ANNOUNCING FESTIVAL 1.3.0 RELEASE (fwd).

[Hans Zoebelein <zocki@goldfish.cube.net>]

Hi Blinuxers,

Festival 1.3.0 is available at
/blinux/festival/cstr.mirror/1.3.0/ 

Here comes the Festival announcement.

Enjoy!
hans

---------- Forwarded message ----------
Date: Mon, 24 Aug 1998 16:41:18 +0100
From: Alan W Black <awb@cstr.ed.ac.uk>
To: festival-beta@cstr.ed.ac.uk
Subject: ANNOUNCING FESTIVAL 1.3.0 RELEASE


Beta-testers

I have released 1.3.0 with most of the updates you suggested, thanks
for the all the feedback.  Given that all the other public releases
we've made have required minor fixes I suspect there will be a 1.3.1
in about a month's time.

Specific things that aren't confirmed/fixed:
   SGI/IRIX port still needs a little work, I suspect,
   -  I didn't have time to fold in the SGI CC changes but will
      make them available to people who want them
   -  bug in longjmp/setjmp for gcc-2.8.1 (?)
   -  built-in IRIX audio seems to be dropping packets
   -  but gcc-2.7.2 port probably works
   Windows/NT 
   -  Visual C++ port is more stable than the Cygwin one (this might
      be true only for 95 though, NT maybe OK).
   -  Still need a proper audio spooler for windows.

I'll do an annoucement in comp.speech and comp.os.linux.announce once we
have the linux binaries ready.

Thanks again for giving quick feedback

Alan

PS you're still allowed to send more bug reports though :-)

-------

        The Festival Speech Synthesis System version 1.3.0 
         and Edinburgh Speech Tools Library version 1.3.0
                          24th August 1998

Festival offers a general framework for building speech synthesis
systems as well as including examples of various modules.  As a whole
it offers full text to speech through a number APIs: from shell level,
though a Scheme command interpreter, as a C++ library, and an Emacs
interface.  Festival is multi-lingual (currently English (British and
American), Spanish and Welsh) though English is the most advanced.

The system is written in C++ and uses the Edinburgh Speech Tools
Library for low level architecture and has a Scheme (SIOD) based
command interpreter for control.  Documentation is given in the FSF
texinfo format which can generate, a printed manual, info files and
HTML.

This distribution includes:
   * Full English (British and American English) text to speech
   * Full C++ source for modules, SIOD interpreter, and Scheme library
   * Lexicon based on OALD and CMULEX (distributed with permission)
   * Edinburgh Speech Tools, low level C++ library
   * British English Male (for residual LPC resynthesis 8k and 16k versions)
   * American English Male (for residual LPC resynthesis 8k and 16k versions)
   * Castilian Spanish Male (for residual LPC resynthesis 11k version)
   * British English Male (for spike excited LPC resynthesis 10k version)
   * Full documentation (html, postscript and GNU info format)

Festival version 1.3.0 is available from
    ftp://ftp.cstr.ed.ac.uk/pub/festival/1.3.0/

The Festival home page, offering descriptions of the system, examples
and online demos, can be found at
    http://www.cstr.ed.ac.uk/projects/festival.html

Requirements

To run Festival you need:
   * A Unix machine, Festival has compiled and run on Suns (SunOS and 
     Solaris), FreeBSD, Linux, SGIs and DEC Alphas but should be portable
     to any standard Unix machine.
   * A C++ compiler: we have used GCC  version 2.7.2, 2.6.3, or 2.8.1 and
     Sun CC 3.01, 4.1 and 4.2, and egcs.  Other C++ compilers are
     probably possible with perhaps some minor chanages
   * GNU Make any recent version
   * Audio hardware, /dev/audio (8 bit and 16 bit on Suns, Linux 
     and FreeBSD) and NCD's NAS network transparent audio system 
     are supported directly but Festival supports the execution of 
     any Unix command that can play audio files.
   * GNU readline library is recommended though not necessary

There is basic support for building the system under Windows NT and
95.  We have successfully ran the system complied with Cygnus' GNU
win32 package and Microsoft's Visual C++.  However such support is
still young so its not worth attempting to use this unless you are
confident about compiling C++ programs under Windows.

We intend to distribute binariary distributions for major
architectures particularly Linux and Solaris.  We will *not*
distribute binary versions for Windows NT/95 as we do not have enough
expertise to support them.

Restrictions

The system may be used, copied, modified and distributed for free for
research, educational and individual use.  Commercial use requires
prior written permission from the authors.  Research distributions,
bundled with other systems are allowed.  Commercial re-distributions
(e.g. on CDROM with collections of other software) are not implicitly
permitted but will usually be permitted for free if you ask.  We do
intend that later versions may be distributed of such CDROMs without
requiring permission but until we have a more stable system we'd like
to control that.

New in 1.3.0 
   * New (improved) diphone synthesizer
   * Better letter to sound rules (trained) for lexicons
   * New utterance architecture
   * Probabilistic parser
   * Improvements in training tools
   * Improvements in signal processing routines 
       (can now build diphone databases from our tools alone)
   * Tilt intonation model support
   * Time and space efficiency
   * Sable/XML markup language support (optionally built in)
   * Basic Java bindings (loading Speech Tools into Java and
       java client access to festival server)
   * Many other fixes

Alan, Paul and Richard
24th August 1998

---
Alan W Black                            email: awb@cstr.ed.ac.uk
Centre for Speech Technology Research   http://www.cstr.ed.ac.uk/~awb
University of Edinburgh                 tel:   (44) 131 650 2787
80 South Bridge, Edinburgh, UK          fax:   (44) 131 650 6351








-- 
         To unsubscribe: mail blinux-announce-request@redhat.com with 
                       "unsubscribe" as the Subject.