Julius 4.0 is now available from the Julius Dev site - from the release notes:

What's new in Julius-4.0
==========================
 
The Julius rev.4.0 is a full major version up, a re-innovation of the
decoder as a flexible speech recognition engine.  The internal
structures are re-organized and modularized thoroughly, which results
in the librarization of core engine, enhancement and unification of
language model, realization of multi-decoding with hot plugging
feature.  The major features are listed below:
 
 - Engine core becomes separate C library with simple API
 - Can handle various LM, thus Julius and Julian are integrated
 - Multi-decoding with multiple models
 - Support to add and remove models while running the decoder
 - Support N-gram longer than 4 (N now unlimited)
 - User-defined LM function
 - Confusion network output
 - GMM-based and decoder-based VAD
 - New tools added, new functions added
 - Memory efficiency is improved
 
Julius-4.0 ensures the compatibility with Julius-3.x for its usage and
Jconf configuration, so that one can easily migrate to Julius-4.
The decoding performance of Julius-4.0 is still kept as the same as
the latest release (Julius-3.5.3) for now.

Many thanks to Ralf Herzog for picking this up and posting on his blog.

Ken 

--- (Edited on 12/26/2007 4:33 pm [GMT-0500] by kmaclean) ---

Julius Main site now updated with Julius 4.0:

Documentation links: 

•  New features in Julius rev.4.0 (pdf)
  

Code Links: 

• Source tarball
  • Julius: julius-4.0.tar.gz (1.0MB)
  • HTK-to-Julius grammar converter: slg2dfa-1.0.tar.gz
• Pre-compiled binaries
  • Linux: julius-4.0-linuxbin.tar.gz (3.2MB, including PDF documents)
  • Win32: julius-4.0-win32bin.zip(4.0MB, including PDF documents)

Forums:

• new Julius phpBB forum

--- (Edited on 1/22/2008 4:45 pm [GMT-0500] by kmaclean) ---

From the Julius Announcements Forum page:

Julius rev.4.0.1 has been released today.
This release incorpolates bug fixes from 4.0 that has been reported so far.

http://sourceforge.jp/projects/julius/f ... 9930#29930

For Linux users, it should be noted that the default audio API
has been changed from OSS to ALSA. You can still use
the old OSS interface by giving "--with-mictype=oss" for
configure script at compilation time.

Have fun!

From the release notes:

4.0.1 (2008.3.12)
==================
New features:
 
  A/D-in
    - ALSA now become default on Linux instead of OSS.
 
  Module mode
    - "ACTIVATEGRAM", "DEACTIVATEGRAM" and "DELGRAM" now accepts
      grammar name as arguments in addition to grammar ID number.
    - new command "GRAMINFO" to get list of current grammars.
 
 
Fixed bugs:
 
  A/D-in
    - ALSA codes updated to work on 1.x drivers.
    - segfault with "-48".
    - segfault on MFCC input with zero frames with "-spsegment".
  VAD
    - CMN not working on spsegment/GMM-VAD/decoder-VAD with microphone input.
  Acoustic model
    - Error when no short-pause model defined in multi-path mode.
  N-gram
    - incorrect 2-gram prob on 1st pass with backward N-gram only.
    - incorrect 1-gram prob for unknown words.
    - fail to read some ARPA files with no back-off compaction.
    - read failure or segfault on big N-gram with over 24bit entries.
    - redundant index for back-off weights in some case. 
  Word recognition
    - incorrect N-best output with "-output N" on word recognition.
  Installation
    - "make install" fails on cygwin.
  Source code
    - Static variables in functions that are not meant to be static
      are made local.
    - Global variables in search are moved to StackDecode.
 

--- (Edited on 3/12/2008 3:40 pm [GMT-0400] by kmaclean) ---

--- (Edited on 3/12/2008 3:41 pm [GMT-0400] by kmaclean) ---