67 lines
2.9 KiB
Plaintext
67 lines
2.9 KiB
Plaintext
|
|
||
|
|
The initial development of flite was primarily done by awb while
|
||
|
|
travelling, perhaps the name is doubly appropriate as a substantial
|
||
|
|
amount of the coding was done over 30,000ft). During most of that
|
||
|
|
time awb was funded by the Language Technonologies Institute at
|
||
|
|
Carnegie Mellon University.
|
||
|
|
|
||
|
|
Kevin A. Lenzo was involved in the design, conversion techniques and
|
||
|
|
representions for the voice distributed with flite (as well as being
|
||
|
|
the actual voice itself).
|
||
|
|
|
||
|
|
Other contributions are:
|
||
|
|
|
||
|
|
Henry Spencer
|
||
|
|
For the regex code
|
||
|
|
University of Edinburgh
|
||
|
|
for releasing Festival for free, making a companion runtime synthesizer
|
||
|
|
a practical project, much of the design of flite relies on the
|
||
|
|
architecture decisions made in the Festival Speech Synthesis Systems and
|
||
|
|
the Edinburgh Speech Tools.
|
||
|
|
The duration cart tree and intonation (accent and F0) models were
|
||
|
|
derived from the models in the Festival distribution. which in turn
|
||
|
|
were trained from the Boston University FM Radio Data Corpus.
|
||
|
|
Carnegie Mellon University
|
||
|
|
The included lexicon is derived from CMULEX and the letter to sound
|
||
|
|
rules are constructed using the Lenzo and Black techniques for
|
||
|
|
building LTS decision graphs.
|
||
|
|
Nagoya Institute of Technology
|
||
|
|
The mlsa code derives from HTS (following a long chain)
|
||
|
|
Tomoki Toda
|
||
|
|
The mlsa and mlpg support came view Tomoki's support for voice convertion
|
||
|
|
in FestVox which in turn (some of which) comes from NITECH's HTS.
|
||
|
|
Marcela Charfuelan (DFKI)
|
||
|
|
For the mixed-excitation techniques. These origianlly came from NITECH
|
||
|
|
but we understood the technqiues from Marcela's Open Mary Java code and
|
||
|
|
implemented them in our optimized version of MLSA.
|
||
|
|
David Huggins-Daines (dhd@cepstral.com)
|
||
|
|
much of the clunits code, porting to multiple platforms, substantial
|
||
|
|
code tidy up and configure/autoconf guidance.
|
||
|
|
Cepstral, LLC (http://cepstral.com)
|
||
|
|
For supporting DHD to spend time on flite and passing back the important
|
||
|
|
early fixes and enhancements including SAPI support (funded by FCT)
|
||
|
|
Willie Walker <william.walker@sun.com> and the rest of the Sun Speech Group
|
||
|
|
lots of low level bugs (and fixes).
|
||
|
|
Portuguese Foundation for Science and Technology (FCT) Praxis XXI program
|
||
|
|
The SAPI interface provided by Cepstral, LLC was partially funded by
|
||
|
|
the above program.
|
||
|
|
Craig Reese: IDA/Supercomputing Research Center
|
||
|
|
Joe Campbell: Department of Defense
|
||
|
|
who wrote the ulaw conversion routines in src/speech/cst_wave_utils.c
|
||
|
|
Mario Lang:
|
||
|
|
causing the support of shared libraries to happen
|
||
|
|
Eric House (fixin@peak.org)
|
||
|
|
who provided examples of how to do 68K Call Backs for system functions
|
||
|
|
Greg Parker gparker@sealiesoftware.com
|
||
|
|
peal, the binding glue and shared library foo for getting the arm
|
||
|
|
version doing something reasonable under PalmOS
|
||
|
|
Lukas Loehrer <loehrerl@gmx.net> Feb 2006
|
||
|
|
alsa support (default if available)
|
||
|
|
Brian Langner
|
||
|
|
redid the Visual Studio support
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|