Facial Expression RecognitionPosted: October 9, 2008
In my previous blog I suggested facial expression recognition software using web cams to improve social interaction between avatars in virtual worlds. I went on the web after to see if it had already been done and what I found was a Science Daily article from February of 2008 about how researchers at the Department of Artificial Intelligence (DIA) of the Universidad Politécnica de Madrid’s School of Computing (FIUPM) have, in conjunction with Madrid’s Universidad Rey Juan Carlos, developed an algorithm for facial expression recognition. So I guess we are not quite there with web cam enabled thin client based recognition software for conveying emotions to avatars in virtual worlds, but the theory is solid.
Now voice alteration… since voice is characterized by the pitch and the timbre, the voice imitating process is actually the analyzing process of the sample voice and the modulating process of the pitch and timbre of the input voice into those of the sample voices. Basically, there is no 100% resemblance between two voices since the pitch and the timbre of a voice are unique. However, you could generate a signature that simulates a likeness. VCS Diamond is one such solution.