Deep fake technology has exploded in popularity since 2017. In a strange parody of Moore’s Law, the number of deep fake videos published online doubles every six months, according to one estimate.
Daniel Higgins knew something was up when he suddenly couldn’t log into his Instagram account and then discovered his password had been changed.
But he couldn’t believe his eyes when he saw a new post on his account: a video of man that looked and sounded just like him, telling all of his Instagram followers to buy Bitcoin.
“I just invested $300 into Bitcoin and got $10,000 back. Gotta try it,” the fake Higgins said in the video.
Suddenly, he received text messages from followers wondering what was going on.
That was weeks ago. Higgins has been trying ever since to regain access to his account. He says his attempts to convince Instagram to help have gone no where.
There’s no real person to contact, so Higgins has gone through the online procedure of alerting Instagram of the problem. He was even told by the system he would be sent a new password.
This work explores the task of synthesizing speech in non-existent human-sounding voices. We call this task "speaker generation", and present TacoSpawn, a system that performs competitively at this task. TacoSpawn is a recurrent attention-based text-to-speech model that learns a distribution over a speaker embedding space, which enables sampling of novel and diverse speakers. Our method is easy to implement, and does not require transfer learning from speaker ID systems. We present objective and subjective metrics for evaluating performance on this task, and demonstrate that our proposed objective metrics correlate with human perception of speaker similarity.
This page contains a set of audio samples in support of the paper: we suggest that readers listen to the samples in conjunction with reading the paper.
Note that the TacoSpawn systems described in the paper extend a baseline Tacotron -- that is, they do not use any additional acoustic or prosody embeddings to improve the naturalness of synthesized speech.
A collaboration between Google Research and Harvard University has developed a new method to create 360-degree neural video of complete scenes using Neural Radiance Fields (NeRF). The novel approach takes NeRF a step closer to casual abstract use in any environment, without being restricted to tabletop models or closed interior scenarios.
Mip-NeRF 360 can handle extended backgrounds and ‘infinite’ objects such as the sky, because, unlike most previous iterations, it sets limits on the way light rays are interpreted, and creates boundaries of attention that rationalize otherwise lengthy training times. See the new accompanying video embedded at the end of this article for more examples, and an extended insight into the process.
Andy Chanley, the afternoon drive host at Southern California's public radio station 88.5 KCSN, has been a radio DJ for over 32 years. And now, thanks to artificial intelligence technology, his voice will live on simultaneously in many places.
"I may be a robot, but I still love to rock," says the robot DJ named ANDY, derived from Artificial Neural Disk-JockeY, in Chanley's voice, during a demonstration for Reuters where the voice was hard to distinguish from a human DJ.
Our phones, speakers and rice cookers have been talking to us for years, but their voices have been robotic. Seattle-based AI startup WellSaid Labs says it has finessed the technology to create over 50 real human voice avatars like ANDY so far, where the producer just needs to type in text to create the narration.
Zack Zalon, CEO of Los Angeles-based AI startup Super Hi-Fi, said ANDY will be integrated into its AI platform that automates music production. So instead of a music playlist, ANDY can DJ the experience, introducing the songs and talking about them.
The next step will be for the AI to automate the text that is created by humans as well. "That's really the triumvirate that we think is going to take this to the next level," Zalon said.
To represent a 3D scene from a 2D image, a light field network encodes the 360-degree light field of the 3D scene into a neural network that directly maps each camera ray to the color observed by that ray. Credit: Massachusetts Institute of Technology
Humans are pretty good at looking at a single two-dimensional image and understanding the full three-dimensional scene that it captures. Artificial intelligence agents are not.
Yet a machine that needs to interact with objects in the world—like a robot designed to harvest crops or assist with surgery—must be able to infer properties about a 3D scene from observations of the 2D images it's trained on.
While scientists have had success using neural networks to infer representations of 3D scenes from images, these machine learning methods aren't fast enough to make them feasible for many real-world applications.
Sounds like the brobot will do well.Yuli Ban wrote: ↑Sun Dec 05, 2021 6:51 pmAndy Chanley, the afternoon drive host at Southern California's public radio station 88.5 KCSN, has been a radio DJ for over 32 years. And now, thanks to artificial intelligence technology, his voice will live on simultaneously in many places.
"I may be a robot, but I still love to rock," says the robot DJ named ANDY, derived from Artificial Neural Disk-JockeY, in Chanley's voice, during a demonstration for Reuters where the voice was hard to distinguish from a human DJ.
Our phones, speakers and rice cookers have been talking to us for years, but their voices have been robotic. Seattle-based AI startup WellSaid Labs says it has finessed the technology to create over 50 real human voice avatars like ANDY so far, where the producer just needs to type in text to create the narration.
Zack Zalon, CEO of Los Angeles-based AI startup Super Hi-Fi, said ANDY will be integrated into its AI platform that automates music production. So instead of a music playlist, ANDY can DJ the experience, introducing the songs and talking about them.
The next step will be for the AI to automate the text that is created by humans as well. "That's really the triumvirate that we think is going to take this to the next level," Zalon said.
Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional image synthesis and compare two different guidance strategies: CLIP guidance and classifier-free guidance. We find that the latter is preferred by human evaluators for both photorealism and caption similarity, and often produces photorealistic samples. Samples from a 3.5 billion parameter text-conditional diffusion model using classifier-free guidance are favored by human evaluators to those from DALL-E, even when the latter uses expensive CLIP reranking. Additionally, we find that our models can be fine-tuned to perform image inpainting, enabling powerful text-driven image editing.
With the ability to intelligently generate media variants (of any kind) in real-time, as would be supported by a cutting-edge video graphics engine, the outcome would be unusually incredible for media enjoyers. Eventually entire movies and video game storylines will be randomly and instantaneously created for each individual user, with lifelike realism.
Like the blockchain, it looks like entertainment is also going down the decentralization route. No more relying on movie & video game studios with all of their money, manpower, and of course, long production times to offer us entertainment content that isn't even specifically catered to our own preferences most of the time.bretbernhoft wrote: ↑Sun Dec 26, 2021 7:53 pm
With the ability to intelligently generate media variants (of any kind) in real-time, as would be supported by a cutting-edge video graphics engine, the outcome would be unusually incredible for media enjoyers. Eventually entire movies and video game storylines will be randomly and instantaneously created for each individual user, with lifelike realism.
IMO, what you've just described is quite an important observation about the future of media; that it is becoming decentralized, or fractalized. Our media and entertainment is mutating, right alongside everything else. All of which is powered by the increasing agency of our digital tools. All of this is hard to describe to other media enthusiasts who haven't dreamed of and considered the subject matter.raklian wrote: ↑Sun Dec 26, 2021 8:11 pmLike the blockchain, it looks like entertainment is also going down the decentralization route. No more relying on movie & video game studios with all of their money, manpower, and of course, long production times to offer us entertainment content that isn't even specifically catered to our own preferences most of the time.bretbernhoft wrote: ↑Sun Dec 26, 2021 7:53 pm
With the ability to intelligently generate media variants (of any kind) in real-time, as would be supported by a cutting-edge video graphics engine, the outcome would be unusually incredible for media enjoyers. Eventually entire movies and video game storylines will be randomly and instantaneously created for each individual user, with lifelike realism.
Entertainment will be interactive, immediate and personalized. That's the future.
