>What are the acoustic models that can be used with Julius apart from

>acoustic models developed using HTK toolkit.

from the Julius website:

About Models

Since Julius itself is a language-independent decoding program, you can make a recognizer of a language if given an appropriate language model and acoustic model for the target language. The recognition accuracy largely depends on the models.

Julius adopts acoustic models in HTK ascii format, pronunciation dictionary in almost HTK format, and word 3-gram language models in ARPA standard format (forward 2-gram and reverse 3-gram trained from same corpus).

YOu might be interest in this post: Speech Recognition Model Converter

 

--- (Edited on 7/28/2010 4:11 pm [GMT-0400] by kmaclean) ---