[mary-users] Running voice import components

[Ingmar Steiner]

Dear Karthi,

in a nutshell, unit-selection voices can provide higher quality with the 
right data, but suffer from glitches otherwise; HMM-based voices provide 
more consistent quality and greater flexibility, but tend to have a 
somewhat unnatural buzziness to them. Moreover, the memory footprint is 
high for unit selection, and low for HMM-based voices.

Regarding how to run the voice import components, I'm not sure why 
you're asking about voiceimport.jar; I don't see where the tutorial 
refers to it. That file was the equivalent of the marytts-builder 
package in the previous version of MaryTTS (4.3). While the 
voicebuilding process is largely similar in 4.3 and 5.0, there are some 
differences, and this is one of them.

I hope this clears things up.

Best wishes,

-Ingmar

On 7/4/13 12:33 PM, Karthi V wrote:
> Hi,
>
> Am trying to build a voice using this tutorial
>
> https://github.com/marytts/marytts/wiki/VoiceImportToolsTutorial
>
> There is a particular section in this tutorial called "*How to run the
> Voice Import Components" *which says about unit voice or hmm voice, am
> new to voice processing concepts, can you please tell me which kind of
> voice has to be used so that it will be compatible with MARYTTS 5.0 and
> I wasn't able to find voiceimport.jar in mary tts 5.0 links that were
> available in the website, where to download it from? I am currently
> using *marytts-builder-5.0-SNAPSHOT-jar-with-dependencies.jar*to compile
> the voices
>
> Thanks and Regards,
>
> Karthi V
>
>
>
> _______________________________________________
> Mary-users mailing list
> Mary-users at dfki.de
> http://www.dfki.de/mailman/cgi-bin/listinfo/mary-users
>