Discriminative training based on an integrated view of MPE and MMI in margin and error space

Erik McDermott, Shinji Watanabe, Atsushi Nakamura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

38 Citations (Scopus)

Abstract

Recent work has demonstrated that the Maximum Mutual Information (MMI) objective function is mathematically equivalent to a simple integral of recognition error, if the latter is expressed as a margin-based Minimum Phone Error (MPE) style error-weighted objective function. This led to the proposal of a general approach to discriminative training based on integrals of MPE-style loss, calculated using "differenced MMI" (dMMI), a finite difference of MMI functionals evaluated at the edges of a margin interval. This article aims to clarify the essence and practical consequences of the new framework. The recently proposed Error-Indexed Forward-Backward Algorithm is used to visualize the close agreement between dMMI and MPE statistics for narrow margin intervals, and to illustrate the flexible control of the weight that can be given to different error levels using broader intervals. New speech recognition results are presented for the MIT OpenCourseWare/MIT-World corpus, showing small performance gains for dMMI compared to MPE for some choices of margin interval. Evaluation with an expanded 44K word trigram language model confirms that dMMI with a narrow margin interval yields the same performance as MPE.

Original languageEnglish
Title of host publication2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings
Pages4894-4897
Number of pages4
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Dallas, TX
Duration: 2010 Mar 142010 Mar 19

Other

Other2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010
CityDallas, TX
Period10/3/1410/3/19

    Fingerprint

Keywords

  • Discriminative training
  • Speech recognition

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

McDermott, E., Watanabe, S., & Nakamura, A. (2010). Discriminative training based on an integrated view of MPE and MMI in margin and error space. In 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2010 - Proceedings (pp. 4894-4897). [5495106] https://doi.org/10.1109/ICASSP.2010.5495106