Title :
Initialization of hidden Markov models for unconstrained on-line handwriting recognition
Author :
Nathan, Krishna ; Senior, Andrew ; Subrahmonia, Jayashree
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
In a hidden Markov model system, the initialization of the model parameters is critical to the performance of the model after retraining. This paper proposes a number of new approaches to the problem of initialization, and demonstrates that a method of smooth alignment results in the best performance
Keywords :
handwriting recognition; hidden Markov models; parameter estimation; hidden Markov models; model parameters initialization; performance; retraining; smooth alignment method; unconstrained online handwriting recognition; Covariance matrix; Gaussian distribution; Handwriting recognition; Hidden Markov models; Parameter estimation; Phase estimation; Probability distribution; Speech recognition; State estimation; Yield estimation;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-3192-3
DOI :
10.1109/ICASSP.1996.550783
