Title :
Duration modeling results for an on-line handwriting recognizer
Author :
Senior, Andrew ; Subrahmonia, Jayashree ; Nathan, Krishna
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
This paper describes a series of experiments that have been conducted to investigate the effect of duration modeling in a hidden Markov model (HMM) based online handwriting recognition system. The issues discussed include parametric vs. non-parametric distributions to model duration, different methods for training transition probabilities and the effect of weighting on duration terms
Keywords :
character recognition; hidden Markov models; statistical analysis; duration modeling results; hidden Markov model; nonparametric distributions; online handwriting recognizer; parametric distributions; training; transition probabilities; weighting; Character generation; Character recognition; Decoding; Handwriting recognition; Hidden Markov models; Histograms; Speech recognition; Stochastic systems; System testing; Viterbi algorithm;
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.1996.550778
