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.
Moved to github: https://github.com/julius-speech/julius
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.
バージョン 4.1.2はN-gramに関する多くの修正が含まれています．2GB以上のサイズの N-gram への対応，SRILM で学習されたN-gramへの対応，および語彙外語（<unk>）の扱いの改善です．また，フォーラムで報告されたいくつかのバグや機能不全への修正も行われました．
[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.
[N-gram]
- サイズ上限を 2GB から 4GB に拡張
- "-mapunk" で unknown word を指定可能に．デフォルトは "<unk>" "<UNK>"
- チェックの厳密化：辞書に未知語がある場合，N-gram に "<unk>" が無いとエラー
[SRILM対応]
- backward ARPA 読み込み時に <s> </s> を自動入れ替え
- mkbingram で backward ARPA 読み込み時に "-swap" で明示的に入れ替え
- <s>の 1-gramが必ず -99 になるのを自動修正
[機能改善]
- successor list 構築アルゴリズムを高速化．
- yomi2voca.pl 更新
- ALSA audio buffer overrun 対策
- generate-ngram の -debug 指定時の挙動を変更
[JuliusLib]
- j_close_stream() 追加
[バグ修正]
- adintool 複数サーバ指定できないバグ修正
- cygwin でのコンパイルエラー修正 (libesd)
- "-input" 無指定時に落ちるバグを修正
