Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training

Erik McDermott, Shinji Watanabe, Atsushi Nakamura

Research output: Contribution to journalConference article

13 Citations (Scopus)

Abstract

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 margin-based 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.

Original languageEnglish
Pages (from-to)224-227
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2009 Nov 26
Externally publishedYes
Event10th Annual Conference of the International Speech Communication Association, INTERSPEECH 2009 - Brighton, United Kingdom
Duration: 2009 Sep 62009 Sep 10

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Sensory Systems

Fingerprint Dive into the research topics of 'Margin-space integration of MPE loss via differencing of MMI functionals for generalized error-weighted discriminative training'. Together they form a unique fingerprint.

  • Cite this