Nico Kadel-Garcia wrote:
> See above. "voice recognition" and accent immunity is not a "python"
> sort of problem, it's a massive ongoing computer and speech research
> issue. Pick something *smaller*.
I would also add to that that Fedora would probably be the wrong mentoring
organization for such a project to begin with, even if it were doable. These
things need to be worked on with upstream projects. But they are very likely
to reject this proposal for the same reasons. Improving the quality of the
speech recognition, if it's possible at all, has to be done inside the C
(Pocketsphinx) or Java (Sphinx4) code of CMU Sphinx. Trying to do it in a
higher layer in Python doesn't make any sense whatsoever.
Kevin Kofler
--
devel mailing list
devel@xxxxxxxxxxxxxxxxxxxxxxx
https://admin.fedoraproject.org/mailman/listinfo/devel
Fedora Code of Conduct: http://fedoraproject.org/code-of-conduct
