The result was Draft:Media synthesis (AI). The article has been moved to the draft space. Thanks everyone for participating and assuming good faith! Missvain (talk) 16:31, 29 January 2020 (UTC)
[Hide this box] New to Articles for deletion (AfD)? Read these primers!
A NEOLOGISM grouping a number of concepts that does not appear in multiple reliable independent in-depth sources to satisfy GNG. The only source that I see that uses the term "media synthesis" is a blog post written by the author of the article. In fact, the only search hits appear to be posts by the author. To me, this fails NOTESSAY.
The article is severely-BOMBARDed by sources that are only relevant to the topic because the article claims so. In other words, it is SYNTHesis of sources grouping various concepts under the label, even though none of the sources for those concepts deliberately use the term "media synthesis". As it appears, it's an invented concept by the author (and likely falls under WP:CSD#A11).
The author also created Category:Media synthesis. They also appear to have gone through other articles and added mentions of the term and category (e.g. [1]), none sourced as far as I can see. This has gone a little beyond WP:BRD and brings up FAITACCOMPLI issues. However, the resolution of this AfD should hopefully also resolve whether category or these other mentions are suitable (I do not believe they are, but I rather not revert en masse).
The article was moved out of draft space, so not re-incubating it. (The author did not resubmit the draft, so there was no chance to review it.) I assume CSD/PROD would be contested (especially since there are so many sources at a glance), so going with full AfD. — HELLKNOWZ ▎TALK 11:55, 22 January 2020 (UTC)
The primary issue with the Media Synthesis article is that I did indeed create the current term before a more widely used and very highly similar term, "synthetic media", was coined. If you may, I'll provide at least 50+ links to articles (including official government documents) that use this term and even define it much the same way. Most notable is the Congressional Deepfake Report Act. My primary reasoning for using the term "media synthesis" was more due to grammatical rules. If it is more prudent to rename this article "Synthetic Media (AI)", it very well should and ought to be done.
As the page is still largely under construction, a number of these sources are to be added as time goes on and the article is further cleaned up.
In regards to moving the page from draft to mainspace, I've been told multiple times by others that this is something available to a user who is autoconfirmed, that I need not wait for administrative approval if the article is already complete. If this is the wrong move, please correct me. I did indeed resubmit the draft, at least over a month ago, and had been patiently waiting for its approval. It was only recently when I was (perhaps erroneously?) informed that I need not wait in the first place if I was not an anonymous user.
Rather than deletion, my personal final verdict is to rename Media Synthesis (AI) to Synthetic Media (AI) and add the proper sources to justify the name. --Yuli Ban (talk) 14:25, 22 January 2020 (UTC)
In regards to further instances of the usage of "synthetic media", I'll simply post ten links just to not clutter up the page. Hopefully this re-establishes the argument towards renaming the article:
All of these articles both mention the term "synthetic media" as well as define it in some capacity, with the most basic being "AI-generated media" (hence the alternate titles for the article). They also refer to "synthetic media" as having multiple branches, of which the likes of deepfakes and human image synthesis are individual branches. Thus, it can be ascertained that at least most of the central argument of the Media Synthesis (AI) page is still applicable.
Also, my reasoning for using multiple tangentially-related sources derives from the central reasoning that "media synthesis" refers to a family of processes of applied computational creativity and algorithmic generation; therefore, image synthesis and procedural generation alike qualify.[1] --Yuli Ban (talk) 14:39, 22 January 2020 (UTC)
References
A few more points of contention:
1: Synthetic media is media synthesis. As mentioned, I created the latter term a good bit of time before the former became widely used. Both refer to the exact same thing. In fact, when I first created the term "media synthesis," calling it "synthetic media" was one of my options, but I decided against it due to it being a noun adjunct. Now I see that "synthetic media" is the more widely used term anyway.
2: Synthetic media is not perfectly synonymous with deepfakes. To use even more sources, it describes everything you've mentioned as an unbrella term for all these different sources. This is how it is usually used: separately from deepfakes, often placed over it to describe a family of different but related techniques (including speech synthesis, natural language generation, music synthesis, etc.)
See more:
My final assertation remains: Media Synthesis (AI) can be moved directly to Synthetic Media (AI) with added sources, but should not be deleted or greatly culled. Yuli Ban (talk) 15:50, 22 January 2020 (UTC)
I do thank you for your assistance, however. All I really wanted this entire time was added help in clarifying the fundamental concepts and finding any flaws, holes, or poorly-expanded research, especially to assist in establishing a clearer centralized terminology for all related technologies deemed "synthetic media." This entire time, I worried that the lack of usage of "media synthesis" in the sources would prove to be a problem right up until I discovered that "synthetic media" was used in increasing amounts. By that time, however, the original article was already mostly complete. To expand upon my reasoning, the intention was that references to sub-branches of synthetic media (e.g. speech synthesis, natural-language generation, procedural generation, human-image synthesis, etc.) were enough to be used. Of course, now I see that there is a rule against synthesized sources. That the term "media synthesis" was my own and I was the primary source for it was also a worry when originally drafting the article last year, and in fact was the reason why it was not drafted sooner: the intention was to write it as early as the fall of 2018, but I feared self-authorship would lead to deletion. It was only when constant efforts to get others to take the initiative failed to materialize anything tangible that I decided to act. As a result, I've had very few to no other persons actually helping me prune or refine details. Considering the subject matter, urgency of the debate, short and long-term implications, and rapid development of the technology, it would be very unfortunate for the article to be outright deleted, especially since the primary issue is entirely the name of the article itself and that rectifying it (plus adding the proper sources for the terminology) would clear it of any further issues. Indeed, perhaps the #1 reason for the article's creation was to help raise awareness for this burgeoning field of technology (which is why it was soon turned into a category, with another intention being to use it as a basis for navboxes and portals in the future).
Yuli Ban (talk) 20:09, 22 January 2020 (UTC)
Author here: The fundamental issue is that "deepfake" in its current form describes a method of face-to-face style transfer, which is indeed a kind of synthetic media, but doesn't describe the full gamut of synthetic media itself. Think of it as being similar to the difference between subgenres of hard rock music, and how "death metal" is a kind of hard rock but wouldn't accurately suffice to describe the entirety of hard rock music. Or, perhaps more on topic, how "machine learning" describes a subfield of artificial intelligence but would not be sufficient to describe the entirety of the AI field. In terms of scientific research and data science, "deepfakes" does not refer to all sorts of algorithmic media generation. Even colloquially, it is only used as a source of comparison (i.e. "the deepfakes of [X]" or "deepfakes for [X]"), which implies that deepfakes is being used more to patch for a lack of a central terminology. There has also been some developments in making deepfakes work for voices. Thus, deepfakes describes swapping between two media, principally video and audio.
Synthetic media, thusly, is the parent "catch-all" term and principally refers to any sort of applied usage of AI-generated data/media. This means it includes deepfakes, but also things unrelated to deepfakes (such as text synthesis, music generation, speech synthesis, etc.) Since "deepfakes" is used predominantly to describe face-swapping, using it interchangeably with synthetic media tends to cause too much confusion, hence why publications often point out that deepfakes are merely a kind of synthetic media or that deepfakes is "the most prominent form of synthetic media. This implies that there is more to synthetic media than just deepfakes. Indeed, they will usually reiterate what I have said: synthetic media refers to any "AI-generated, enhanced, or manipulated media or data." It is often mentioned that this goes for video, image, text, and voice; the implication is that any media whatsoever can be generated. "Synthetic media" encompasses the same scope as "media synthesis," perhaps losing Procedural generation only due to a lack of sources currently combining the terms.
There are some more papers and articles that go a bit more in-depth. If the article remains (but is renamed), Synthetic media (AI) would become the basis for a navbox, and Deepfake would be a link within in a "Video" or "Image" cell, separate from something like Pop music automation and natural language generation.
Or to use an active example, my voice and face being swapped for Sirfurboy's for use by HELLKNOWZ is a deepfake. This, as well as Sirfurboy generating a new, novel face via human-image synthesis and then generating a short story to go along with it via OpenAI's GPT-2 transformer, would all qualify as "synthetic media." This new person who does not exist could then be made to sing via MIDI files or waveform manipulation (set to an AI-generated song), and this quasi-music video could be made interactive if a neural network generated video game assets and the proper coding instructions (not unlike NVIDIA's work here). All of such, too, is synthetic media. Swapping the AI-generated person for another AI-generated person via autoencoding methods, however, would qualify as a deepfake. Generating a new person would not be considered a deepfake in technical terms, but might be referred to it in the media by some publications. Or it would be compared to deepfakes, but formally considered something different.
At this point, it seems the primary issue at hand is more whether to rename the article to Synthetic Media; we've all established well that the term does exist, and I have been trying to explain why it is not synonymous with deepfakes. I'm fully in support of doing this and editing all the outgoing links & category page.
Yuli Ban (talk) 23:15, 22 January 2020 (UTC)
I've decided to go ahead and begin work on Synthetic Media (AI) as a replacement article, reworking most aspects from the ground up to better tie everything directly to "synthetic media." Since I've saved/downloaded the page, media synthesis can be nuked. There are thus only three hang-ups:
1) Synonyms. "Synthetic media" and "AI-generated media" are perfectly synonymous (the definition of synthetic media is that of autonomous algorithmic generation of data/media), so the question here would be whether or not a report and paper on "AI-generated media" that nevertheless does not contain the term "synthetic media" would qualify as a suitable source. It seems obvious and uncontroversial to me that this would be the case, especially since the term was largely unused by the media before 2019, but the exact same principle was described via "AI-generated [i.e. synthetic] media". This is likely the only instance where I'll see any feedback from others and would like some alternative input. This would greatly ease finding sources, but it's also a very fuzzy area that really comes down only to the minutia of language. No source I've found, from blogs to scientific papers to government documents, lists any separation between "AI-generated media" and "synthetic media" and indeed often very explicitly state the latter is the former.
2) Applications, concerns, and impacts. Admittedly, this could use culling to remove some of the more personal takes on long-term implications to keep it purely down to the facts, but a primary issue with all of these is that, since they all describe sub-branches of synthetic media even as defined by many other outlets, at least some ought to remain.
3) Existence as a category. Seeing as synthetic media is supposed to describe a very wide range of different technologies (and as the term becomes more prominent, it will almost certainly be used by articles, papers, and documents to describe whatever currently "doesn't fit" the term as per this page's discussion thus far, so the article will eventually refill to the same level as the previous one), its existence as a category seems obvious to me, but again, I'd like alternative takes before making a decision.Yuli Ban (talk) 05:31, 23 January 2020 (UTC)