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

[hts-users:01319] Re: Dependencies in HHEd context clustering


Hi,

Sacha Krstulovic wrote (2008/04/10 23:15):

In the way HHEd operates, does the overall result of the clustering
depend on the order of these commands?

More specifically:
does each TB command start from the originally loaded models,
hence all starting from the same MDL criterion value, or do they
start from the clustered models that resulted from the preceding
TB command, i.e., from the MDL criterion value reached after
the preceding TB command?
In the second case, has anyone tried to change the order of
the TB commands, and if yes to which extent did that impact
the synthesis results?

Same question with the dependencies of stream-related clustering:
does it matter to context-cluster first mgc, then lf0, then durations,
or can these clustering operations be safely considered orthogonal
from the point of view of MDL optimization?

Theoretically each of TB command is independent.
However, sometimes the final result is affected by the order of TB commands
because of implementation (numerical errors, etc.).

Regards,

Heiga ZEN (Byung Ha CHUN)

--
------------------------------------------------
Heiga ZEN     (in Japanese pronunciation)
Byung Ha CHUN (in Korean pronunciation)

Department of Computer Science and Engineering
Nagoya Institute of Technology
Gokiso-cho, Showa-ku, Nagoya 466-8555 Japan

http://www.sp.nitech.ac.jp/~zen
------------------------------------------------

References
[hts-users:01317] Dependencies in HHEd context clustering, Sacha Krstulovic