Develop and Download Open Source Software

Julius

[view other images]

Julius is an open-source, high-performance large vocabulary continuous speech recognition (LVCSR) engine for speech-related researchs and developments. With HMM acoustic model and language model, you can construct your own speech recognition system.

Would you recoomend this project?

LastUpdate:2012-01-18 19:56
Member:forsteri, julius, julius4, kudravka_, sumomo, itonao [View]
Other Info.

Latest File Releases of Julius

PackageVersionDateNotes
/ Change Log
Juliusbook4.1.52010-06-04 00:00Document / Document

Update for Ver 4.1.5.

dictation-kit4.22011-05-11 00:00Document / Document

Update for Julius rev.4.2.

grammar-kit4.22011-05-11 00:00Document / Document

Update for Julius rev.4.2.

julius4.2.12011-12-25 00:00Document / Document

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.

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.

sample_grammars200508172005-08-29 12:09Document / Document

Julian 用のサンプル文法です。
音声認識に使える 11個の認識用文法が含まれています。
.tar.gz がEUC版(Linux向け)、.zipがSJIS版(Windows向け)です。

segmentation-kit4.02011-03-03 00:00Document / Document

Update for 4.1.5.

simpleword-kit2.02005-08-29 16:36Document / Document

Julian を用いた簡単な単語認識を行うキットです。
単語を登録するだけで、とりあえずその単語を認識することができます。
Julianの本格的な使用には文法を書くことが必須ですが、
とりあえず単語だけ認識したい!という方はこちらを
試してみては。

動作にはJulianの実行バイナリおよび音響モデルが必要です。
Julian実行キットから入手できます。

2003/11/21 ver.2.0
- Julian ベースの最初のバージョン

slf2dfa1.02006-12-29 12:05Document / Document

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.

Initial release.

wordflow0.52007-12-20 00:57Document / Document

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

Initial release.

  • Review
  • News
  • Ticket
  • RSS

Project ReviewsProject Review by Users

5 Stars
(75)
4 Stars
(0)
3 Stars
(1)
2 Stars
(0)
1 Star
(8)
Julius's rating is

Last 3 reviews

ee

Was this review helpful for you?:
YesNo
0


2
Project Review by Anonymous - 2010-09-12 01:07

They fail to explain how to set up the program

Was this review helpful for you?:
YesNo
0


3
Project Review by Anonymous - 2010-08-20 06:01

よい

Was this review helpful for you?:
YesNo
0


2
Project Review by Anonymous - 2010-07-29 13:20

Latest Project News for Julius

No Project News

RSS Feeds List for Julius

URL: http://sourceforge.jp/projects/julius/news/rss
URL: http://sourceforge.jp/projects/julius/releases/rss
URL: http://sourceforge.jp/projects/julius/reviews/rss
URL: http://sourceforge.jp/export/rss_milestone.php?group_id=232
URL: http://sourceforge.jp/projects/julius/history/rss

Software Map