Projects / Julius Speech Recognition Engine

Julius Speech Recognition Engine

Julius is a high-performance large vocabulary continuous speech recognition (LVCSR) engine for speech-related research and development. You can construct your own speech recognition system, but you need a separate English acoustic model and language model or grammar file.

Operating Systems

Recent releases

  •  04 Jan 2007 04:13

    Release Notes: Acoustic computation is now 20-40% faster. New grammar tools were provided, including "slf2dfa", a toolkit for converting HTK slf to Julian dfa. An option to load an HTK Config file to set correct acoustic parameter configuration was provided. Acoustic parameter configuration can be embedded into the header of a binary HMM file. Preliminary support for live recognition using an acoustic model with energy normalization was implemented.

    •  04 Oct 2006 19:23

      No changes have been submitted for this release.


      Project Spotlight


      A Fluent OpenStack client API for Java.


      Project Spotlight

      TurnKey TWiki Appliance

      A TWiki appliance that is easy to use and lightweight.