Resources for Speech Synthesis of Viennese Varieties

by 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 of Viennese for unit selection speech synthesis. The synthetic voices for Viennese varieties, implemented with the open domain unit selection speech synthesis engine Multisyn of Festival will also be released within Festival. The paper especially focuses on two questions: how we selected the appropriate speakers and how we obtained the text sources needed for the recording of these non-standard varieties. Regarding the first one, it turned out that working with a ‘prototypical’ professional speaker was much more preferable than striving for authenticity. In addition, we give a brief outline about the differences between the Austrian standard and its dialectal varieties and how we solved certain technical problems that are related to these differences. In particular, the specific set of phones applicable to each variety had to be determined by applying various constraints. Since such a set does not serve any descriptive purposes but rather is influencing the quality of speech synthesis, a careful design of such a set was an important task.
Reference:
Resources for Speech Synthesis of Viennese Varieties (Michael Pucher, Friedrich Neubarth, Volker Strom, Sylvia Moosmüller, Gregor Hofer, Christian Kranzler, Gudrun Schuchmann and Dietmar Schabus), In Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC), 2010.
Bibtex Entry:
@InProceedings{Pucher2010d,
  Title                    = {Resources for Speech Synthesis of Viennese Varieties},
  Author                   = {Michael Pucher and Friedrich Neubarth and Volker Strom and Sylvia Moosmüller and Gregor Hofer and Christian Kranzler and Gudrun Schuchmann and Dietmar Schabus},
  Booktitle                = {Proceedings of the 7th International Conference on Language Resources and Evaluation (LREC)},
  Year                     = {2010},

  Address                  = {Valletta, Malta},
  Month                    = may,
  Pages                    = {105-108},

  Abstract                 = {This paper describes our work on developing corpora of three varieties of Viennese for unit selection speech synthesis. The synthetic voices for Viennese varieties, implemented with the open domain unit selection speech synthesis engine Multisyn of Festival will also be released within Festival. The paper especially focuses on two questions: how we selected the appropriate speakers and how we obtained the text sources needed for the recording of these non-standard varieties. Regarding the first one, it turned out that working with a ‘prototypical’ professional speaker was much more preferable than striving for authenticity. In addition, we give a brief outline about the differences between the Austrian standard and its dialectal varieties and how we solved certain technical problems that are related to these differences. In particular, the specific set of phones applicable to each variety had to be determined by applying various constraints. Since such a set does not serve any descriptive purposes but rather is influencing the quality of speech synthesis, a careful design of such a set was an important task.},
  File                     = {/download/pucher_LREC_2010},
  Owner                    = {schabus},
  Timestamp                = {2014.09.16},
  Url                      = {http://www.lrec-conf.org/proceedings/lrec2010/summaries/361.html}
}