Art

J-GLOBAL ID：201902218952559537   Reference number：19S0507705

Comparison of tied- mixture and state-clustered HMMs with respect to recognition performance and training method

Author (5)： Segi, Hiroyuki (NHK (Japan Broadcasting Corporation) Science and Technology Research Laboratories) ,  Onoe, Kazuo (NHK (Japan Broadcasting Corporation) Science and Technology Research Laboratories) ,  Sato, Shoei (NHK (Japan Broadcasting Corporation) Science and Technology Research Laboratories) ,  Kobayashi, Akio (NHK (Japan Broadcasting Corporation) Science and Technology Research Laboratories) ,  Ando, Akio (Faculty of Engineering, University of Toyoma)
Material： Journal of Information Technology Research
Volume： 7  Issue： 3  Page： 15-31  Publication year： 2014 
JST Material Number： SCOPUS  ISSN： 1938-7857 
Country of issue： United States (USA)  Language： English (EN)