211–220 of 311 posts
Earlier quoted context omitted.
Woah that's kinda scary. What could we do to determine if a video is legitimate or not?
Mainly, practice critical thinking. Don't take anything at face value until it has been reconfirmed from many sources. At least that's what I do.
If they can pull this off with the API, this is worth millions of dollars on the table.
1. Is this company new? 2. Is this better then what Google or Baidu are doing? 3. I remember reading Adobe has something similar. 4. Why ( What happened ) that all of a sudden we have 4 company making voice breakthrough tech like these? 5. What Happen to Voice Acting? Places like Japan where they highly value voice actor. Is Voice even patentable?
2) Possibly. Google and Baidu have compute resources far beyond a university. This method might be better, and do well with more resources.
3) Adobe's method required far more input data. This apparently requires only 1 minute of your audio to start sounding like you.
4) Deep learning has revolutionized vision, and language processing for a while. It was just a matter of time before people started applying those methods on speech data, with similar surprising results.
5) It will be hard to capture human elements like "emotion" and tone via generative models. Maybe in the future the work will become sophisticated enough to be indistinguishable from human speech, but right now there are some telltale signs that it is artificially generated.
1. Open source voice-copying software
2. At worst, create entire market of voice-fraudsters, at best, very few voice-fraudsters but very high and very real perception of fear of such
3. Become leading security experts in voice fraud detection
4. Sell software / time / services to intelligence agencies, governments, law enforcement, news networks
Ethically I'm a bit concerned with (2), but realistically the team is right --- this technology exists, it will certainly be used for good and for bad, and they're positioning themselves as the leading experts.
I'm interested to see which VCs and acquirers line up here. Applying a voice to any phrase seems useful for voice assistants (Amazon Alexa, Google Home) but I don't think that's the $B model.
I built a toy concatenative Donald Trump speech system [1], but I don't have an ML background. I've been taking Andrew Ng's online course in addition to Udacity's deep learning program in an attempt to learn the basics. I'm hoping I can use my dataset to build something backed by ML that sounds better.
Is anyone in the Atlanta area interested in ML? I'd love to chat over coffee or join local ML interest groups.
Earlier quoted context omitted.
> No it hasn't, not at all. What do you mean? it most certainly has. It is much harder to look at a photograph now and say for sure it's real. Before photoshop, there were ways of manipulating photos, but they were much harder and did not yield nearly as good results. You can photoshop people into photos they were not originally in, doing things they have never done. Even Trump is having his hands enlarged in photos.…
Certainly it raises the bar for skepticism, but I can think of relatively few cases where a photoshopped image has driven a news cycle/key event because someone famous/important believed it to be real. Most doctored images/videos get snuffed out by the media very quickly if they grow viral.
I have a friend who believes in aliens. They showed me a video that someone had put together of "footage". They were seriously showing it to me as evidence, to convince me that they are real, based on this video. I was shocked they were so serious - and having a hard time containing my laughter.
I later found a number of other videos debunking the videos and clips that video was based off of - but my friend still believes in aliens, based on those videos. And this is someone I regularly have "intelligent" conversations with.
This change, the ability to put words in someones mouth, is the next photoshop. And it WILL have consequences to it, good and bad. And we are not prepared for that, as a society - we haven't gotten over photoshop yet.
It's there any copyright protections for a person's voice? If not, David Attenborough and Morgan Freeman will be lead voice actors in my next game project
let's do it.