Download List


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:


System requirement is not defined

发布: 2003-05-06 18:11
julius 3.3p4 (4 files 隐藏)


3.3p4 (2003.05.06)
BUG FIX release: several bugs relating audio input are now fixed.


3.3p4 (2003.05.06)
- Fixes for audio input:
- Fix segfault/hangup with continuous microphone input.
- Fix client hangup when input speech too long in module mode.
(now send an buffer overflow message to the client)
- Fix audio input buffering for very short input (<1000 samples).
- Fix blocking handling in tcpip adin.
- Some cosmetic changes (jcontrol, LOG_TEN, etc.)