial fake (PF), audio with noise, voice conversion (VC), text-to-speech (TTS), and real. The data are then used to evaluate several detection models, revealing that the available detection models incur a markedly higher equal error rate (EER) when detecting PF audio instead of entirely fake audio. The lowest EER recorded was 25.42%. Therefore, we believe that creators of detection models must seriously consider using datasets like RFP that include PF and other types of fake audio.