New Releases of Julius

julius - 4.2.1

Julius (julius4) — Sat, 24 Dec 2011 15:00:00 GMT

ReleaseNote

Version 4.2.1 is a bug fix release. Many bugs has been fixed,
especially the C0 handling with CMN. Additionary, per-word insertion
penalty at grammar is newly supported.

See the "Release.txt" file for the full list of updates.

ChangeLog

New features:
- Add support for per-word insertion penalty setting at grammar
recognition. You can set different word insertion score for each word
entry at .dict file. For example, if you have an entry
15 [a] a
in .dict file and want to assign word insertion score of "-2.0" to
this word, you can write like this:
15 @-2.0 15 [a] a
The figure after "@" is the insertion penalty. The third
element should be the same as the first element.

- New option "-chunk_size" can specify the audio fragment size in
number of samples. The default value is 1000.

- At "adintool", enable input detection by default for standard input.

Fixed bugs:
- (IMPORTANT) CMN is not performed for C0 coef. This bug exists in
the versions from 4.1.3 to 4.2.
- "-forcedict" won't work for additional dictionaries given by "-adddict".
- Corrupted header of recorded WAV file when interrupted by CTRL+C.
- Occasional segfault when reading a wrongly formatted dictionary.
- Won't compile with configure option "--enable-word-graph".
- Segfault of "mkbingram" and "generate-ngram" at cygwin.

dictation-kit - 4.2

Julius (julius4) — Tue, 10 May 2011 15:00:00 GMT

ReleaseNote

Update for Julius rev.4.2.

grammar-kit - 4.2

Julius (julius4) — Tue, 10 May 2011 15:00:00 GMT

ReleaseNote

Update for Julius rev.4.2.

julius - 4.2

Julius (julius4) — Sat, 30 Apr 2011 15:00:00 GMT

ReleaseNote

Version 4.2 includes new features, improvements and bug fixes. Score
pruning (-bs) is implemented at the 1st pass search for faster
decoding. It can be used in conjunction with the conventional rank
pruning (-b). For audio interface, PulseAudio API is newly supported,
and PortAudio library are updated to V19. At pulseaudio (i.e. Windows
OS), you can choose the capture device by environment variable etc.
The part of codes are refined for stability, by eliminating memory
leaks and efficiency. Some other bugs are fixed.

See the "Release.txt" file for the full list of updates.

ChangeLog

New features:
- Additional score-based pruning at the 1st pass. It is disabled by
default, you can enable by using an option "-bs arg". The argument
is score range.
- New support for PulseAudio (--with-mictype=pulseaudio)
- New Option "-adddict", "-addword" to read additional dictionaries / words.
- Portaudio library updated to V19. Audio capture device can be
changed by env. "PORTAUDIO_DEV_NUM". The device list will be
output at start up.

Changed behavior:
- "mkbinhmmlist" now saves pseudo phone list extracted from AM for
faster start up. The output should be used with the same AM
specified at generation. Note that the converted binhmmlist file
can not be used with older Julius.
- Audio library linking was modified at configure script.
When "--with-mictype=..." is explicitly specified, Julius will link
ONLY the audio library. If not specified, Julius will link all the
audio devices whose development file was detected by the configure.

Library functions:
- j_config_load_string_new(char *str): like j_config_load_file(), but
parse the given string to set parameters.
- add_dict(), add_word(): the same as "-adddict" and "-addword".
(They should be called at start up before starting engine)
- (portaudio/Windows) j_open_stream(recog, NUMSTR) to choose device NUM.
ex. 'j_open_stream(recog, "1")' will open device number one.
- (portaudio/Windows) get_device_list(): obtain list of available devices.

Fixes:
- Improved tree lexicon structure for better memory management.
- Reduce malloc calls at reading N-gram.
- Eliminated memory leaks using Valgrind.
- Workarounds to avoid crash with j_close_stream().
- Now allow "-iwsp" only with multi-path acoustic model.

dictation-kit - 4.1

Julius (julius4) — Wed, 02 Mar 2011 15:00:00 GMT

ReleaseNote

Update for 4.1.5.
Convert character code of language model for Windows into Shift_JIS.

grammar-kit - 4.1

Julius (julius4) — Wed, 02 Mar 2011 15:00:00 GMT

ReleaseNote

Update for Julius rev.4.1.5.

segmentation-kit - 4.0

Julius (julius4) — Wed, 02 Mar 2011 15:00:00 GMT

ReleaseNote

Update for 4.1.5.

julius - 4.1.5.1

Julius (julius4) — Fri, 24 Dec 2010 15:00:00 GMT

ReleaseNote

This release contains a small fix relating to the license.
See "Release.txt" for details of the changes.

ChangeLog

Modified:
- Fixed problem related to the license.

julius - 4.1.5

Julius (julius4) — Thu, 03 Jun 2010 15:00:00 GMT

ReleaseNote

The version 4.1.5 is a bug-fix release.
Two bugs are found relating search algorithm, word insertion penalty handling on grammar recognition and LM score handling of the first word on the second pass.
They have been fixed on this release.
If you have been encountering unreasonable search failures on the second pass,
they may be eased by using the newest version.

Other bugs are also fixed.
See "Release.txt" for the full list of the fixed bugs.

ChangeLog

Bug fixes:

- Language model / decoding (these bugs may affect the ASR performance):
- Several wrong word insertion penalty handling on grammar was found and fixed.
- Now correctly add the prob. of the first word at the second pass.

- MFCC computation:
- Support MFCC computation when liftering parameter (CEPLIFTER) = 0.

- Compilation:
- Fixes to build Julius on cygwin and MSVC.
- Supports "gcc -mno-cygwin" on cygwin.
- Compilation error with configure "--disable-plugin"

- Module mode:
- Unable to send grammar from jcontrol.
- Not working "DELPROCESS" command when SR and LM has different names.

- Other fixed bugs:
- wrong parsing of "-mapunk" option.
- "-htkconf" in a jconf file now correctly handles the file path as relative to the jconf file.
- "-input stdin" now supports WAV format.
- not working "-plugin DIRNAME" on Win32/MSVC.

Juliusbook - 4.1.5

Julius (julius4) — Thu, 03 Jun 2010 15:00:00 GMT

ReleaseNote

Update for Ver 4.1.5.

julius - 4.1.4

Julius (julius4) — Fri, 25 Dec 2009 03:05:00 GMT

ReleaseNote

This release contains minor fixes: improved Julius class definition on Microsoft Visual C++ 2008, fixes for audio input on Windows, and support for Mac OS X 10.6 SDK.
Now you can select the audio device to use on Windows.
See "Release.txt" for details of the changes.

ChangeLog

New feature:
- added function to choose input audio device on MSVC compiled Julius,
by specifying a device ID with env. var. "PORTAUDIO_DEV_NUM".
The available device IDs will be listed in the system log at start up.
- You can now set a locale for a LM in Julius.cpp.

Bug fixes:
- now can be compield on Mac OS X (OS X 10.6 SDK).
- fixes around portaudio for smaller latency and compatibility (Windows).

dictation-kit - 4.0

Julius (julius4) — Thu, 17 Dec 2009 10:07:00 GMT

ReleaseNote

Update for 4.1.3.

Juliusbook - 4.1.3

LEE Akinobu (sumomo) — Tue, 27 Oct 2009 08:12:00 GMT

ReleaseNote

Update for Ver 4.1.3.　Very minor updates for portaudio related part only.

julius - 4.1.3

LEE Akinobu (sumomo) — Tue, 27 Oct 2009 08:07:00 GMT

ReleaseNote

This release has a new support for building Julius on Microsoft Visual C++ 2008. A sample wrapper class that handles Julius engine is also included, with a sample application. See "msvc/00README.txt" for details.

It also support N-gram of arbitrary N, portaudio extension (V19 and external library support) and many bug fixes.

ChangeLog

4.1.3 (2009.11.02)
===================

New features:
- new MSVC support: please read "msvc/00README.txt"
- extended N-gram to support arbitrary N
- portaudio external library (V19) can be used instead of internal V18.
When configure detects portaudio library installed in your system,
Julius will use it instead of internal V18. You can also choose
input device by "PORTAUDIO_DEV" env. var. at V19library. See the
log text at start up to know how to set it.
- allow word alignment output (-walign) in module mode

Modified:
- ! now Julius do not perform CMN on 0'th cepstral coefficients,
which is the same as the old 4.0.x versions.
- j_get_current_filename() added on JuliusLib
- improved "--enable-wpair" handling

Bug fixes:
- many bugs around audio open/close API on JuliusLib
- fail to do make in julius-simple
- unable to record inputs at cygwin
- segfault on adintool with "-server"
- occasional segfault at grammar recognition

julius - 4.1.2

LEE Akinobu (sumomo) — Wed, 11 Feb 2009 09:06:00 GMT

ReleaseNote

4.1.2 is a bug fix release. It includes many fixes for N-gram. It now allows over 2GB N-gram, improved support for SRILM, and correct handling of unknown words. Some bugs and improvements that has been reported on the Forum has been also fixed.

ChangeLog

[SRILM support]
- Added swapping "<s>" and "</s>" when reading BACKWARD ARPA file trained by SRILM. It will be automatically detected. If detection fails, you can specify an option "-swap" in mkbingram to do that.
- Internally modify the unigram probability of "<s>" or "</s>", since they may be set to "-99" in SRILM model. The same value as opposite will be assigned.
[N-gram]
- Size limit extended from 2GB to 4GB for big N-gram.
- "<unk>" and "<UNK>" can be changed by "-mapunk".
- More strict check for unknown words: Julius now terminates with error when dictionary has OOV words and N-gram is not open (no unk word).
[Improvements]
- Faster successor list building algorithm
- Update yomi2voca.pl to cover more minor Japanese pronunciation.
- Workaround for audio buffer overrun in ALSA
[JuliusLib]
- Added API function "j_close_stream()" to exit main recognition loop.
[Bug Fixes]
- Fixed segfault on adintool when specifying multiple servers.
- Fixed compilation error on cygwin (libesd)
- Fixed segfault when not specifying "-input" option.

Juliusbook - 4.1.2

LEE Akinobu (sumomo) — Wed, 11 Feb 2009 09:02:00 GMT

ChangeLog

Minor updates for 4.1.2:
- Add section for SRILM (Japanese)
- new option "-mapunk"

Information about using SRILM model in Julius will be available on the Web Forum.

julius - 4.1.1

LEE Akinobu (sumomo) — Sat, 13 Dec 2008 13:25:00 GMT

ReleaseNote

Revision 4.1.1 is a bug fix release. Many bugs are fixed relating
N-gram handling (tested on SRILM), module mode and more. All users
that uses older versions of Julius-4 are strongly recommended to use
this version.

ChangeLog

Bug fixes:

[N-gram]
- sometimes could not read an ARPA N-gram file trained by SRILM.
[A/D-in]
- "-input stdin" does not work.
- "SOURCERATE" at "-htkconf" is ignored.
[Forced alignments]
- now can be used in isolated word recognition and with "-1pass".
- "-palign", "-walign" and "-salign" can not be run together at a time.
[Module mode]
- freezes when a grammar is specified by its ID number.
- wrong grammar ID in recognition result (GRAM=.. always 0)
- "SYNCGRAM" will cause crash at isolated word recognition.
- unable to receive/activate/dactivate on isolated word recognition.
[Others]
- fails to compile on several OS (needs "-ldl").
- does not handle backslash escaping correctly in Jconf file.
- does not output the 1st pass result as a final result with "-1pass".
[Tools]
Jcontrol
- does not support "graminfo" command.
- can not send a dictionary to Julius running isolated word recognition.
mkdfa
- segfault on mkfa
- fails to read a grammar file on DOS format.
adintool
- wrong behavior when splitting a long audio file.
- now output time of each segment.

Juliusbook - 4.1-ja

LEE Akinobu (sumomo) — Sat, 04 Oct 2008 11:48:00 GMT

julius - 4.1

LEE Akinobu (sumomo) — Thu, 02 Oct 2008 16:45:00 GMT

ReleaseNote

What's new in Julius-4.1
==========================

From 4.0 to 4.0.2, many bugs are fixed and small improvements were
done. New options "-fallback1pass" and "-usepower" were added. The
default audio API is changed from "oss" to "alsa" on Linux.

From 4.0.2 to 4.1, multi-stream AM, MSD-HMM, CVN, frequency warping
for VTLN are all supported. "jclient-perl", a perl version of module
mode client, is newly added.

Plug-in support is newly implemented on rev. 4.1. Using dynamic
object linking, Julius now can load extensions at run time, and extend
its ability easily without modifying the original engine source code.
The directory "plugin" contains several example source codes and ready
to compile and test them. The source codes also contain all function
specification documents.

From this release, you can get the total documentation of Julius
called "Juliusbook". It is written in Docbook XML, and PDF version
and HTML version is available. At this time English version has only
the option descriptions and online manuals. Full version that
explains all aspects and specification of Julius (models, input,
decoding, etc...) will be released within a short term.

ChangeLog

4.1 (2008.10.3)
================
New plugin extension:
- supported types:
- A/D-in plugin
- feature vector input plugin
- audio input monitor / postprocess plugin
- feature vector monitor / postprocess plugin
- result plugin
- can add arbitrary JuliusLib callback via plugin
- sample codes is included, with full documentation of function spec.
- run on Linux, Windows and other unix variants with dlopen() capability

Newly supported features:
- multi-stream feature input
- MSD-HMM (compatible with "HTS" toolkit)
- CVN
- frequency warping for VTLN (no estimation yet)
- "-input alsa", "-input oss" and "-input esd"
- perl version of jcontrol client "jclient-perl"

Modified:
- Restrict option orders when multiple instances defined (-AM, -LM, -SR):
- Option should be just after correspondence instance declaration.
(ex. LM options should be placed after "-LM" and before other
instance declaration.)
- Global option should be before any instance declaration, or
just after "-GLOBAL" option.
This new restriction can be removed by "-nosectioncheck" option.

Fixed bugs:
- "-record" fails to record the first silence part!
- Not working "-multigramout"
- environment variable expansion sometimes fail within jconf file.
- limits extended:
maximum HMM name length = 256 char, Number of HMM states unlimited.
- Module mode error message on grammar command.

Documents:
- Alpha version of "Juliusbook" (contains only manuals at this time)
- Unix manuals are moved to "man" directory.

segmentation-kit - 1.0-julius4

LEE Akinobu (sumomo) — Mon, 18 Aug 2008 02:16:00 GMT

ReleaseNote

Segmentation kit update for Julius-4.

ChangeLog

Minor update to be used with Julius-4.

julius - 4.0.2

LEE Akinobu (sumomo) — Tue, 27 May 2008 09:41:00 GMT

ReleaseNote

Julius rev.4.0.2 is a bug fix release.
Please see Release.txt for detailed list of fixes.

ChangeLog

4.0.2 (2008.5.27)
==================
New features:

- New option "-fallback1pass" will output 1st pass result as final result
when the 2nd pass fails.
- Added support for "USEPOWER=T" on feature extraction.

Modified:
- "-AM_GMM" becomes optional: GMM will share AM params if not specified.

Fixed:
- GMM rejection does not work (since 4.0.1)
- Cannot specify other A/D device on Linux/ALSA correctly.
- Sometimes fails to read a big N-gram.
- Sometimes crush with "-record" option.
- Callback timing modified on real-time input with sp-segment/GMM/VAD.
- Other minor fixes.

julius - 4.0.1

LEE Akinobu (sumomo) — Wed, 12 Mar 2008 08:58:00 GMT

ReleaseNote

Julius rev.4.0.1 is a bug fix release.
It is recommended for all users using 4.0 to use this release.

Now ALSA is the default audio API on Linux. You can still use
the old OSS interface by specifying "--with-mictype=oss" for
the configure script at compilation time.

ChangeLog

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.

dictation-kit - 3.2

LEE Akinobu (sumomo) — Thu, 17 Jan 2008 12:56:00 GMT

ReleaseNote

Update for 3.5.3.

wordflow - 0.5

LEE Akinobu (sumomo) — Wed, 19 Dec 2007 15:57:00 GMT

ReleaseNote

Word flow is a sample GUI application of word recognition that
uses JuliusLib rev.4.0, based on SDL libraries.

ChangeLog

Initial release.

julius - 4.0

LEE Akinobu (sumomo) — Wed, 19 Dec 2007 06:58:00 GMT

ReleaseNote

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.

slf2dfa - 1.0

LEE Akinobu (sumomo) — Fri, 29 Dec 2006 03:05:13 GMT

ReleaseNote

Initial release:

This is a set of tools that convert any HTK SLF grammar to Julian DFA format. Please read README in the archive for details.

ChangeLog

Initial release.

julius - 3.5.3

LEE Akinobu (sumomo) — Fri, 29 Dec 2006 02:57:00 GMT

ReleaseNote

Julius/Julian rev.3.5.3 is an update release. The most outstanding
feature of this release is that some code optimization around acoustic
computation made the recognition process faster up to 1.5 times.
Other improvements has been done for graph precision, usability,
stability and code modurality. All users using previous versions of
Julius/Julian are encouraged to upgrade to this release.

Summary of changes in 3.5.3:

o Recognition speed-up by code optimization for acoustic
computation and memory allocation.
o Support another way of specifying acoustic parameter conditions:
- can read an HTK Config file directly by "-htkconf".
- can embed acoustic analysis condition parameters into binary AM.
o New grammar-related tools: "dfa_minimize", "dfa_determinize".
(An HTK-to-Julian automatic grammar convertion tool "slf2dfa" is
also released)
o Other refinements:
- support generating separate candidates of different phone
context in word graph output.
- preliminary support for emulating energy normalization on live input.
o Bug fixes and code improvements.

Details of the changes are listed in "Release.txt".

Please note that if you want to compile Julius with DirectSound
support, you need DirectX headers installed in your mingw / cygwin
environment. If not exist, configure will choose an old interface.
Please see install instruction on the Web.

ChangeLog

3.5.3 (2006.12.29)
===================
o Improved Performance:
- acoustic computation optimized: now becomes 20%-40% faster!
- optimize memory access: re-use work area of deleted hypothesis
in the 2nd pass.
- some memory allocation improvement on dictionary and word trellis.

o New Grammar Tools:
- "dfa_minimize", "dfa_determinize" will minimize/determinize DFA.
mkdfa.pl now calls dfa_mimize in it.
- "slf2dfa": a toolkit to convert HTK slf to Julian dfa (separate kit)

o Embedding HTK Acoustic Parameters:
- add option to load HTK Config file to set correct acoustic parameter
configuration at recognition time.
- the acoustic parameter configuration can be embedded into
header of a binary HMM file.

o Improved Word Graph:
- add an option to completely separate graph words: words with
different phone contexts can be output separatedly by
"-graphrange -1".

o Support for online energy normalization:
- Preliminary support for live recognition using acoustic model with
energy normalization. (approximate with maximum energy of last input)

o Code refinements:
- re-organize libsent/src/wav2mfcc.
- modularize acoustic parameter (Value) handling.
- output compile-time configuration of libsent with "--setting" option.
- Doxygen 1.5.0 support.
- "julius-info@lists.sourceforge.jp" becomes the official contact address.
- fixed typo on copyright notice.

o Fixed bugs:
- sometimes unable to read a binary LM on "--enable-words-int".
- memory leaks around option handling, global variables and local buffers.
- segmentation fault on very long input.
- doublely counted initial state of DFA.
- mkdfa.pl: unable to find mkfa on some OS.
- adintool: makes empty output file on termination.
- adintool: miss last inputs when killed.
- other small changes.

julius - 3.5.2

LEE Akinobu (sumomo) — Sat, 29 Jul 2006 14:30:00 GMT

ReleaseNote

What's new in Julius-3.5.2 ?
=============================

Julius/Julian rev.3.5.2 is a minor update to improves performance on
Windows, enhancements and fixes for word graph outputs, and other bug
fixes. All users of previous version is encouraged to upgrade to 3.5.2.

Summary of changes in 3.5.2:

o Speed-up and improvement on Windows console.
- DirectSound
- Recent MinGW support
o More accurate word graph output.
- new optimization params: -graphcut, -graphboundloop, -graphsearchdelay
o Add capability to output word graph instead of trellis on 1st pass.
o Bug fixes.
o Imprementation improvements.

Details of the changes are listed in "Release.txt".

Please note that if you want to compile Julius with DirectSound
support, you need DirectX headers installed in your mingw / cygwin
environment. If not exist, configure will choose an old interface.
Please see install instruction on the Web.

ChangeLog

3.5.2 (2006.07.31)
===================
o Speed-up and improvement on Windows console:
- Support DirectSound for better input handling
- Support input threading utilizing callback API on portaudio.
- Support newest MinGW (tested on 5.0.2)

o More accurate word graph output:
- Add option to cut the resulting graph by its depth
(option -graphcut, and enabled by default!)
- Set limit for post-processing loop to avoid infinite loop
(option -graphboundloop, and set by default)
- Refine graph generation algorithm concerning dynamic word merging
and search termination on the second pass.

o Add capability to output word graph instead of trellis on 1st pass:
- 1st pass generates word graph instead of word trellis as
intermediate result by specifying "--enable-word-graph".
In that case, the 2nd pass will be restricted on the graph, not
on the whole trellis.
- With "--enable-word-graph" and "--enable-wpair" option, the
first pass of Julius can perform 1-pass graph generation based
on 2-gram with basically the same algorithm as other popular
word graph based decoders.

o Bug fixes:
- configure script did not work on Solaris 8/9
- "-gprune none" did not work on tied-mixture AM
- Incorrect error message for AM with duration header other than "NULLD"
- Always warns abount zero frame stripping upon MFCC

o Imprementation improvements:
- bmalloc2-based AM memory management

julius - 3.5.1

LEE Akinobu (sumomo) — Thu, 30 Mar 2006 07:04:00 GMT

ReleaseNote

======================================================================
Large Vocabulary Continuous Speech
Recognition Engine

Julius

(Rev 1.0 1998/02/20)
(Rev 2.0 1999/02/20)
(Rev 3.0 2000/02/14)
(Rev 3.1 2000/05/11)
(Rev 3.2 2001/06/18)
(Rev 3.3 2002/09/12)
(Rev 3.4 2003/10/01)
(Rev 3.4.1 2004/02/25)
(Rev 3.4.2 2004/04/30)
(Rev 3.5 2005/11/11)
(Rev 3.5.1 2006/03/31)

Copyright (c) 1991-2006 Kawahara Lab., Kyoto University
Copyright (c) 1997-2000 Information-technology Promotion Agency, Japan
Copyright (c) 2000-2005 Shikano Lab., Nara Institute of Science and Technology
Copyright (c) 2005-2006 Julius project team, Nagoya Institute of Technology
All rights reserved

======================================================================

What's New in Julius-3.5.1 ?
=============================

Julius/Julian rev.3.5.1 enhances MFCC parameter extraction function to
enable direct speech recognition on various kinds of acoustic model.
It also improves direct microphone / network input recognition by
MAP-CMN. Bugs on module mode, large N-gram, multi-path version are
fixed.

Summary of changes in 3.5.1:

o Wider MFCC support to enable direct speech recognition on various AM:
- Added extraction of acceleration coefficients (_A).
- Support all MFCC qualifier conbination.
- Added options to specify detailed analysis parameters.

o Improved microphone / network recognition by MAP-CMN:
- Cepstral mean of last 5 second input is used as an initial mean
for each input. You can inhibit updating of the initial mean
and keep the value loaded by "-cmnload" by option "-cmnnoupdate".

o Module mode:
- Julius will output "<STARTPROC/>" when recognition starts, and
"<STOPPROC/>" after recognition stopped by module command.
It may help some server-client synchronization problem.

o Bug fixes:
- Sometimes segfault on pause/resume command on module mode.
- Can not read N-gram whose tuples > 2^24 (enbuged on 3.5).
- Can not read HMM with 3-state (1 output state) model on multi-path.
- Sometimes omit the last line in DFA file.
- Sometimes fails to compile gramtools on MacOSX.

All the changes are listed in "Release.txt".

Contents of Julius-3.5.1
=========================

(Documents with suffix "ja" are written in Japanese)

00readme.txt ReadMe (This file)
LICENSE.txt Terms and conditions of use
Release.txt Release note / ChangeLog
configure configure script
configure.in
Sample.jconf Sample configuration file for Julius-3.5.1
Sample-julian.jconf Sample configuration file for Julian-3.5.1
julius/ Julius/Julian 3.5.1 sources
libsent/ Julius/Julian 3.5.1 library sources
adinrec/ Record one sentence utterance to a file
adintool/ Record/split/send/receive speech data
gramtools/ Tools to build and test recognition grammar
jcontrol/ A sample network client module
mkbingram/ Convert N-gram to binary format
mkbinhmm/ Convert ascii hmmdefs to binary format
mkgshmm/ Model conversion for Gaussian Mixture Selection
mkss/ Estimate noise spectrum from mic input
support/ some tools to compile julius/julian from source
olddoc/ ChangeLogs before 3.2

From rev.3.4, a grammar-based recognizer called "Julian" is also
included. the Julian can be compiled from Julius sources by
specifying configure option "--enable-julian". The grammar format
Julian uses is original one based on BNF. A grammar compiler that
converts the written BNF to finite state grammar, and several test
tools are included in this archive.

About Documentation
====================

- Documents

The overall document that contains installation procedure,
tutorial, model formats and more, are available at:

http://julius.sourceforge.jp/en/Julius-3.2-book-e.pdf

It is basically based on rev.3.2, but will be also helpful for
recent versions.

The most up-to-date documentations and references can be available
on the Julius Web site.

http://julius.sourceforge.jp/en/

Please refer to other documents in Japanese at:

http://julius.sourceforge.jp/

- Recent changes

Changes between releases are fully listed in "Release.txt".

- Online reference manuals

for Julius, adintool, and other tools can be obtained in each
source directory, in both Unix man format and plain text.

For more information, see the URL below:

http://julius.sourceforge.jp/ (Japanese)
http://julius.sourceforge.jp/en/ (English)

Some documents are available only in Japanese. We are sorry for the
inconvenience.

LICENSE
========

Julius is an open-source software distributed as is, and available for
free. For more information about its license, please refer to
"LICENSE.txt" in this archive.

ChangeLog

3.5.1 (2006.03.31)
===================
o Wider MFCC types support:
- Added extraction of acceleration coefficients (_A). Now you
can recognize waveform or microphone input with AM trained with _A.
- Support all MFCC qualifiers (_0, _E, _N, _D, _A, _N, _Z) and their
combination
- Support for any vector lenth (will be guessed from AM header)
- New option: "-accwin"
- New option "-zmeanframe": frame-wise DC offset removal, like HTK
- New options to specify detailed analysis parameters (see manual):
-preemph, -fbank, -ceplif, -rawe / -norawe,
-enormal / -noenormal, -escale, -silfloor

o Improved microphone / network recognition by MAP-CMN:
- New option "-cmnmapweight" to change MAP weight
- Option "-cmnload" can be used to specify the initial cepstral
mean at startup
- Cepstral mean of last 5 second input is used as an initial mean
for each input. You can inhibit updating of the initial mean
and keep the value loaded by "-cmnload" by option "-cmnnoupdate".

o Module issue:
- Julius now outputs "<STARTPROC/>" when recognition starts, and
"<STOPPROC/>" after recognition stopped by module command.
Use this for safer server-client synchronization.
- now can specify grammar name from client by specifying a name
after a command like "ADDGRAM name" or "CHANGEGRAM name".

o Bug fixes:
- Sometimes segfault on pause/resume command on module mode while input.
- Can not read N-gram with tuples > 2^24.
- Can not read HMM with 3-state (1 output state) model on multi-path.
- Sometimes omit the last transition definition in DFA file.
- Sometimes fails to compile the gramtools on MacOSX.

julius - 3.5

LEE Akinobu (sumomo) — Fri, 11 Nov 2005 10:00:00 GMT

ReleaseNote

======================================================================
Large Vocabulary Continuous Speech
Recognition Engine

Julius

(Rev 1.0 1998/02/20)
(Rev 2.0 1999/02/20)
(Rev 3.0 2000/02/14)
(Rev 3.1 2000/05/11)
(Rev 3.2 2001/06/18)
(Rev 3.3 2002/09/12)
(Rev 3.4 2003/10/01)
(Rev 3.4.1 2004/02/25)
(Rev 3.4.2 2004/04/30)
(Rev 3.5 2005/11/11)

Copyright (c) 1991-2005 Kawahara Lab., Kyoto University
Copyright (c) 1997-2000 Information-technology Promotion Agency, Japan
Copyright (c) 2000-2005 Shikano Lab., Nara Institute of Science and Technology
Copyright (c) 2005 Julius project team, Nagoya Institute of Technology
All rights reserved

======================================================================

What's New in Julius-3.5?
==========================

Julius/Julian rev.3.5 is a major update that incorporates several new
functions that may be useful for realizing a speech interface.
Memory efficiency is also improved. Another big progress to system
developers is that the comments in source codes are fully re-written
to be able to cross-reference in HTML format.

Summary of changes in 3.5:

- New features
- Input verification / rejection concurrently with recognition process
based on one-state GMM scores
- Word graph output
- Arbitrary character set conversion for tty/module output
- Improved multi grammar support on Julian
- EsounD audio server support on Linux
- Linux and Windows version have been integrated into one source
- Multi-path version has been integrated to the original.
(can use by "--enable-multipath" at compilation time)
- Migrated from VC++ to minGW on Windows
- Improved memory size
- Remove redundant part of tree lexicon and beam work area for 1st pass.
- Compaction of word N-gram index (reduced from 32 bit to 24 bit).
- New N-gram binary format (can still read old binary).
- Many bug fixes
- Spectral subtraction now works.
- Fixed newline code problems in Win&Mac (grammar files and -filelist).
- Fix USB audio input in Linux.
- Many other fixes.
- Documentation
- Doxygen support (you can generate full source documents in English!)
- Remove old Japanese documents in doc.

All the changes are listed in "Release.txt".

Contents of Julius-3.5
=======================

(Files with "ja" are written in Japanese)

00readme.txt ReadMe (This file)
LICENSE.txt Terms and conditions of use
Release.txt Release note / ChangeLog
configure configure script
configure.in
Sample.jconf Sample configuration file for Julius-3.5
Sample-julian.jconf Sample configuration file for Julian-3.5
julius/ Julius/Julian 3.5 sources
libsent/ Julius/Julian 3.5 library sources
adinrec/ Record one sentence utterance to a file
adintool/ Record/split/send/receive speech data
gramtools/ Tools to build and test recognition grammar
jcontrol/ A sample network client module
mkbingram/ Convert N-gram to binary format
mkbinhmm/ Convert ascii hmmdefs to binary format
mkgshmm/ Model conversion for Gaussian Mixture Selection
mkss/ Estimate noise spectrum from mic input
support/ some tools to compile julius/julian from source
olddoc/ ChangeLogs before 3.2

From rev.3.4, a grammar-based recognizer called "Julian" is also
included. the Julian can be compiled from Julius sources by
specifying configure option "--enable-julian". The grammar format
Julian uses is original one based on BNF. A grammar compiler that
converts the written BNF to finite state grammar, and several test
tools are included in this archive.

About Documentation
====================

- Documents

The overall document that contains installation procedure,
tutorial, model formats and more, are available at:

http://julius.sourceforge.jp/en/Julius-3.2-book-e.pdf

It is basically based on rev.3.2, but will be also helpful for
recent versions.

The most up-to-date documentations and references can be available
on the Julius Web site.

http://julius.sourceforge.jp/en/

Please refer to other documents in Japanese at:

http://julius.sourceforge.jp/

- Recent changes

Changes between releases are fully listed in "Release.txt".

- Online reference manuals

for Julius, adintool, and other tools can be obtained in each
source directory, in both Unix man format and plain text.

For more information, see the URL below:

http://julius.sourceforge.jp/ (Japanese)
http://julius.sourceforge.jp/en/ (English)

Some documents are available only in Japanese. We are sorry for the
inconvenience.

LICENSE
========

Julius is an open-source software distributed as is, and available for
free. For more information about its license, please refer to
"LICENSE.txt" in this archive.

ChangeLog

3.5 (2005.11.11)
=================
o New features:
- Input verification / rejection using GMM (-gmm, -gmmnum, -gmmreject)
- Word graph output (--enable-graphout, --enable-graphout-nbest)
- Pruning on 2nd pass based on local posterior CM (--enable-cmthres)
- Multiple/per-grammar recognition (-gram, -gramlist, -multigramout)
- Can specify multiple grammars at startup: "-gram prefix1,prefix2,..."
or "-gramlist listfile" where listfile contains list of prefixes.
- General output character set conversion "-charconv from to"
based on iconv (Linux) or Win32API+libjcode (Windows)

o Improved audio inputs on Linux:
- ALSA-1.x support. (--with-mictype=alsa)
- EsounD daemon input support. (--with-mictype=esd)
- Fixed some bugs on USB audio input.
- Audio capturing device can be specified via env. "AUDIODEV".
- Extra microphone API support using portaudio and spLib API.

o Performance improvements:
- Reduced memory size for beam operation on the 1st pass.
- Slightly optimized tree lexicon by removing redundant data.
- Reduced size of word N-gram index (reduced from 32 bit to 24 bit).

o Fixed bugs:
- Not working spectral subtraction.
- Memory leak when stack exhausted ("stack empty") on 2nd pass.
- Segmentation fault on a very short input of 1 to 4 frames.
- AM trained with no CMN cannot be used with waveform/mic input.
- Wrong short-pause word handling on successive decoding mode.
(--enable-sp-segment)
- No output of "maxcodebooksize" at startup.
- No output of the number of sentences found when stack exhausted.
- No output of "-separatescore" on module mode.
- Beam width does not adjusted when grammar has been changed and
full beam options (-b 0) is specified in Julian.
- Wrong update of category-aware cross-word triphones when
dynamically switching grammar on Julian.
- No output of grammar to stdout on multiple grammar mode.
- Unable to send/receive audio data between different endian machines.
- (Linux) crash when compiled with icc.
- (Linux) some strange behavior on USB audio.
- (Windows) confuse with CR/LF newline inputs in several text inputs.
- (Windows) mkdfa.pl could not work on cygwin.
- (Windows) sometimes fails to read a file when not using zlib.
- (Windows) wrong file suffix when recording with "-record" (.raw->.wav)

o Unified source code:
- Linux and Windows version are integrated into one source.
- Multi-path version has been integrated with the normal version
into one source. The multi-path version of Julius/Julian, that
allows any transitions of HMMs including model skip transition,
can be compiled by "--enable-multipath" option. The part of
source codes for the multi-path version can be identified
by the definition "MULTIPATH_VERSION".

o Other improvements:
- Now can be compiled on MinGW/MSYS on Windows
- Totally rewritten comments in entire source in Doxygen format.
You can generate fully browsable source documents in English.
Try "make doxygen" at the top directory (you need doxygen installed)
- Install additional executables of julius/julian with version and setting
names like "julius-3.5-fast" when "make install" is invoked.
- Updated LICENSE.txt with English translation for reference.

o Changed behaviors:
- Binary N-gram file format has been changed for smaller size.
The old files can still be read directly by julius, in which
case on-line conversion will be performed at startup.
You can convert the old files (3.4.2 and earlier) to the new
format with the new mkbingram by involing the command below:
"mkbingram -d oldbinary newbinary"
Please note that since mkbingram now output the new format
file, it can not be read by older Julius.
The binary N-gram file version can be detected by the first 17
bytes of the file: old format should be "julius_bingram_v3" and
new format should be "julius_bingram_v4".
- Byte order of audio stream via tcpip fixed to LITTLE ENDIAN.
- Now use built-in zlib by default for compressed files. This may
make the engine startup slower, and if you prefer, you can still
use the previous method using external gzip command by specifying
"--disable-zlib".
- (Windows) Changed the compilation procedure on VC++. You can build
Julian by only specifying "-DBUILD_JULIAN" at compiler option,
and do not need to alter "julius.h".