Conventional MLP classifiers used in phonetic recognition and speech recognition may encounter local minima during training, and they often lack an intuitive and flexible adaptation approach. This paper presents a hybrid MLP-SVM classifier and its associated adaptation strategy, where the last layer of a conventional MLP is learned and adapted in the maximum separation margin sense. This structure also provides a support vector based adaptation mechanism which better interpolates between a speaker-independent model and speaker-dependent adaptation data. Preliminary experiments on vowel classification have shown promising results for both MLP learning and adaptation problems.
Cite as: Li, X., Bilmes, J., Malkin, J. (2005) Maximum margin learning and adaptation of MLP classifiers. Proc. Interspeech 2005, 1789-1792, doi: 10.21437/Interspeech.2005-164
@inproceedings{li05b_interspeech,
author={Xiao Li and Jeff Bilmes and Jonathan Malkin},
title={{Maximum margin learning and adaptation of MLP classifiers}},
year=2005,
booktitle={Proc. Interspeech 2005},
pages={1789--1792},
doi={10.21437/Interspeech.2005-164}
}