Summary of the paper

Title Resources for Speech Synthesis of Viennese Varieties
Authors Michael Pucher, Friedrich Neubarth, Volker Strom, Sylvia Moosmüller, Gregor Hofer, Christian Kranzler, Gudrun Schuchmann and Dietmar Schabus
Abstract This paper describes our work on developing corpora of three varieties ofViennese for unit selection speech synthesis. The synthetic voices for Viennesevarieties, implemented with the open domain unit selection speech synthesisengine Multisyn of Festival will also be released within Festival. The paperespecially focuses on two questions: how we selected the appropriate speakersand how we obtained the text sources needed for the recording of thesenon-standard varieties. Regarding the first one, it turned out that workingwith a ‘prototypical’ professional speaker was much more preferable thanstriving for authenticity. In addition, we give a brief outline about thedifferences between the Austrian standard and its dialectal varieties and howwe solved certain technical problems that are related to these differences. Inparticular, the specific set of phones applicable to each variety had to bedetermined by applying various constraints. Since such a set does not serve anydescriptive purposes but rather is influencing the quality of speech synthesis,a careful design of such a set was an important task.
Language Corpus (creation, annotation, etc.)
Topics Speech resource/database, Speech Synthesis, Corpus (creation, annotation, etc.)
Full paper Resources for Speech Synthesis of Viennese Varieties
Bibtex @InProceedings{PUCHER10.361,
  author = {Michael Pucher, Friedrich Neubarth, Volker Strom, Sylvia Moosmüller, Gregor Hofer, Christian Kranzler, Gudrun Schuchmann and Dietmar Schabus},
  title = {Resources for Speech Synthesis of Viennese Varieties},
  booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)},
  year = {2010},
  month = {may},
  date = {19-21},
  address = {Valletta, Malta},
  editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias},
  publisher = {European Language Resources Association (ELRA)},
  isbn = {2-9517408-6-7},
  language = {english}
 }
Powered by ELDA © 2010 ELDA/ELRA