Welcome to European Tribune. It's gone a bit quiet around here these days, but it's still going.
Display:
Fake news: you ain't seen nothing yet   The Economist

Generating convincing audio and video of fake events

EARLIER this year Françoise Hardy, a French musician, appeared in a YouTube video (see link). She is asked, by a presenter off-screen, why President Donald Trump sent his press secretary, Sean Spicer, to lie about the size of the inauguration crowd. First, Ms Hardy argues. Then she says Mr Spicer "gave alternative facts to that". It's all a little odd, not least because Françoise Hardy (pictured), who is now 73, looks only 20, and the voice coming out of her mouth belongs to Kellyanne Conway, an adviser to Mr Trump.

The video, called "Alternative Face v1.1", is the work of Mario Klingemann, a German artist. It plays audio from an NBC interview with Ms Conway through the mouth of Ms Hardy's digital ghost. The video is wobbly and pixelated; a competent visual-effects shop could do much better. But Mr Klingemann did not fiddle with editing software to make it. Instead, he took only a few days to create the clip on a desktop computer using a generative adversarial network (GAN), a type of machine-learning algorithm. His computer spat it out automatically after being force fed old music videos of Ms Hardy. It is a recording of something that never happened



"It is not necessary to have hope in order to persevere."
by ARGeezer (ARGeezer a in a circle eurotrib daught com) on Tue Aug 22nd, 2017 at 10:17:45 PM EST
[ Parent ]
I had thought that we were already further along than this.

"It is not necessary to have hope in order to persevere."
by ARGeezer (ARGeezer a in a circle eurotrib daught com) on Tue Aug 22nd, 2017 at 10:19:04 PM EST
[ Parent ]
by Cat on Wed Aug 23rd, 2017 at 12:29:35 AM EST
[ Parent ]
Back in the late '70s, the last time I was involved in new electronic circuit design, I saw an article, perhaps in Electronics Design magazine, that described a chip that was, essentially, an analog of the human vocal tract. By feeding audio of a given person speaking over and over a set of parameters could be derivied and, IIRCC, stored in programmable read only memory, be used in conjunction with the chip to render speech from text input that sounded like the person who had been analyzed.

A few years later I had designed and installed a board room AV system for an LA based petroleum company headed by a well known philanthropist/business man/art collector. This system was used for board room meetings, some of which were confidential, so I was sent out to the hall, which was lined with the CEO's Renaissance paintings. While out there one time the CEO was in a telephone booth being importuned by relatives to attend a wedding. (I had really no place to go where I could not hear.)

I thought about that, the veneration and the avidity of the descendents and relatives for the advice, etc. of the 'great man', and then of the artificial vocal tract. At that time we were just starting to get AI expert systems. So I conceived of a product:

THE VOICE OF (FILL IN THE BLANK)

With the artificial vocal tract and the AI program I could offer the very wealthy a product that would allow their descendants to avail themselves of the wisdom of their ancestor. I described this joke system to another small enterprise CEO with whom I had worked to develop the Digital Editor for the 3M Digital Audio Mastering System. I told him: "The marketing plan is simplicity itself! A direct appeal to the vanity of the rich! He said "You had better be careful."  

"It is not necessary to have hope in order to persevere."

by ARGeezer (ARGeezer a in a circle eurotrib daught com) on Wed Aug 23rd, 2017 at 02:11:09 AM EST
[ Parent ]

Display:

Occasional Series