[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Re: Bug#596511: ITP: simon -- Open source speech recognition


Please cc me in further requests because I am not subscribed to
debian-devel@lists.debian.org (I found this by accident).

Samuel Thibault<sthibault@debian.org>  writes:
>  « The HTK is, strictly speaking, no dependency of simon. It extends
>  simon functionality: Without it is not possible to create speech mdoels
>  but you can still use existing ones. »
>  And can you modify one?  I guess you can't.  That's an issue.
Of course you can. The HTK format is a well documented ASCII format.
However, I doubt that this is what you want.
Speech models are not really modified - they are re-created (like
compiled source code). You could possibly convert them to the SPHINX
format with the GPL converter on sourceforge tough and do the adaption
there. You could then convert it back for use with simon. With the same
procedure you could also create entirely new models for use with simon with
completely free software.

I have to note that I haven't tried this yet, tough.

Please also keep in mind that for example GNOME voice control doesn't
provide any training at all - open source or otherwise. Its not like simon
doesn't provide any functionality on an completely free software stack.

Peter, have you prepared a source *.deb yet?  It would be interesting to
look at the code to understand how critical the non-free component is.
Sure. There are complete packages in the Ubuntu ppa:

The package files are in the debian git repository on git.debian.org.

Best regards,

Reply to: