Multistream articulatory feature-based models for visual speech recognition

IEEE Trans Pattern Anal Mach Intell. 2009 Sep;31(9):1700-7. doi: 10.1109/TPAMI.2008.303.

Abstract

We study the problem of automatic visual speech recognition (VSR) using dynamic Bayesian network (DBN)-based models consisting of multiple sequences of hidden states, each corresponding to an articulatory feature (AF) such as lip opening (LO) or lip rounding (LR). A bank of discriminative articulatory feature classifiers provides input to the DBN, in the form of either virtual evidence (VE) (scaled likelihoods) or raw classifier margin outputs. We present experiments on two tasks, a medium-vocabulary word-ranking task and a small-vocabulary phrase recognition task. We show that articulatory feature-based models outperform baseline models, and we study several aspects of the models, such as the effects of allowing articulatory asynchrony, of using dictionary-based versus whole-word models, and of incorporating classifier outputs via virtual evidence versus alternative observation models.

Publication types

  • Evaluation Study
  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

  • Algorithms
  • Computer Simulation
  • Humans
  • Image Enhancement / methods
  • Image Interpretation, Computer-Assisted / methods*
  • Lip / anatomy & histology*
  • Lip / physiology*
  • Lipreading*
  • Models, Anatomic
  • Models, Biological*
  • Pattern Recognition, Automated / methods
  • Speech Production Measurement / methods*
  • Speech Recognition Software*