Surface Learning with Applications to Lipreading

Most connectionist research has focused on learning mappings from one space to another (eg. This paper introduces the more general task of learning constraint surfaces. It describes a simple but powerful architecture for learning and manipulating nonlinear surfaces from data. We demonstrate the technique on low dimensional synthetic surfaces and compare it to nearest neighbor approaches. We then show its utility in learning the space of lip images in a system for improving speech recognition by lip reading.