Deep Learning and Synthetic Media
This work addresses conceptual and taxonomical issues in media studies for researchers and practitioners, but it is incremental as it builds on existing discussions without introducing new empirical results.
The paper examines how deep learning algorithms are transforming audiovisual media production, particularly synthetic media like 'deepfakes', which are easy to produce and can be indistinguishable from real recordings, and argues that these methods challenge traditional taxonomical distinctions and enable novel kinds of media.
Deep learning algorithms are rapidly changing the way in which audiovisual media can be produced. Synthetic audiovisual media generated with deep learning - often subsumed colloquially under the label "deepfakes" - have a number of impressive characteristics; they are increasingly trivial to produce, and can be indistinguishable from real sounds and images recorded with a sensor. Much attention has been dedicated to ethical concerns raised by this technological development. Here, I focus instead on a set of issues related to the notion of synthetic audiovisual media, its place within a broader taxonomy of audiovisual media, and how deep learning techniques differ from more traditional approaches to media synthesis. After reviewing important etiological features of deep learning pipelines for media manipulation and generation, I argue that "deepfakes" and related synthetic media produced with such pipelines do not merely offer incremental improvements over previous methods, but challenge traditional taxonomical distinctions, and pave the way for genuinely novel kinds of audiovisual media.