Festival is currently actively developed by:
Alan W Black (Carnegie Mellon University)
Rob Clark (Edinburgh University)
Junichi Yamagishi (Edinburgh University)
Keiichiro Oura (Nagoya Institute of Technology)
The following people and organisations have contributed to the
development of Festival in various ways. It is their work that makes
it all possible.
Alan W Black Overall design, most of the front end and software control
Paul Taylor Overall design, most of the back end
Richard Caley for doing lots of difficult and boring bits
Rob Clark Intonation, multisyn voice building, general developement and
Keiichiro Oura Updated HTS engine and API
Korin Richmond Multisyn engine, swig wrappers and general developement.
Heiga Zen HTS engine
Brian Foley Mac OSX support
Kevin Lenzo for speaking a bunch of different nonsense words,
design and improvements to the clunits module,
and co-author of the whole festvox project
Alistair Conkie various low level code points and some design work
Spanish synthesis, recording Roger
Steve Isard design of diphone schema, LPC diphone code, and
EPSRC who funded awb and pault
Carnegie Mellon University
who fund awb
David Huggins Daines (Cepstral, LLC)
configure, and lots of Linux associated bugs
Sun Microsystems Laboratories
For believing in us and their generosity.
AT&T Research Labs
For providing funding and using our work
Paradigm Assoc. and George Carrett
For Scheme In One Defun
CNET, France Telecom
for use of Donovan diphones and some code in
modules/donovan (used with permission)
The beta testers
Thanks for wanting to use the system, you make it
worth doing. (And thanks for helping me debug my code.)
You all responded to my requests fast and accurately
thanks, even when I dumped last minute changes on you
Andy Donovan for speaking a bunch of nonsense words
Roger Burroughes for speaking another bunch of nonsense words
Kurt Dusterhoff for speaking another bunch of nonsense words
Amy Isard for her SSML project and related synthesizer
Mike Macon for signal processing advice
Richard Tobin for answering all those difficult questions,
and the socket code, and rxp the XML parser
Simmule Turner and Rich Salz
command line editor: editline
For Spanish synthesis and answer signal processing
Briony Williams Welsh synthesis
Jacques H. de Villiers
from CSLU at OGI, for the TCL interface.
ATR and Nick Campbell
for first allowing Paul and Alan to work together
Oxford Text Archive
For the computer users version of Oxford Advanced
Learners' Dictionary redistributed with permission
for access to MARSEC from which the phrase break
model was trained.
Mari Ostendorf For giving access to the FM Radio Corpus from which
some models were trained.
LDC & Penn Tree Bank
from which the POS ragger was trained, redistribution
of the models is with permission from the LDC.
Grady Ward for the MOBY pronunciation lexicon
FSF for G++, make, ....
and others too.