作者: Mohammad Mosleh , Saeed Setayeshi , Mohammad Kheyrandish
关键词: Iterative Viterbi decoding 、 Speech recognition 、 Soft output Viterbi algorithm 、 Forward algorithm 、 Speech processing 、 Genetic algorithm 、 Pattern recognition 、 Computer science 、 Dynamic programming 、 Hidden Markov model 、 Artificial intelligence 、 Algorithm 、 Viterbi algorithm
摘要: Abstract - One of the best current methods for modeling dynamic speech signal is using HMM model. The recognition systems based on can be able to compute likelihood measure between unknown input pattern and reference models by Viterbi algorithm. Whereas such algorithm programming, it consists many computations with increasing number words. In this paper, we will present a new evolutionary methodology synergic GA that measurement patterns in parallel form cellular automata. We introduce as HGC. HGC compared from the“recognition accuracy” “recognition speed” viewpoints.Obtained results show algorithms are close viewpoint, but HGCisso faster than