Automated visual speech analysis and synthesis is becoming a widespread application. The most important stage in these systems is to design an algorithm for lip finding and tracking. These systems normally find the lip area in the first captured image and then try to initialize a tracking algorithm with the results. After initialization, the tracking algorithm tries to follow the defined features to track the lip contour. The time adaptive self organizing map is a powerful method for active contour modeling in non-stationary environments. In this paper we have used the TASOM based active contour modeling algorithm to track the lips. The results show convincing improvements in comparison with traditional snake methods.