titleDetecting and Tracking Lips in Unconstrained Imagery
lNameZhang
fNameJane
phone756-7528
emailjzhang@calpoly.edu
additional
departmentElectrical Engineering
proj_descWhen combined with acoustical speech information, visual speech information (lip movement) significantly improves Automatic Speech Recognition (ASR) in acoustically noisy environments. Previous research has demonstrated that visual modality is a viable tool for identifying speech. However, the visual information has yet to become utilized in mainstream ASR systems due to the difficulty in accurately tracking lips in real-world conditions. In this project, student will develop a lip detection and tracking system in visually challenging environment.
The applications include improved automatic speech recognition, and biometric speaker identification.


inter_descThe subject of computer vision is interdisciplinary in nature. It is closely related to a wide range of fields including signal processing, pattern recognition, machine learning, physics, neurobiology, statistics.
links
students2
majorsCPE, EE, CSC, ENGR, MATH, MATH, STAT, PHYS
desired_resThis project will train students in the field of digital image processing, computer vision and pattern recognition. Students with basic knowledge in signal processing and good math skills could make a contribution to this project.
date_added2008-10-19 12:59:25