On 21.03.2015 12:11, Vincenzo Rubano wrote:
Hi Tobias,
thank you for posting this. Since I would be interested in this kind of things,
I wonder wether we can discuss these aspects of list.
In particular, I’d like to know what tools you used to create this song as well
as getting the English voice when it is released. Together with my friends, I
run a non-profit web radio and we would be interested in using this kind of
tools: we tried using vocaloid, but it is not completely accessible and it
lacks support for Italian (our native language) in addition to being really
expensive for us.
Let me know if you could be interested in discussing this sort of things!
Cheers
Vincenzo.
Il giorno 21/mar/2015, alle ore 11:54, Tobias Platen
<[email protected]> ha scritto:
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]
The speech synthesis library is at
https://notabug.org/isengaara/sekai
--
To UNSUBSCRIBE, email to [email protected]
with a subject of "unsubscribe". Trouble? Contact [email protected]
Archive: https://lists.debian.org/[email protected]
