Is This the Real Life? Investigating the Credibility of Synthesized Faces and Voices Created by Amateurs Using Artificial Intelligence Tools

The widespread availability and accessibility of artificial intelligence (AI) tools have enabled experts to create content that fools many and needs deep scrutiny to be discernible from reality; nevertheless, it is unclear whether presented with the same tools amateurs can also create synthesized faces and voices with similar ease. The possibility of creating this kind of content can be life-changing for smaller movie makers. Thus, it is important to understand how, can amateurs be supported and guided into creating similar media and how believable are their results. This paper aims to propose a framework that can be used by amateurs to create completely artificial content and investigate the credibility of synthesized faces and voices created by amateurs using AI tools. Specifically, we explore whether an entirely AI-generated piece of media, encompassing both visual and audio components, can be convincingly created by non-experts. To achieve this, we conducted a series of experiments in which participants were asked to evaluate the credibility of synthesized media produced by amateurs. We analyzed the responses and evaluated the extent to which the synthesized media could pass as authentic to the participants. Our findings suggest that, while AI-generated media created by amateurs may appear visually convincing, the audio component is still lacking in terms of naturalness and authenticity. However, we also found that participants’ perceptions of credibility were influenced by their prior knowledge of AI-generated media and their familiarity with the source material. Our findings also suggest that while AI-generated media has the potential to be highly convincing, current AI tools and techniques are still far from achieving perfect emulation of human behavior and speech, when done by amateurs without artistic interference.