Project Description We are interested in a new framework for speech recognition. In particular we believe that adaptive systems can do a good job in learning the structure of speech
signals such that the learned features can be used for many speech processing tasks. The goal of the project is to develop software that can enhance the sound or image signal using a
newly developed technique called ICA (independent component analysis). ICA is able to separate sounds or images when the environment has mixed them. This software is an important step in advancing computer
systems closer to humanlike performance and hence will make the human machine interaction more natural. . Project Goals - Speech Enhancement
- Speech de-noising - Speech feature extraction Schedule .
| |
Phase Name |
End Date |
 |
Phase 1 |
March 16, 2002 |
|
Staff
Oh-Wook Kwon Gil-Jin Jang Manabu Otsuka Eric Visser . |