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

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

The UniSyn_module_hooks are run before synthesis, see the next selection about diphone name selection. At<br />

present only lpc is supported by the UniSyn module, though potentially there may be others.<br />

An optional implementation of TD-PSOLA moulines90 has been written but fear of legal problems unfortunately<br />

prevents it being in the public distribution, but this policy should not be taken as acknowledging or not<br />

acknowledging any alleged patent violation.<br />

[ < ] [ > ] [ > ] [Top] [Contents] [Index] [ ? ]<br />

20.6 Diphone selection<br />

Diphone names are constructed for each phone-phone pair in the Segment relation in an utterance. If a segment has<br />

the feature in forming a diphone name UniSyn first checks for the feature us_diphone_left (or<br />

us_diphone_right for the right hand part of the diphone) then if that doesn't exist the feature us_diphone<br />

then if that doesn't exist the feature name. Thus is is possible to specify diphone names which are not simply the<br />

concatenation of two segment names.<br />

This feature is used to specify consonant cluster diphone names for our English voices. The hook<br />

UniSyn_module_hooks is run before selection and we specify a function to add us_diphone_* features as<br />

appropriate. See the function rab_diphone_fix_phone_name in<br />

`lib/voices/english/rab_diphone/festvox/rab_diphone.scm' for an example.<br />

Once the diphone name is created it is used to select the diphone from the database. If it is not found the name is<br />

converted using the list of alternates_left and alternates_right as specified in the database<br />

declaration. If that doesn't specify a diphone in the database. The default_diphone is selected, and a warning is<br />

printed. If no default diphone is specified or the default diphone doesn't exist in the database an error is thrown.<br />

[ < ] [ > ] [ > ] [Top] [Contents] [Index] [ ? ]<br />

21. Diphone synthesizer<br />

NOTE: use of this diphone synthesis is depricated and it will probably be removed from future versions, all of its<br />

functionality has been replaced by the UniSyn synthesizer. It is not compiled by default, if required add<br />

ALSO_INCLUDE += diphone to your `festival/config/config' file.<br />

A basic diphone synthesizer offers a method for making speech from segments, durations and intonation targets. This<br />

module was mostly written by Alistair Conkie but the base diphone format is compatible with previous CSTR<br />

diphone synthesizers.<br />

The synthesizer offers residual excited LPC based synthesis (hunt89) and PSOLA (TM) (moulines90) (PSOLA is not<br />

available for distribution).<br />

21.1 Diphone database format Format of basic dbs<br />

21.2 LPC databases Building and using LPC files.<br />

21.3 Group files Efficient binary formats<br />

21.4 Diphone_Init Loading diphone databases<br />

21.5 Access strategies Various access methods<br />

21.6 Diphone selection Mapping phones to special diphone names<br />

[ < ] [ > ] [ > ] [Top] [Contents] [Index] [ ? ]

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

Saved successfully!

Ooh no, something went wrong!