News

The Julius speech recognition engine and the VoxForge acoustic model are now available as a package on Ubuntu Intrepid.

Many thanks to RainCT for doing this for us... it's greatly appreciated!

Ken

From this post:

gvc [gnome-voice-control] has just got German and Russian support. To test it you need to checkout gvc from svn trunk as well as pocketsphinx and sphinxbase from trunk. Then unpack voxforge acoustic model to ${prefix}/share/pocketsphinx/models/hmm/voxforge-de and start applet in de_DE locale. Everything should work fine, testers are welcome.

MojoMove is a new site that houses Podcasts that sometimes get incorporated into the LibriVox community podcast feed.   They also have a Forum where you can ask technical questions about recording your speech using Audacity for recording audio books for LibriVox (e.g. microphones, Audacity plugins, etc ...).

They are also graciously helping us out with their Shorts Weekly Poetry Reading and their Shorts Weekly Monologue Reading.  Each week they select a new short poem or monologue, and invite users to submit their reading of it.  The resulting audio files are then stored on archive.org, and can then be used by VoxForge for incorporation into our speech corpus, and for the creation of acoustic models.

Many thanks to Robert and Ticktockman for their efforts on this!

Ken