Open AccessMaximum Likelihood Training and Adaptation of Embedded Speech Recognizers for Mobile Environments
Author(s) -
Cho Youngkyu,
Yook Dongsuk
Publication year - 2010
Publication title -
etri journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.295
H-Index - 46
eISSN - 2233-7326
pISSN - 1225-6463
DOI - 10.4218/etrij.10.0209.0242
Subject(s) - adaptation (eye) , speech recognition , computer science , training (meteorology) , maximum likelihood , psychology , statistics , mathematics , geography , meteorology , neuroscience
For the acoustic models of embedded speech recognition systems, hidden Markov models (HMMs) are usually quantized and the original full space distributions are represented by combinations of a few quantized distribution prototypes. We propose a maximum likelihood objective function to train the quantized distribution prototypes. The experimental results show that the new training algorithm and the link structure adaptation scheme for the quantized HMMs reduce the word recognition error rate by 20.0%.