Improved Automatic Lipreading by Stochastic Optimization of Hidden Markov Models


The KIPS Transactions:PartB , Vol. 14, No. 7, pp. 523-530, Dec. 2007
10.3745/KIPSTB.2007.14.7.523,   PDF Download:

Abstract

This paper proposes a new stochastic optimization algorithm for hidden Markov models (HMMs) used as a recognizer of automatic lipreading. The proposed method combines a global stochastic optimization method, the simulated annealing technique, and the local optimization method, which produces fast convergence and good solution quality. We mathematically show that the proposed algorithm converges to the global optimum. Experimental results show that training HMMs by the method yields better lipreading performance compared to the conventional training methods based on local optimization.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
J. S. Lee and C. H. Park, "Improved Automatic Lipreading by Stochastic Optimization of Hidden Markov Models," The KIPS Transactions:PartB , vol. 14, no. 7, pp. 523-530, 2007. DOI: 10.3745/KIPSTB.2007.14.7.523.

[ACM Style]
Jong Seok Lee and Cheol Hoon Park. 2007. Improved Automatic Lipreading by Stochastic Optimization of Hidden Markov Models. The KIPS Transactions:PartB , 14, 7, (2007), 523-530. DOI: 10.3745/KIPSTB.2007.14.7.523.