| |
|
Digital lip reader
|
| |
Massachusetts, USA (MIT Technology Review) Groups at Intel, IBM, and other institutions are modifying language-processing programs to link each vocal sound to several possible mouth movements, allowing the software to make a best guess about what's being uttered. In tests in noisy environments, adding visual information boosted speech recognition accuracy from 20 percent to 75 percent, says Ara Nefian, a senior researcher at Intel Research in Santa Clara, CA.
For more information, please visit:
www.technologyreview.com/BizTech/wtr_13279,295,p1.html
|
|