Hello,
In my master thesis[1] I wrote about about speech synthesis using modern
algorithms. I evaluated several algorithms and wrote an implementation
of an MBROLA clone that I released under GPL v3. It is based on WORLD[2]
by Masanori Morise, which has been used in VOCALOID clones such as
v.Connect-STAND[3]. Next step will be the creation of a multilingual
voice database that supports German, English and Japanese. I also
prepared a Debian source package which will import in a git repository
soon. I use "gbp create-remote-repo" to upload the package to alioth.
[1] (German)
http://digdok.bib.thm.de/volltexte/2014/5014/pdf/Sprachausgabe_Final_Screen.pdf
[2] http://ml.cs.yamanashi.ac.jp/world/english/index.html
[3] https://www.youtube.com/watch?v=9EMjbm39x40
--
To UNSUBSCRIBE, email to [email protected]
with a subject of "unsubscribe". Trouble? Contact [email protected]
Archive: https://lists.debian.org/[email protected]
