Microsoft is taking its Kinect technology to a whole new level. We've already looked at how the company is attempting to integrate its product into retail, but Microsoft Research is also tapping into sign language. Numerous videos have been released showing off how the Kinect Sign Language Translator is able to interpret sign language and translate it.
The technology works both ways (wouldn't be such a good conversation otherwise, right?), but this alone shows just how useful the Xbox Kinect is when not used to keep fit or play video games.
How does the technology work? Sign language is detected, captured and translated to text while speech is rendered as visual signs for the hard hearing to see on-screen. Being mastered in Asia, the technology currently supports 300 Chinese sign language words out of a total of 4,000.
Check out the video below to see an overview on the project and how the technology works:
Explaining the scope of the project, Guobin Wu, Research Program Manager, Microsoft Research Asia, wrote the following in a blog post on MSDN:
"The next milestone was to build a sign language recognition system. The team has published many papers that explain the technical details, but what I want to stress here is the collaborative nature of the project. Every month, we had a team meeting to review the progress and plan our next steps. Experts from a host of disciplines—language modeling, translation, computer vision, speech recognition, 3D modeling, and special education—contributed to the system design."
This technology can prove useful in many situations and Wu plans to make the technology available outside the lab. According to the program manager, there are more than 20 million people in China who are hard of hearing, who join an estimated 360 million around the world. We look forward to seeing further progress made with the project.
Head on over to the Microsoft Research website for more details and be sure to check out the blog posts over on MSDN (part 1) (part 2). via: The Next Web
