TY - GEN A1 - Tóth, László A1 - Kocsor, András A1 - Csirik, János A2 - Korbicz, Józef - red. A2 - Uciński, Dariusz - red. PB - Zielona Góra: Uniwersytet Zielonogórski N2 - The currently dominant speech recognition technology, hidden Markov modeling, has long been criticized for its simplistic assumptions about speech, and especially for the naive Bayes combination rule inherent in it. Many sophisticated alternative models have been suggested over the last decade. N2 - These, however, have demonstrated only modest improvements and brought no paradigm shift in technology. The goal of this paper is to examine why HMM performs so well in spite of its incorrect bias due to the naive Bayes assumption. To do this we create an algorithmic framework that allows us to experiment with alternative combination schemes and helps us understand the factors that influence recognition performance. N2 - From the findings we argue that the bias peculiar to the naive Bayes rule is not really detrimental to phoneme classification performance. Furthermore, it ensures consistent behavior in outlier modeling, allowing efficient management of insertion and deletion errors. L1 - http://www.zbc.uz.zgora.pl/Content/57515/AMCS_2005_15_2_11.pdf L2 - http://www.zbc.uz.zgora.pl/Content/57515 KW - naive Bayes KW - segment-based speech recognition KW - hidden Markov model T1 - On naive Bayes in speech recognition UR - http://www.zbc.uz.zgora.pl/dlibra/docmetadata?id=57515 ER -