3 Acknowledgements

The code in this system was primarily written by Alan W Black, Paul Taylor and Richard Caley. Festival sits on top of the Edinburgh Speech Tools Library, and uses much of its functionality.

Amy Isard wrote a synthesizer for her MSc project in 1995, which first used the Edinburgh Speech Tools Library. Although Festival doesn't contain any code from that system, her system was used as a basic model.

Much of the design and philosophy of Festival has been built on the experience both Paul and Alan gained from the development of various previous synthesizers and software systems, especially CSTR's Osprey and Polyglot systems taylor91 and ATR's CHATR system black94.

However, it should be stated that Festival is fully developed at CSTR and contains neither proprietary code or ideas.

Festival contains a number of subsystems integrated from other sources and we acknowledge those systems here.

3.1 SIOD

The Scheme interpreter (SIOD -- Scheme In One Defun 3.0) was written by George Carrett (gjc@mitech.com, gjc@paradigm.com) and offers a basic small Scheme (Lisp) interpreter suitable for embedding in applications such as Festival as a scripting language. A number of changes and improvements have been added in our development but it still remains that basic system. We are grateful to George and Paradigm Associates Incorporated for providing such a useful and well-written sub-system.

                       Scheme In One Defun (SIOD)
                       COPYRIGHT (c) 1988-1994 BY 
        PARADIGM ASSOCIATES INCORPORATED, CAMBRIDGE, MASSACHUSETTS.
                           ALL RIGHTS RESERVED

Permission to use, copy, modify, distribute and sell this software
and its documentation for any purpose and without fee is hereby
granted, provided that the above copyright notice appear in all copies
and that both that copyright notice and this permission notice appear
in supporting documentation, and that the name of Paradigm Associates
Inc not be used in advertising or publicity pertaining to distribution
of the software without specific, written prior permission.

PARADIGM DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING
ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL
PARADIGM BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR
ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS,
WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION,
ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
SOFTWARE.

3.2 editline

Because of conflicts between the copyright for GNU readline, for which an optional interface was included in earlier versions, we have replace the interface with a complete command line editing system based on `editline'. `Editline' was posted to the USENET newsgroup `comp.sources.misc' in 1992. A number of modifications have been made to make it more useful to us but the original code (contained within the standard speech tools distribution) and our modifications fall under the following licence.

Copyright 1992 Simmule Turner and Rich Salz.  All rights reserved.       
                                                                         
This software is not subject to any license of the American Telephone    
and Telegraph Company or of the Regents of the University of California. 
                                                                         
Permission is granted to anyone to use this software for any purpose on  
any computer system, and to alter it and redistribute it freely, subject 
to the following restrictions:                                           
1. The authors are not responsible for the consequences of use of this   
   software, no matter how awful, even if they arise from flaws in it.   
2. The origin of this software must not be misrepresented, either by     
   explicit claim or by omission.  Since few users ever read sources,    
   credits must appear in the documentation.                             
3. Altered versions must be plainly marked as such, and must not be      
   misrepresented as being the original software.  Since few users       
   ever read sources, credits must appear in the documentation.          
4. This notice may not be removed or altered.                            

3.3 Edinburgh Speech Tools Library

The Edinburgh Speech Tools lies at the core of Festival. Although developed separately, much of the development of certain parts of the Edinburgh Speech Tools has been directed by Festival's needs. In turn those who have contributed to the Speech Tools make Festival a more usable system.

See section `Acknowledgements' in Edinburgh Speech Tools Library Manual.

Online information about the Edinburgh Speech Tools library is available through

http://www.cstr.ed.ac.uk/projects/speech_tools.html

3.4 Others

Many others have provided actual code and support for Festival, for which we are grateful. Specifically,

• Alistair Conkie: various low level code points and some design work, Spanish synthesis, the old diphone synthesis code.
• Steve Isard: directorship and LPC diphone code, design of diphone schema.
• EPSRC: who fund Alan Black and Paul Taylor.
• Sun Microsystems Laboratories: for supporting the project and funding Richard.
• AT&T Labs - Research: for supporting the project.
• Paradigm Associates and George Carrett: for Scheme in one defun.
• Mike Macon: Improving the quality of the diphone synthesizer and LPC analysis.
• Kurt Dusterhoff: Tilt intonation training and modelling.
• Amy Isard: for her SSML project and related synthesizer.
• Richard Tobin: for answering all those difficult questions, the socket code, and the XML parser.
• Simmule Turner and Rich Salz: command line editor (editline)
• Borja Etxebarria: Help with the Spanish synsthesis
• Briony Williams: Welsh synthesis
• Jacques H. de Villiers: `jacques@cse.ogi.edu' from CSLU at OGI, for the TCL interface, and other usability issues
• Kevin Lenzo: `lenzo@cs.cmu.edu' from CMU for the PERL interface.
• Rob Clarke: for support under Linux.
• Samuel Audet `guardia@cam.org': OS/2 support
• Mari Ostendorf: For providing access to the BU FM Radio corpus from which some modules were trained.
• Melvin Hunt: from whose work we based our residual LPC synthesis model on
• Oxford Text Archive: For the computer users version of Oxford Advanced Learners' Dictionary (redistributed with permission).
• Reading University: for access to MARSEC from which the phrase break model was trained.
• LDC & Penn Tree Bank: from which the POS tagger was trained, redistribution of the models is with permission from the LDC.
• Roger Burroughes and Kurt Dusterhoff: For letting us capture their voices.
• ATR and Nick Campbell: for first getting Paul and Alan to work together and for the experience we gained.
• FSF: for G++, make, ....
• Center for Spoken Language Understanding: CSLU at OGI, particularly Ron Cole and Mike Macon, have acted as significant users for the system giving significant feedback and allowing us to teach courses on Festival offering valuable real-use feedback.
• Our beta testers: Thanks to all the people who put up with previous versions of the system and reported bugs, both big and small. These comments are very important to the constant improvements in the system. And thanks for your quick responses when I had specific requests.
• And our users ... Many people have downloaded earlier versions of the system. Many have found problems with installation and use and have reported it to us. Many of you have put up with multiple compilations trying to fix bugs remotely. We thank you for putting up with us and are pleased you've taken the time to help us improve our system. Many of you have come up with uses we hadn't thought of, which is always rewarding. Even if you haven't actively responded, the fact that you use the system at all makes it worthwhile.

Go to the first, previous, next, last section, table of contents.