Julius

Not Rated
Tags: speech

Description
"Julius" is a high-performance, two-pass large vocabulary continuous speech recognition (LVCSR) decoder software for speech-related researchers and developers. Based on word N-gram and context-dependent HMM, it can perform almost real-time decoding on most current PCs in 60k word dictation task. Major search techniques are fully incorporated such as tree lexicon, N-gram factoring, cross-word context dependency handling, enveloped beam search, Gaussian pruning, Gaussian selection, etc. Besides search efficiency, it is also modularized carefully to be independent from model structures, and various HMM types are supported such as shared-state triphones and tied-mixture models, with any number of mixtures, states, or phones. Standard formats are adopted to cope with other free modeling toolkit such as HTK, CMU-Cam SLM toolkit, etc.

The main platform is Linux and other Unix workstations, and also works on
Interface: Command Line
Associated Programs
julius-voxforge acoustic models for Julius (English)
Available deb Repositories (how-to add a respository)
Ubuntu 32-bit 64-bit
lucid 4.1.2-0ubuntu1 4.1.2-0ubuntu1
precise 4.1.5-0ubuntu1 4.1.5-0ubuntu1
raring 4.2.2-0ubuntu2 4.2.2-0ubuntu2
saucy 4.2.2-0ubuntu2 4.2.2-0ubuntu2
trusty 4.2.2-0ubuntu2 4.2.2-0ubuntu2

Rating: Not Rated (0 votes)


Login or Register to rate Julius, add a Tag, or designate as an alternative to a Windows app



Upload Screenshots
Images must be in GIF, JPG, or PNG formats and can be no larger than 2 MB. Only one file can be uploaded at a time. A description can be included, but it is optional.
Desc:
File:
You must login or register to upload a screenshot.
Submit Web Links
Submit the title and link (including http://) to an article pertaining to Julius and it will appear in the Web Links section of the right banner. Contact us here if an entry needs to be removed.
Title:
Link:
You must login or register to post links.