Acoustic Models for HUD

Ted Gould ted at
Mon Feb 25 21:51:22 UTC 2013

On Mon, 2013-02-25 at 11:41 -0800, Steve Langasek wrote:

+AD4 On Mon, Feb 25, 2013 at 07:13:43PM +-0100, Siegfried-Angel Gevatter Pujals wrote:
+AD4 +AD4 It's great to hear that voice recognition in Ubuntu is finally getting some
+AD4 +AD4 love :).
+AD4 +AD4 The English Voxforge models are currently packaged in julius-voxforge.
+AD4 +AD4 There I did go with the nightly builds there, since in addition to the time
+AD4 +AD4 and disk size (which IMHO is already enough of a reason), it needed HTK to
+AD4 +AD4 build, which is not redistributable. It'd also be interested in more
+AD4 +AD4 opinions though.
+AD4 In terms of freeness of the OS, depending on non-redistributable tools for
+AD4 building the data files is more of an issue than whether we actually process
+AD4 them at package build time.  Is this a julius-specific requirement, or does
+AD4 it also affect sphinx?

Julius uses the HTK models.  To build the Sphinx ones we need
sphinx-train (which isn't packaged yet, but we've got some test
packages) and some scripts that Pete wrote.

We haven't gone through a license audit on those yet, but I don't expect
any issues.

That is an interesting question though, is there a +ACI-binary blob+ACI
argument if we built the models offline and not in the source packages?
It would seem like as long as it was documented and used free tools
there wouldn't be an issue.


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <>
-------------- 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: <>

More information about the ubuntu-devel mailing list