continuous speech recognition (LVCSR) decoder software for
speech-related researchers and developers. Based on word N-gram and
triphone context-dependent HMM, it can perform almost real-time
decoding on most current PCs with small amount of memory.
WWW: http://julius.sourceforge.jp/en_index.php
PR: 135153
Submitted by: Simun Mikecin <numisemis@yahoo.com>