Voice-nav MP3 Players & HD-based Video

[Tinroad]

Intel has released software that lets computers read lips, a step forward that could lead to better voice-recognition applications. The Audio Visual Speech Recognition (AVSR) software tracks a speaker's face and mouth movements. By matching these movements with speech, the application can provide a computer with enough data to respond to voice recognition commands, even when these are given in noisy environments.

29 April 2003
Lip-reading computers are born

New open source software from Intel enables computers to read users' lips – a great leap forward for voice recognition applications.

The accuracy of many current speech recognition applications degrades when there is background noise – in public places, for example.

Intel has developed Audio Visual Speech recognition (AVSR) software that uses face detection algorithms to help computers track a speaker's mouth movements.

The software synchronizes video data with speech identification to enable much more accurate speech recognition.

"Intel wants to develop technology that allows computers to naturally interact with the world the way humans do," said Justin Rattner, Intel senior fellow, Enterprise Platform Group and director of Intel's Microprocessor Research Labs.

"Human recognition is seldom based on a single type of information. We make decisions by combining information from a variety of sources."

The AVSR software has been released as part of Intel's OpenCV computer vision library – a royalty-free toolbox of code for researchers, designed to increase innovation in the field.

http://www.internet-magazine.com/news/view.asp?id=3379
http://www.intel.com/research/mrl/research/avcsr.htm