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

[hts-users:02630] Announcing Festival 2.1 release


       The Festival Speech Synthesis System version 2.1
        and Edinburgh Speech Tools Library version 2.1
                       November 2010

Surprisingly we have a new release.  Please give feedback for
installation issues so they can be fixed in a 2.1 release.

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, from Java, and
an Emacs interface.  Festival is multi-lingual (currently English
(British and American), and Spanish) though English is the most
advanced.  Other groups release new languages for the system.  And
full tools and documentation for build new voices are available
through Carnegie Mellon's FestVox project (http://festvox.org).  This
version also supports voices built with the latest version of Nagoya
Institute of Technologies' HTS system (http://hts.sp.nitech.ac.jp)

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.

Festival is free software.  Festival and the speech tools are
distributed under an X11-type licence allowing unrestricted commercial
and non-commercial use alike.

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 CMULEX and OALD (OALD is restricted to non-commercial
    use only)
  * Edinburgh Speech Tools, low level C++ library
  * rab_diphone: British English Male residual LPC, diphone
  * kal_diphone: American English Male residual LPC diphone
  * cmu_us_slt_arctic_hts: American Female, HTS
  * cmu_us_rms_cg: American Male using  clustergen
  * cmu_us_awb_cg: Scottish English Male (with US frontend) clustergen
  * Full documentation (html, postscript and GNU info format)

Note there are some licence restrictions on the voices themselves.
The US English voices have the same restrictions as Festival.

The UK lexicon (OALD) is restricted to non-commercial use.

Addition voices are also available.

Festival version 2.1 sources, voices

In Europe:
   http://www.cstr.ed.ac.uk/downloads/festival/
In North America:
   http://festvox.org/festival

Requirements

To run Festival you need:
  * A Unix-like environment, e.g Linux, FreeBSD, OSX, cygwin under Windows.
  * A C++ compiler: we have used GCC  versions. 2.x upto 4.5
  * GNU Make any recent version

New in 2.1
  * Support for the new versions of C++ that have been released
  * Integrated and updated support for HTS, Clustergen, Multisyn and Clunits
    voices
  * "Building Voices in Festival" document describing process of building
    new voices in the system
      http://festvox.org/

Alan W Black (CMU)
Rob Clark (Edinburgh)
Junichi Yamagishi (Edinburgh)
Keiichiro Oura (Nagoya)