Training hidden Markov models by hybrid simulated annealing for visual speech recognition

Jong Seok Lee; Cheol Hoon Park

doi:10.1109/ICSMC.2006.384382

Training hidden Markov models by hybrid simulated annealing for visual speech recognition

Jong Seok Lee, Cheol Hoon Park

School of Integrated Technology

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

12 Citations (Scopus)

Abstract

This paper presents a novel training algorithm of hidden Markov models (HMMs) for visual speech recognition based on a modified simulated annealing (SA) algorithm, hybrid simulated annealing, where SA is combined with a local optimization technique to improve the convergence speed and the solution quality. While the popular training method of HMMs, the expectation-maximization (EM) algorithm, only achieves local optima in the parameter space, the proposed algorithm performs global search and thus obtains solutions giving improved recognition performance. The effectiveness of the proposed method is demonstrated via isolated word recognition experiments.

Original language	English
Title of host publication	2006 IEEE International Conference on Systems, Man and Cybernetics
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	198-202
Number of pages	5
ISBN (Print)	1424401003, 9781424401000
DOIs	https://doi.org/10.1109/ICSMC.2006.384382
Publication status	Published - 2006 Jan 1
Event	2006 IEEE International Conference on Systems, Man and Cybernetics - Taipei, Taiwan, Province of China Duration: 2006 Oct 8 → 2006 Oct 11

Publication series

Name	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Volume	1
ISSN (Print)	1062-922X

Other

Other	2006 IEEE International Conference on Systems, Man and Cybernetics
Country/Territory	Taiwan, Province of China
City	Taipei
Period	06/10/8 → 06/10/11

All Science Journal Classification (ASJC) codes

Engineering(all)

Access to Document

10.1109/ICSMC.2006.384382

Cite this

Lee, J. S., & Park, C. H. (2006). Training hidden Markov models by hybrid simulated annealing for visual speech recognition. In 2006 IEEE International Conference on Systems, Man and Cybernetics (pp. 198-202). [4273829] (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics; Vol. 1). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICSMC.2006.384382

@inproceedings{1c742fbc326543daa3b9c9ba4af6f7e3,

title = "Training hidden Markov models by hybrid simulated annealing for visual speech recognition",

abstract = "This paper presents a novel training algorithm of hidden Markov models (HMMs) for visual speech recognition based on a modified simulated annealing (SA) algorithm, hybrid simulated annealing, where SA is combined with a local optimization technique to improve the convergence speed and the solution quality. While the popular training method of HMMs, the expectation-maximization (EM) algorithm, only achieves local optima in the parameter space, the proposed algorithm performs global search and thus obtains solutions giving improved recognition performance. The effectiveness of the proposed method is demonstrated via isolated word recognition experiments.",

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

year = "2006",

month = jan,

day = "1",

doi = "10.1109/ICSMC.2006.384382",

language = "English",

isbn = "1424401003",

series = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "198--202",

booktitle = "2006 IEEE International Conference on Systems, Man and Cybernetics",

address = "United States",

note = "2006 IEEE International Conference on Systems, Man and Cybernetics ; Conference date: 08-10-2006 Through 11-10-2006",

}

Lee, JS & Park, CH 2006, Training hidden Markov models by hybrid simulated annealing for visual speech recognition. in 2006 IEEE International Conference on Systems, Man and Cybernetics., 4273829, Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, vol. 1, Institute of Electrical and Electronics Engineers Inc., pp. 198-202, 2006 IEEE International Conference on Systems, Man and Cybernetics, Taipei, Taiwan, Province of China, 06/10/8. https://doi.org/10.1109/ICSMC.2006.384382

Training hidden Markov models by hybrid simulated annealing for visual speech recognition. / Lee, Jong Seok; Park, Cheol Hoon.
2006 IEEE International Conference on Systems, Man and Cybernetics. Institute of Electrical and Electronics Engineers Inc., 2006. p. 198-202 4273829 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics; Vol. 1).

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

TY - GEN

T1 - Training hidden Markov models by hybrid simulated annealing for visual speech recognition

AU - Lee, Jong Seok

AU - Park, Cheol Hoon

PY - 2006/1/1

Y1 - 2006/1/1

N2 - This paper presents a novel training algorithm of hidden Markov models (HMMs) for visual speech recognition based on a modified simulated annealing (SA) algorithm, hybrid simulated annealing, where SA is combined with a local optimization technique to improve the convergence speed and the solution quality. While the popular training method of HMMs, the expectation-maximization (EM) algorithm, only achieves local optima in the parameter space, the proposed algorithm performs global search and thus obtains solutions giving improved recognition performance. The effectiveness of the proposed method is demonstrated via isolated word recognition experiments.

AB - This paper presents a novel training algorithm of hidden Markov models (HMMs) for visual speech recognition based on a modified simulated annealing (SA) algorithm, hybrid simulated annealing, where SA is combined with a local optimization technique to improve the convergence speed and the solution quality. While the popular training method of HMMs, the expectation-maximization (EM) algorithm, only achieves local optima in the parameter space, the proposed algorithm performs global search and thus obtains solutions giving improved recognition performance. The effectiveness of the proposed method is demonstrated via isolated word recognition experiments.

UR - http://www.scopus.com/inward/record.url?scp=34548139784&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548139784&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2006.384382

DO - 10.1109/ICSMC.2006.384382

M3 - Conference contribution

SN - 1424401003

SN - 9781424401000

T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SP - 198

EP - 202

BT - 2006 IEEE International Conference on Systems, Man and Cybernetics

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2006 IEEE International Conference on Systems, Man and Cybernetics

Y2 - 8 October 2006 through 11 October 2006

ER -

Lee JS, Park CH. Training hidden Markov models by hybrid simulated annealing for visual speech recognition. In 2006 IEEE International Conference on Systems, Man and Cybernetics. Institute of Electrical and Electronics Engineers Inc. 2006. p. 198-202. 4273829. (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). doi: 10.1109/ICSMC.2006.384382

Training hidden Markov models by hybrid simulated annealing for visual speech recognition

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this