A new artificial intelligence tool called EMO was introduced. This tool can convert photos into videos. Moreover, it can make the people in the photo speak and even sing in the voice you want.
Alibaba Group Intelligent Computer InstituteResearchers Linrui Tian, Qi Wang, Bang Zhang and Liefeng Bo have developed an artificial intelligence system that allows artificial intelligence to read selected texts and fluently change facial expressions according to the texts they read. EMO introduced.
Mouth movements change in accordance with the words
of EMO The most striking aspect is not that it makes a photo or image speak, we have seen many other applications that do this. The most important difference of this artificial intelligence tool is that it can animate visuals based on sounds, in addition to the pre-prepared configuration. Moreover mouth movements It also changes to suit the lyrics. In other words, the visual is literally converted into video in accordance with the audio.
Another striking feature is that the artificial intelligence tool adjusts according to the sound source. ability to adjust tempo. Artificial intelligence, which can understand the difference between calm speaking and rapping, adjusts the tempo of gestures, facial expressions and mouth movements in animations accordingly. Moreover, artificial intelligence can also make animated characters, images created by artificial intelligence or anime characters talk.
So how does it work?
Researchers found that the artificial intelligence model Essentially, it consists of two parts states. One of them identifies the image and creates moving frames based on the reference image. The other one identifies the audio file and identifies key points. Afterwards too key points Images are matched with . Artificial intelligence also has two control modules. One of them ensures that the character in the image remains unchanged, while the other controls the sound. The results from both sides are then combined.
RELATED NEWS