[mary-users] Question on using Mary on a mobile device

[Foust, William [IT]]

I've been searching for some comments or messages about putting Mary TTS on a mobile platform. Even though the platform is a server based approach, I'm really looking at something that can be accomplished locally in a stand-alone implementation. Do you see this as a viable solution to get a TTS implementation on a mobile device in a stand-alone configuration?   Are there any packages that you suspect wouldn't work or be available in a Java Mobile type of platform?

The architecture has many layers where the server functionality could be split. Assuming the text changes infrequently, does it make sense to try to separate the synthesizer layer out? The thought process is that the text could be pre-processed and stored as TARGETFEATURES, or some other format, which is the lowest level text format of the audio conversion.Then, all that would be needed is to synthesis the text from the file. I assume the synthesis is the most demanding step in the process, so it might not be worth it, but I'm asking.

Thanks!
Bill


________________________________

This e-mail may contain Sprint proprietary information intended for the sole use of the recipient(s). Any use by others is prohibited. If you are not the intended recipient, please contact the sender and delete all copies of the message.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.dfki.de/pipermail/mary-users/attachments/20140327/a47abf1c/attachment.htm