Surface Learning with Applications to Lipreading
Abstract
Most connectionist research has focused on learning mappings from one space to another (eg. classification and regression). 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. This learned surface is used to improve the visual tracking performance during recognition.
Cite
Text
Bregler and Omohundro. "Surface Learning with Applications to Lipreading." Neural Information Processing Systems, 1993.Markdown
[Bregler and Omohundro. "Surface Learning with Applications to Lipreading." Neural Information Processing Systems, 1993.](https://mlanthology.org/neurips/1993/bregler1993neurips-surface/)BibTeX
@inproceedings{bregler1993neurips-surface,
title = {{Surface Learning with Applications to Lipreading}},
author = {Bregler, Christoph and Omohundro, Stephen M.},
booktitle = {Neural Information Processing Systems},
year = {1993},
pages = {43-50},
url = {https://mlanthology.org/neurips/1993/bregler1993neurips-surface/}
}