Discriminative training of hidden Markov models by multiobjective optimization for visual speech recognition

Jong Seok Lee, Cheol Hoon Park

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

4 Citations (Scopus)

Abstract

This paper proposes a novel discriminative training algorithm of hidden Markov models (HMMs) based on the multiobjective optimization for visual speech recognition. We develop a new criterion composed of two minimization objectives for training HMMs discriminatively and a global multiobjective optimization algorithm based on the simulated annealing algorithm to find the Pareto solutions of the optimization problem. We demonstrate the effectiveness of the proposed method via an isolated digit recognition experiment. The results show that the proposed method is superior to the conventional maximum likelihood estimation and the popular discriminative training algorithms.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks, IJCNN 2005
Pages2053-2058
Number of pages6
DOIs
Publication statusPublished - 2005 Dec 1
EventInternational Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada
Duration: 2005 Jul 312005 Aug 4

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume4

Other

OtherInternational Joint Conference on Neural Networks, IJCNN 2005
CountryCanada
CityMontreal, QC
Period05/7/3105/8/4

    Fingerprint

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Lee, J. S., & Park, C. H. (2005). Discriminative training of hidden Markov models by multiobjective optimization for visual speech recognition. In Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005 (pp. 2053-2058). [1556216] (Proceedings of the International Joint Conference on Neural Networks; Vol. 4). https://doi.org/10.1109/IJCNN.2005.1556216