IMS Festival Sprachsynthese in Deutsch

Gregor Möhler, Antje Schweitzer, Mark Breitenbücher, Martin Barbisch, und andere

Die Sprachsynthese-Aktivitäten am IMS (Experimentelle Phonetik) konzentrieren sich auf verschiedene linguistische und anwendungsorientierte Aspekte der Sprachsynthese. Unser Ziel ist es, eine natürlich klingende und sprachlich motivierte Sprachsynthese zu erreichen.

Das am IMS entwickelte Sprachsynthesesystem ist das IMSGermanFestival System. Es basiert auf dem ursprünglichen, am CSTR der Universität Edinburgh entwickelten Festival Sprachsyntheserahmen. Die aktuelle Stimme unseres Systems verwendet Diphone, die aus dem MBROLA Projekt stammen.

The German Festival version was developed at the Institute of Natural Language Processing, University of Stuttgart by Gregor Möhler, Antje Schweitzer, Mark Breitenbücher, Martin Barbisch, and others.
IMS German Festival is a German Text-to-Speech system which we provide as an extension to the original Festival distribution by CSTR, University of Edinburgh. Together with two non-IMS resources (the BOMP lexicon developed at the former IKP institute at University of Bonn, which is included in the distribution, and diphones from the  MBROLA project) it enables Festival to speak German.
IMS German Festival contains all modules necessary for text-to-speech conversion. More explicitly this involves linguistic text analysis (modules tokenization, token-pos, token-to-word), grapheme-to-phoneme conversion (lexicon-lookup, letter-to-sound rules), prosody (phrasing, intonation, duration, intonation targets) and waveform synthesis (carried out by the MBROLA engine through an appropriate interface).
For more background information about the IMS German Festival see the README file and the COPYING file of the distribution or consult the manual included in the distribution.
The packages are distributed for research and educational (i.e. non-commercial and non-military) purposes. The license terms can be found in the file COPYING.ims_german_festival for the IMS German Festival package and in file COPYING.bomp for the BOMP lexicon.

NEW!! This is a new version, IMS German Festival 1.4beta-os. It is compatible with Festival_2.5 and should also work with older versions down to Festival_1.95. Older IMS German Festival sources are also provided in a separate directory on the download page, in case you prefer them.

These are the changes compared to version IMS German Festival 1.3:

• compatible with Festival 2.5
• should compile with recent versions of gcc
• can be used with the new MBROLA distribution available from github

These are the changes compared to version IMS German Festival 1.2-os:

• compatible with Festival 2.4 (and 2.1, 1.96, 1.95)
• handles short, tense vowels
• no error when no voiced segment in syllable
• supports MBROLA voice de4, with glottalized and unglottalized vowels
• can deal with British English 9: in BOMP lexicon
• improved duration for nasals
• new text preprocessing, hopefully improved! but still far from perfect (numbers, abbreviations, etc.)
• can theoretically deal with French accents in text (but reasonable pronunciation only if words are added in lexicon!)
• less unknown_diphones warnings
• better durations, and also pause lengths reduced, especially utterance-initial and utt-final
• more reasonable voice resets
• BOMP lexicon improved: distinguish between A~ and o~, some errors corrected
• festival/examples/text2wave should work with German voices now

Requirements

• Festival 2.5 (speech_tools and festival itself)
  from http://www.festvox.org/festival
  compiled on a Linux machine (with GCC)
• MBROLA engine and at least one German MBROLA voice
  from the MBROLA project page

Here are the FAQ.
Here is a link to Carnival, a GUI for Festival, which was developed at the IMS.

Get the distribution

Please send an email to german-festival AT ims.uni-stuttgart.de.

Wir bieten eine Demo an, in der Sie jeden beliebigen Text online synthetisieren können. Die Demo bietet eine Diphonsynthese mit Synthesemodulen, die am IMS entwickelt wurden. Nicht alle diese sind in unserer Open-Source-Version enthalten; einige Module in der Open-Source-Version sind einfacher als diese, so dass die Synthese-Ergebnisse der Open-Source-Version anders klingen können als die der Open-Source-Version.

Ich erhalte folgende Meldung: "SIOD ERROR: unbound variable: mark-string-match". Wie kann ich das beheben?

Fügen Sie die Zeile

ALSO_INCLUDE += ims_german_text

an das Ende von festival/config/config an. Beachten Sie, dass die Ausführung von 'configure' die Datei config/config mit der Datei config/config.in überschreibt. Es wird empfohlen, die Zeile dort zusätzlich einzufügen, aber nur config/config wird zur Übersetzungszeit abgefragt.