Acoustic Models for HUD

[Ted Gould]

On Mon, 2013-02-25 at 19:13 +-0100, Siegfried-Angel Gevatter Pujals
wrote:
+AD4 The English Voxforge models are currently packaged in julius-voxforge.
+AD4 There I did go with the nightly builds there, since in addition to the
+AD4 time and disk size (which IMHO is already enough of a reason), it
+AD4 needed HTK to build, which is not redistributable. It'd also be
+AD4 interested in more opinions though.

Yes, thanks for doing that+ACE  We found it early on and it created some
very good results.  But yes, Julius does have redistribution problems.
But the library being 4-clause BSD and the tools.

By size, you're talking about the size of the source package, right?  I
wasn't too worried about that, figuring that we could probably find a
server close to the builders to grab the files and upload the package.
Then it would all be on Canonical's network.

For everyone else reading along, the English Voxforge data is roughly
8GB.  It is basically 100 hours of WAV files.

+AD4 Out of curiosity, what's the plan for voice recognition in Ubuntu?
+AD4 Sphinx/Julius/Kaldi?

In the demo images we're using Julius, but we've gotten a lot of help
from the Sphinx list this week to make it much better.  We were
considering keeping Julius as an option, but with that help I'm not sure
that we need to.  I hope that we can get to the point of just dropping
Julius to avoid any issues with redistribution.

Ted

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https:+AC8ALw-lists.ubuntu.com+AC8-archives+AC8-ubuntu-devel+AC8-attachments+AC8-20130225+AC8-2f59adc1+AC8-attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application+AC8-pgp-signature
Size: 836 bytes
Desc: This is a digitally signed message part
URL: <https:+AC8ALw-lists.ubuntu.com+AC8-archives+AC8-ubuntu-devel+AC8-attachments+AC8-20130225+AC8-2f59adc1+AC8-attachment.pgp>