Languages
VoxForge
VoxForge
This QuickStart download was designed to highlight the use of VoxForge Acoustic Models with Open Source Speech Recognition Engines. We will start with a download that uses the Julius Speech Recognition Engine.
These downloads contain everything you need to get Julius working:
Click the link for your operating system for the and follow the instructions in the enclosed README file. You can also try one of the Nightly Builds for the most up to date version of the Acoustic Models.
|
Notes: 1. The Acoustic Models currently included with the QuickStart Downloads are still in alpha stage, so the recognition quality reflects this. We need much more GPL transcribed speech audio to create decent quality Acoustic Models. So please take the time to submit some transcribed speech to VoxForge. Go to the Read page for instructions on how to do this. 2. A "Speech Recognition Engine" (like Julius) is only one component of a Speech Command and Control System (where you can speak a command and the computer does something). You still need a Dialog Manager to understand what to do with the recognition results from the speech recognition engine (i.e. to take the words recognized by the Speech Recognition Engine, and make the computer do something useful). VoxForge has not yet created a dialog manager for use with Julius. |
