AFAIK, GANs are used for generating/synthesizing near-perfect human faces (deepfakes), gallery arts, etc., but can GANs be used to generate something other than images?


They can indeed. Although generally they are kept to images because at the moment, they are the best at that, but not the best in other areas that you might consider.

GANs can be used for audio generation, with many examples such as GANsynth and GAN voice generation. But each of these tasks are outperformed by other methods. With music generation, WaveNet is the best (last I checked, and it also performs very well at speech synthesis), and a more powerful model for voice generation is achieved through the use of a VAE.

This is only looking at one area that you could use GANs for, because in reality you could use them for any kind of generation if you wanted to, but at the moment the vast majority of the research into GANs is into image generation, and as such other areas do not compete with the current SOTA techniques, unless there's some big paper I've missed within the last few months.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.