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

Jong Seok Lee; Cheol Hoon Park

doi:10.1109/IJCNN.2005.1556216

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

Jong Seok Lee, Cheol Hoon Park

School of Integrated Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 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 language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005
Pages	2053-2058
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2005.1556216
Publication status	Published - 2005
Event	International Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada Duration: 2005 Jul 31 → 2005 Aug 4

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	4

Other

Other	International Joint Conference on Neural Networks, IJCNN 2005
Country/Territory	Canada
City	Montreal, QC
Period	05/7/31 → 05/8/4

All Science Journal Classification (ASJC) codes

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2005.1556216

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

@inproceedings{469ca7e322cf468ab434db354b919dbf,

title = "Discriminative training of hidden Markov models by multiobjective optimization for visual speech recognition",

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.",

author = "Lee, {Jong Seok} and Park, {Cheol Hoon}",

year = "2005",

doi = "10.1109/IJCNN.2005.1556216",

language = "English",

isbn = "0780390482",

series = "Proceedings of the International Joint Conference on Neural Networks",

pages = "2053--2058",

booktitle = "Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005",

note = "International Joint Conference on Neural Networks, IJCNN 2005 ; Conference date: 31-07-2005 Through 04-08-2005",

}

Lee, JS & Park, CH 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., 1556216, Proceedings of the International Joint Conference on Neural Networks, vol. 4, pp. 2053-2058, International Joint Conference on Neural Networks, IJCNN 2005, Montreal, QC, Canada, 05/7/31. https://doi.org/10.1109/IJCNN.2005.1556216

Discriminative training of hidden Markov models by multiobjective optimization for visual speech recognition. / Lee, Jong Seok; Park, Cheol Hoon.
Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005. 2005. p. 2053-2058 1556216 (Proceedings of the International Joint Conference on Neural Networks; Vol. 4).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Discriminative training of hidden Markov models by multiobjective optimization for visual speech recognition

AU - Lee, Jong Seok

AU - Park, Cheol Hoon

PY - 2005

Y1 - 2005

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=33750123087&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750123087&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1556216

DO - 10.1109/IJCNN.2005.1556216

M3 - Conference contribution

AN - SCOPUS:33750123087

SN - 0780390482

SN - 9780780390485

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 2053

EP - 2058

BT - Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005

T2 - International Joint Conference on Neural Networks, IJCNN 2005

Y2 - 31 July 2005 through 4 August 2005

ER -

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

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this