The researchers note their videos are currently not always perfect. This work could also help people talk with digital copies of a person in virtual reality or augmented reality applications, Kemelmacher-Shlizerman says. #Ispeech obama online software#Although teleconferencing video feeds may stutter, freeze or suffer from low-resolution, the audio feeds often work, so in the future, videoconferencing may simply transmit audio from people and use this software to reconstruct what they might have looked like while they talked. One potential application for this new technology is improving videoconferencing, says study co-author Ira Kemelmacher-Shlizerman at the University of Washington. In contrast, this new work can learn from millions of hours of video that already exist on the Internet or elsewhere. The researchers note that similar previous research involved filming people saying sentences over and over again to map what mouth shapes were linked to various sounds, which is expensive, tedious and time-consuming. Essentially, the researchers synthesized videos where Obama lip-synched words he said up to decades beforehand. They next took mouth shapes that matched the new audio clips and grafted and blended them onto the video. The researchers took audio clips and dubbed them over the original sound files of a video. In the new study, the neural net learned what mouth shapes were linked to various sounds. Over time, the neural net learns which patterns are best at computing solutions, an AI strategy that mimics the human brain. The neural net can then alter the pattern of connections among those neurons to change the way they interact, and the network tries solving the problem again. In an artificial neural network, components known as artificial neurons are fed data, and work together to solve a problem such as identifying faces or recognizing speech. The research team had a neural net analyze millions of frames of video to determine how elements of Obama's face moved as he talked, such as his lips and teeth and wrinkles around his mouth and chin. The researchers chose Obama for their latest work because there were hours of high-definition video of him available online in the public domain. Such work suggested it could one day be relatively easy to create such models of anybody, when there are untold numbers of digital photos of everyone on the Internet. Such work could one day help generate digital models of a person for virtual reality or augmented reality applications, researchers say.Ĭomputer scientists at the University of Washington previously revealed they could generate digital doppelgängers of anyone by analyzing images of them collected from the Internet, from celebrities such as Tom Hanks and Arnold Schwarzenegger to public figures such as George W. The work will be published in ACM Transactions on Graphics and you can see the researchers' process in the video below.Īrtificial intelligence software could generate highly realistic fake videos of former president Barack Obama using existing audio and video clips of him, a new study finds. Some limitations the team has pointed out include occasional mistakes in mouth and facial alignment - sometimes it gave Obama two chins - an inability to match emotion and issues arising with sounds that require a particular placement of the tongue, like "th," which isn't currently covered by their program.īut, overall this artificial lip-syncing program creates a much more realistic image than others have. The program isn't perfect yet, but in the video below you can see how much better it gets after three minutes, one hour, seven hours and 14 hours of training data. Those images are then used by the system to make the resulting video's teeth look more realistic. #Ispeech obama online manual#The whole process is automated save for one manual step that requires a person to select two frames in the video where the subject's upper and lower teeth are front-facing and highly visible. To make it look more natural, the system corrected for head placement and movement, timing and details like how the jaw looked. The mouth synced to the audio was then superimposed and blended onto a video of Obama that was different from the audio source. Once trained, their system was then able to take an audio clip from the former president, create mouth shapes that synced with the audio and then synthesize a realistic looking mouth that matched Obama's. The researchers used 14 hours of Obama's weekly address videos to train a neural network.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |