package high quality voices for festival

[Pavel Rojtberg]

Binary package hint: festival

the voice packages currently available in the repository are all diphone based, which results in sub standard synthesis quality.
Instead Hidden Markov Based (HTS) voices should be packaged and used which are more like state of the art and thus give better sound quality.
I the following free voices work fine with the current version of festival in jaunty:
http://hts.sp.nitech.ac.jp/?Download#z142d16f

[Charlie Kravetz (cjkgeek)]

Thanks for reporting this bug and any supporting documentation. Since this bug has enough information provided for a developer to begin work, I'm going to mark it as confirmed and let them handle it from here. Thanks for taking the time to make Ubuntu better!

[Jarno Suni (jarnos)]

Do you have to remove diphone based voices to add HTS voices? There used to be even more languages packed for festival than its man page shows. E.g. "finnish" voice was pretty good. After ubuntu 9.10 no other than the default English voice works. Can you confirm Bug #688940?

[Charlie Kravetz (cjkgeek)]

I am sorry. I don't see the relationship between this bug and bug 688940. However, I am unable to confirm that bug in Natty Narwhal.

[Paul Gevers (paul-climbing)]

See https://lists.alioth.debian.org/pipermail/tts-project/Week-of-Mon-20151102/000369.html