University of Washington researchers have developed new algorithms that solve a thorny challenge in the field of computer vision: turning audio clips into a realistic, lip-synced video of the person speaking those words.
As detailed in a paper to be presented Aug. 2 at SIGGRAPH 2017, the team successfully generated highly-realistic video of former president Barack Obama talking about terrorism, fatherhood, job creation and other topics using audio clips of those speeches and existing weekly video addresses that were originally on a different topic.
“These type of results have never been shown before,” said Ira Kemelmacher-Shlizerman, an assistant professor at the UW’s Paul G. Allen School of Computer Science & Engineering. “Realistic audio-to-video conversion has practical applications like improving video conferencing for meetings, as well as futuristic ones such as being able to hold a conversation with a historical figure in virtual reality by creating visuals just from audio. This is the kind of breakthrough that will help enable those next steps.”
In a visual form of lip-syncing, the system converts audio files of an individual’s speech into realistic mouth shapes, which are then grafted onto and blended with the head of that person from another existing video.
The team chose Obama because the machine learning technique needs available video of the person to learn from, and there were hours of presidential videos in the public domain. “In the future video, chat tools like Skype or Messenger will enable anyone to collect videos that could be used to train computer models,” Kemelmacher-Shlizerman said.
Because streaming audio over the internet takes up far less bandwidth than video, the new system has the potential to end video chats that are constantly timing out from poor connections.
“When you watch Skype or Google Hangouts, often the connection is stuttery and low-resolution and really unpleasant, but often the audio is pretty good,” said co-author and Allen School professor Steve Seitz. “So if you could use the audio to produce much higher-quality video, that would be terrific.”
By reversing the process — feeding video into the network instead of just audio — the team could also potentially develop algorithms that could detect whether a video is real or manufactured.
The new machine learning tool makes significant progress in overcoming what’s known as the “uncanny valley” problem, which has dogged efforts to create realistic video from audio. When synthesized human likenesses appear to be almost real — but still manage to somehow miss the mark — people find them creepy or off-putting.
“People are particularly sensitive to any areas of your mouth that don’t look realistic,” said lead author Supasorn Suwajanakorn, a recent doctoral graduate in the Allen School. “If you don’t render teeth right or the chin moves at the wrong time, people can spot it right away and it’s going to look fake. So you have to render the mouth region perfectly to get beyond the uncanny valley.”
Previously, audio-to-video conversion processes have involved filming multiple people in a studio saying the same sentences over and over to try to capture how a particular sound correlates to different mouth shapes, which is expensive, tedious and time-consuming. By contrast, Suwajanakorn developed algorithms that can learn from videos that exist “in the wild” on the internet or elsewhere.
“There are millions of hours of video that already exist from interviews, video chats, movies, television programs and other sources. And these deep learning algorithms are very data hungry, so it’s a good match to do it this way,” Suwajanakorn said.
Rather than synthesizing the final video directly from audio, the team tackled the problem in two steps. The first involved training a neural network to watch videos of an individual and translate different audio sounds into basic mouth shapes.
By combining previous research from the UW Graphics and Image Laboratory team with a new mouth synthesis technique, they were then able to realistically superimpose and blend those mouth shapes and textures on an existing reference video of that person. Another key insight was to allow a small time shift to enable the neural network to anticipate what the speaker is going to say next.
The new lip-syncing process enabled the researchers to create realistic videos of Obama speaking in the White House, using words he spoke on a television talk show or during an interview decades ago.
Currently, the neural network is designed to learn on one individual at a time, meaning that Obama’s voice — speaking words he actually uttered — is the only information used to “drive” the synthesized video. Future steps, however, include helping the algorithms generalize across situations to recognize a person’s voice and speech patterns with less data – with only an hour of video to learn from, for instance, instead of 14 hours.
“You can’t just take anyone’s voice and turn it into an Obama video,” Seitz said. “We very consciously decided against going down the path of putting other people’s words into someone’s mouth. We’re simply taking real words that someone spoke and turning them into realistic video of that individual.”
The Latest on: Audio-to-video conversion
- Vochi, the ‘computer vision’-based video editing and effects app, raises $1.5M seedon May 11, 2020 at 1:03 am
Vochi, a startup operating out of Belarus that’s created a “computer vision”-based video editing and effects app for mobile phones, has raised $1.5 million in seed funding. Leading the round is ...
- Computer Vision Can Renovate Financial Services say Deltec Bank, Bahamason May 8, 2020 at 12:33 pm
Financial services can be improved by implementing computer vision technology, which offers many great benefits for financial organizations that adopt it. But what makes computer vision so great? Read ...
- Computer vision helps scientists study lithium ion batterieson May 8, 2020 at 3:15 am
Lithium-ion batteries lose their juice over time, causing scientists and engineer to work hard to understand that process in detail. Now, scientists at the Department of Energy's SLAC National ...
- Invisible AI uses computer vision to help (but hopefully not nag) assembly line workerson May 6, 2020 at 10:07 am
Assembly” may sound like one of the simpler tests in the manufacturing process, but as anyone who’s ever put together a piece of flat-pack furniture knows, it can be surprisingly (and frustratingly) ...
- Computer vision is transforming healthcare with rapid cell counting and patient identificationon May 6, 2020 at 4:02 am
Fast forward to the present day and computer vision is being used to identify and count cell nuclei not only more accurately than people can count, but far faster. To accomplish this, an AI model is ...
- AI In Computer Vision Market ,Share, Trends, Growth, Opportunities and Top Key players, Forecast to 2023on May 5, 2020 at 8:24 am
AI In Computer Vision Market Research Report by Component (Hardware, Software), Vertical (healthcare, security, ...
- AI Hub Singapore creates first AI computer vision application that allows businesses to monitor social distancing with a mobile phoneon May 5, 2020 at 12:00 am
To allow more businesses and people to monitor social distancing easily, AI Hub Singapore has created an AI application that turns a ubiquitous device - a mobile phone - into a social distance ...
- Computer Vision Market is expected to surpass a valuation of $ 48,300 Mn by 2023on May 3, 2020 at 2:08 am
The computer vision technology landscape continues to undergo relentless transformation, concurrently creating new application opportunities. In 2017, the global market for comput ...
- Nurse-Led Inspiren Deploys Computer Vision A.I. to Protect Front Line from COVID-19on April 30, 2020 at 5:00 am
PRNewswire/ -- Inspiren, a nurse-led technology company, deploys its flagship solution in the fight against COVID-19 to ensure staff are adequately ...
- Computer vision system detects fever remotely to rule out COVID-19 symptomson April 28, 2020 at 9:24 pm
People who approach the front desk at Albert Einstein Jewish Hospital (HIAE) in the city of São Paulo have their temperature taken remotely by a computer vision system installed in a nearby column.
via Google News and Bing News