Festival Speech Synthesis System: - Speech Resource Pages
Festival Speech Synthesis System: - Speech Resource Pages
Festival Speech Synthesis System: - Speech Resource Pages
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
[ < ] [ > ] [ > ] [Top] [Contents] [Index] [ ? ]<br />
5.2 Future<br />
<strong>Festival</strong> is still very much in development. Hopefully this state will continue for a long time. It is never possible to<br />
complete software, there are always new things that can make it better. However as time goes on <strong>Festival</strong>'s core<br />
architecture will stabilise and little or no changes will be made. Other aspects of the system will gain greater attention<br />
such as waveform synthesis modules, intonation techniques, text type dependent analysers etc.<br />
<strong>Festival</strong> will improve, so don't expected it to be the same six months from now.<br />
A number of new modules and enhancements are already under consideration at various stages of implementation.<br />
The following is a non-exhaustive list of what we may (or may not) add to <strong>Festival</strong> over the next six months or so.<br />
● Selection-based synthesis: Moving away from diphone technology to more generalized selection of units for<br />
speech database.<br />
● New structure for linguistic content of utterances: Using techniques for Metrical Phonology we are building<br />
more structure representations of utterances reflecting there linguistic significance better. This will allow<br />
improvements in prosody and unit selection.<br />
● Non-prosodic prosodic control: For language generation systems and custom tasks where the speech to be<br />
synthesized is being generated by some program, more information about text structure will probably exist,<br />
such as phrasing, contrast, key items etc. We are investigating the relationship of high-level tags to prosodic<br />
information through the Sole project http://www.cstr.ed.ac.uk/projects/sole.html<br />
● Dialect independent lexicons: Currently for each new dialect we need a new lexicon, we are currently<br />
investigating a form of lexical specification that is dialect independent that allows the core form to be mapped<br />
to different dialects. This will make the generation of voices in different dialects much easier.<br />
[ < ] [ > ] [ > ] [Top] [Contents] [Index] [ ? ]<br />
6. Installation<br />
This section describes how to install <strong>Festival</strong> from source in a new location and customize that installation.<br />
6.1 Requirements Software/Hardware requirements for <strong>Festival</strong><br />
6.2 Configuration Setting up compilation<br />
6.3 Site initialization Settings for your particular site<br />
6.4 Checking an installation But does it work ...<br />
[ < ] [ > ] [ > ] [Top] [Contents] [Index] [ ? ]<br />
6.1 Requirements<br />
In order to compile <strong>Festival</strong> you first need the following source packages<br />
festival-1.4.3-release.tar.gz<br />
<strong>Festival</strong> <strong>Speech</strong> <strong>Synthesis</strong> <strong>System</strong> source<br />
speech_tools-1.2.3-release.tar.gz<br />
The Edinburgh <strong>Speech</strong> Tools Library<br />
festlex_NAME.tar.gz<br />
The lexicon distribution, where possible, includes the lexicon input file as well as the compiled form, for your<br />
convenience. The lexicons have varying distribution policies, but are all free except OALD, which is only free