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
Using AI and Computer Vision to Fix Productivity in Construction
on March 15, 2018 at 10:23 pm
Insight for I&O leaders on deploying AIOps platforms to enhance performance monitoring today. Read the Guide. Construction is a huge industry that has long struggled with productivity issues. One startup that is attempting to improve matters is Doxel ... […]
Global Computer Vision Market Report 2018-2023 - Growing Demand for Vision-Guided Robotic Systems is Driving the Market
on March 15, 2018 at 2:54 pm
The "Computer Vision Market by Component (Hardware (Camera, Frame Grabber, Optics, Processor) and Software (Deep Learning and Traditional Software)), Product (PC Based and Smart Camera Based), Application, Vertical - Global Forecasts to 2023" report has ... […]
Computer vision market worth 17.38 billion USD by 2023
on March 12, 2018 at 5:53 pm
The computer vision market is expected to be valued at USD 11.94 Billion in 2018 and is likely to reach USD 17.38 Billion by 2023, at a CAGR of 7.80% between 2018 and 2023. According to the new market research report "Computer Vision Market by Component ... […]
Four Ways Computer Vision Can Elevate Your Marketing
on March 8, 2018 at 6:34 am
One of the great advantages that digital advertising has had over its print, billboard and other physical space counterparts is the ability to track its effectiveness in real time. That advantage may fade if a new startup aiming to track the demand, supply ... […]
New Training Class Expands Technical Program for 2018 Embedded Vision Summit
on March 8, 2018 at 6:09 am
More than 1,200 computer vision professionals are expected to attend the Embedded Vision Summit, which attracts a global audience of companies developing vision-enabled products, both at the edge and in the cloud. The event features industry innovators ... […]
The total market for computer vision hardware, software, and services will grow from $1.1 billion in 2016 to $26.2 billion by 2025
on March 7, 2018 at 4:14 am
The computer vision market continues to gain momentum. Cameras in mobile devices and cameras added to consumer, commercial, and industrial products are being leveraged. Software algorithms for computer vision are improving. Deep learning and convolutional ... […]
Computer Vision Hardware, Software, and Services Market to Reach $26.2 Billion by 2025, According to Tractica
on March 6, 2018 at 1:10 pm
The computer vision market continues to gain momentum, according to a new report from Tractica. Cameras in mobile devices and cameras added to consumer, commercial, and industrial products are being leveraged. Artificial intelligence (AI) based software ... […]
Walmart plans to open a computer vision and machine learning office in Dallas on April 5
on March 6, 2018 at 2:20 am
Retail giant Walmart now thinks of itself as a tech company — but it’s not putting all its eggs in Silicon Valley. The company announced today that it is opening an emerging technologies office in Dallas, Texas. Thirteen employees have already been ... […]
Computer Vision Market 2018 Global Size, Growth, Profit Analysis, Segments and Trends by Forecast to 2023
on March 5, 2018 at 10:17 am
The field of computer vision has changed since its inception. The emergence of artificial intelligence with deep learning methods changed how the computers see an object. The advancements in algorithms led to identify, analyze and react to the obstacles ... […]
via Google News and Bing News