Using the central observation that margin-based weighted classification error (modeled using Minimum Phone Error (MPE)) corresponds to the derivative with respect to the margin term of margin-based hinge loss (modeled using Maximum Mutual Information (MMI)), this article subsumes and extends marginbased MPE and MMI within a broader framework in which the objective function is an integral of MPE loss over a range of margin values. Applying the Fundamental Theorem of Calculus, this integral is easily evaluated using finite differences of MMI functionals; lattice-based training using the new criterion can then be carried out using differences of MMI gradients. Experimental results comparing the new framework with margin-based MMI, MCE and MPE on the Corpus of Spontaneous Japanese and the MIT OpenCourseWare/MIT-World corpus are presented.
Cite as: McDermott, E., Watanabe, S., Nakamura, A. (2009) Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training. Proc. Interspeech 2009, 224-227, doi: 10.21437/Interspeech.2009-81
@inproceedings{mcdermott09_interspeech,
author={Erik McDermott and Shinji Watanabe and Atsushi Nakamura},
title={{Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training}},
year=2009,
booktitle={Proc. Interspeech 2009},
pages={224--227},
doi={10.21437/Interspeech.2009-81}
}