|
From: | David Hill |
Subject: | Re: [gnuspeech-contact] Status of gnuspeech port? |
Date: | Sun, 5 Mar 2006 12:59:08 -0800 |
Hi Ken,Monet has been ported to Mac OS/X and can be used to play with speech postures, convolution rules, and explicit adjustment of intonation patterns. The GNUStep port is under way, and held up because the Mac port uses Core Audio which is not (yet) part of GNUStep.
You could do some experimentation to explore possibilities and learn the core of the system by running Monet on Mac OS/X.
The "Synthesizer" port to Mac OS/X is well under way and will be available "real soon now". Best guess is of the order of 6 weeks. The GNUStep port of "Synthesizer" will have the same problem as Monet -- namely dealing with the sound output properly within the GNUStep framework.
Greg Casamento (GNUStep guru) is looking at porting the needed parts of Core Audio to GNUStep, which would solve the above problems.
"Real-time Monet" -- an engine that will run **without interaction** using the rules, postures, dictionaries and so on established by use of Monet, Synthesizer, and associated databases to provide a speech service for whatever language was embodied in the databases, in whatever application or operating system facility wished to use speech based on a standard API, will be ported to Mac OS/X as soon as there is a stable version of Synthesizer. No sure guesses yet as to how long that would take but, with luck and hard work probably before the end of the year.
If you want immediate access to the whole set or tools, applications dictionaries etc you can obtain black NeXT hardware from http:// www.blackholeinc.com and load up the software available from the savannah gnuspeech site. I can give some information about configuration, tools needed, where the passwords are for access to the kits, tools that are not on the site that I could provide (very few, mainly to do with NeXT dictionary creation). I should probably put a page up about this, but not many people are wanting that info and I really want to focus on Mac OS/X, GNU/Linux and GNUStep. Going back to the NeXT implementation is deprecated, but is a possibility for those in urgent need.
Hope that helps. david ---- On Mar 5, 2006, at 10:20 AM, Ken Beesley wrote:
I haven't looked into gnuspeech for quite a while. Could some kind soul post a brief update on the status of the port? Has the "Synthesizer" (the GUI front-end to tube) been ported? My need is to produce a preliminary TTS system for an American Indian language, without using any recordings. The orthography is a reliable representation of the phonology, so there is no need (at least initially) for any kind of pronunciation dictionary, and I have already done grapheme-to-phoneme conversion (IPA output). My preferred platform is Apple OS X. Thanks, Ken _______________________________________________ gnuspeech-contact mailing list address@hidden http://lists.gnu.org/mailman/listinfo/gnuspeech-contact
[Prev in Thread] | Current Thread | [Next in Thread] |