12.12.2012 Views

Festival Speech Synthesis System: - Speech Resource Pages

Festival Speech Synthesis System: - Speech Resource Pages

Festival Speech Synthesis System: - Speech Resource Pages

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

automatically created (one for each different architecture the system is compiled on). Scripts are added to this<br />

top level directory itself.<br />

`./lib/voices/'<br />

By default this contains the voices used by <strong>Festival</strong> including their basic Scheme set up functions as well as<br />

the diphone databases.<br />

`./lib/dicts/'<br />

This contains various lexicon files distributed as part of the system.<br />

`./config/'<br />

This contains the basic `Makefile' configuration files for compiling the system (run-time configuration is<br />

handled by Scheme in the `lib/' directory). The file `config/config' created as a copy of the<br />

standard `config/config-dist' is the installation specific configuration. In most cases a simpel copy<br />

of the distribution file will be sufficient.<br />

`./src/'<br />

The main C++/C source for the system.<br />

`./src/lib/'<br />

Where the `lib<strong>Festival</strong>.a' is built.<br />

`./src/include/'<br />

Where include files shared between various parts of the system live. The file `festival.h' provides<br />

access to most of the parts of the system.<br />

`./src/main/'<br />

Contains the top level C++ files for the actual executables. This is directory where the executable binary<br />

`festival' is created.<br />

`./src/arch/'<br />

The main core of the <strong>Festival</strong> system. At present everything is held in a single sub-directory<br />

`./src/arc/festival/'. This contains the basic core of the synthesis system itself. This directory<br />

contains lisp front ends to access the core utterance architecture, and phonesets, basic tools like, client/server<br />

support, ngram support, etc, and an audio spooler.<br />

`./src/modules/'<br />

In contrast to the `arch/' directory this contains the non-core parts of the system. A set of basic example<br />

modules are included with the standard distribution. These are the parts that do the synthesis, the other parts<br />

are just there to make module writing easier.<br />

`./src/modules/base/'<br />

This contains some basic simple modules that weren't quite big enough to deserve their own directory. Most<br />

importantly it includes the Initialize module called by many synthesis methods which sets up an<br />

utterance structure and loads in initial values. This directory also contains phrasing, part of speech, and word<br />

(syllable and phone construction from words) modules.<br />

`./src/modules/Lexicon/'<br />

This is not really a module in the true sense (the Word module is the main user of this). This contains<br />

functions to construct, compile, and access lexicons (entries of words, part of speech and pronunciations).<br />

This also contains a letter-to-sound rule system.<br />

`./src/modules/Intonation/'<br />

This contains various intonation systems, from the very simple to quite complex parameter driven intonation<br />

systems.<br />

`./src/modules/Duration/'<br />

This contains various duration prediction systems, from the very simple (fixed duration) to quite complex<br />

parameter driven duration systems.<br />

`./src/modules/UniSyn/'<br />

A basic diphone synthesizer system, supporting a simple database format (which can be grouped into a more<br />

efficient binary representation). It is multi-lingual, and allows multiple databases to be loaded at once. It offers<br />

a choice of concatenation methods for diphones: residual excited LPC or PSOLA (TM) (which is not<br />

distributed)<br />

`./src/modules/Text/'<br />

Various text analysis functions, particularly the tokenizer and utterance segmenter (from arbitrary files). This<br />

directory also contains the support for text modes and SGML.<br />

`./src/modules/donovan/'<br />

An LPC based diphone synthesizer. Very small and neat.<br />

`./src/modules/rxp/'<br />

The <strong>Festival</strong>/Scheme front end to An XML parser written by Richard Tobin from University of Edinburgh's<br />

Language Technology Group.. rxp is now part of the speech tools rather than just <strong>Festival</strong>.<br />

`./src/modules/parser'<br />

A simple interface the the Stochastic Context Free Grammar parser in the speech tools library.

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!