Answers are grounded in this paper and cite their sources.
A technique to smooth hidden Markov model parameters, based on the fuzzy mapping concept, is presented. The proposed algorithm is shown to result in a higher recognition rate than the co-occurrence smoothing method and requires neither an interpolation procedure nor the addition of more training data.
No takes yet. Share an insight, caveat, or question.
Koo et al. (1990) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: