Research Scientist
Acoustic Phonetics
Machine Learning

Tel. +43 1 51581-2508
Email: michael.pucher [at] oeaw.ac.at

Scientific IDs:
ORCID: 0000-0002-5374-1342
Google Scholar

Academic background


Michael Pucher obtained his doctoral degree (Dr.techn.) in Electrical and Information Engineering from Graz University of Technology in 2007. In 2017 he received the venia docendi in Speech Communication at Graz University of Technology with a habilitation thesis on Speech Processing for Multimodal and Adaptive Systems. He holds a master degree (Dipl.-Ing.) in Computer Science from Vienna University of Technology (TUW) and a diploma degree (Mag.phil.) in philosophy from University of Vienna. From 2007 to 2015 he was Senior Researcher at the Telecommunications Research Center Vienna (FTW). Since 2016 he is Senior Research Scientist at the Acoustics Research Institute (ARI) of the Austrian Academy of Sciences (ÖAW).

Current research


During the last years his work was focused on the improvement of state-of-the-art speech synthesis technologies for the synthesis of language varieties and audio-visual speech. He has also made significant contributions in the area of speaker verification spoofing, where he showed how adaptive synthesizers can spoof a speaker verification system. Currently he is working on sociophonetics, articulatory modeling, synthesis of animal vocalizations, and synthesis of singing speech. More information and all publications can be found on http://sociolectix.org.

Publications

Publications

  • Pucher M.; Klingler N.; Luttenberger J.; Spreafico L. (2020) Accuracy, recording interference, and articulatory quality of headsets for ultrasound recordings. Speech Communication, Bd. 123, S. 83-97.
  • Lozo C. (2020) Revisiting nonstandard variety TTS and its evaluation in Austria. Phonetik und Sprachtechnologie in Österreich anlässlich der ÖLT 2018 (N. Klingler and Pucher, M., eds.). Bd. 117 S. 34-44.
  • Klinger N.; Pucher M. (Eds.) (2020) The Phonetician Special Issue 117 [Proceedings of the Phonetics and Speech Technology" Workshop 2018]. The Phonetician, special issue. Bd. 117.
  • Noll A.; Pucher M.; Lozo C. (2020) Formant tracking in Sound Tools eXtended (STx) 5.0. Fortschritte in der Akustik (DAGA 2020). Hannover S. 956-958.
  • Pucher M.; Moosmüller S.; Rausch-Supola M. (2019) Aufnahme von authentischen Dialektdaten für die Verwendung in der Sprachsynthese. In: Methodik moderner Dialektforschung. Erhebung, Aufbereitung und Auswertung von Daten am Beispiel des Oberdeutschen.. Olms, Hildesheim Bd. 241-243 S. 105-123.
  • Pucher M.; Trouvain J.; Lozo C. (Eds.) (2019) HSCR 2019 - Proceedings of the Third International Workshop on the History of Speech Communication Research. Studientexte zur Sprachkommunikation. Bd. Band 94.
  • Klingler N.; Kleber F.; Jochim M.; Pucher M.; Schmid S.; Zihlmann U. (2019) Temporal organization of vowel plus stop sequences in production and perception: Evidence from the three major varieties of German. Proceedings of the 19th International Congress of Phonetic Sciences, Melbourne, Australia 2019 (ICPhS 2019). Melbourne S. 825-829.
  • Lozo C.; Pucher M. (2019) The thought collective behind thirty years of progress in speech synthesis. 3rd Workshop of History of Speech Communication Research.
  • Noll A.; Stuefer J.; Klingler N.; Leykum H.; Lozo C.; Luttenberger J.; et al. (2019) Sound Tools eXtended (STx) 5.0 – a powerful sound analysis tool optimized for speech. Proceedings Interspeech 2019. Graz S. 2370-2371.
  • Gutscher L.; Pucher M.; Lozo C.; Hoeschele M.; Mann D. (2019) Statistical parametric synthesis of budgerigar songs. SSW10 - The 10th ISCA Speech Synthesis Workshop. Vienna S. 127-131.
  • Pucher M.; Lozo C.; Vergeiner P.; Wallner D. (2019) Diphthong interpolation, phone mapping, and prosody transfer for speech synthesis of similar dialect pairs. SSW10 - The 10th ISCA Speech Synthesis Workshop. Vienna S. 200-204.
  • Pucher M. (2019) Synthetic voices in Austrian German and Viennese sociolects/dialects. . ARI, .
  • Pucher M.; Lozo C.; Moosmüller S. (2018) Evaluation methods for dialect speech synthesis of similar dialect pairs. Fortschritte in der Akustik (DAGA 2018). München S. 515-517.
  • Spreafico L.; Pucher M.; Matosova A. (2018) UltraFit: A speaker-friendly headset for ultrasound recordings in speech science. Proceedings of the 19th Annual Conference of the International Speech Communication Association (INTERSPEECH 2018). Hyderabad S. 1517-1520.
  • Pucher M.; Lozo C.; Moosmüller S. (2017) Phone Mapping and Prosodic Transfer in Speech Synthesis of similar Dialect Pairs. 28. Konferenz Elektronische Sprachsignalverarbeitung 2017. Saarbrücken S. 180 -185.
  • Pucher M.; Zillinger B.; Toman M.; Schabus D.; Valentinni-Botinhao C.; Yamagishi J.; et al. (2017) Influence of speaker familiarity on blind and visually impaired children"s and young adults" perception of synthetic voices. Computer, Speech & Language, Bd. 46, S. 179-195.
  • Pucher M. (2017) Speech processing for multimodal and adaptive systems. . Technische Universität Graz, .
  • Schmid C.; Moosmüller S. (2017) L2 acquisition and L1 atrritioin in Bosnian-German late bilinguals - Phonetic observations at the segmental level. . S. 251.
  • Pucher M.; Rausch-Supola M.; Moosmüller S.; Toman M.; Schabus D.; Neubarth F. (2016) Open data for speech synthesis of Austrian German language varieties. 12. Tagung Phonetik und Phonologie im deutschsprachigen Raum (C. and K. Draxler F. (Eds.), ed.). München S. 147-150.
  • Pucher M.; Villavicencio F.; Yamagishi J. (2016) Development and evaluation of a statistical parametric synthesis system for operatic singing in German. Speech Synthesis Workshop (SSW9). Sunnyvale, California S. 64-69.
  • 1

Additional Information

Teaching


  • SS 2013 to WS 2019 Lecture on Cognitive User Interfaces at Institute of Computer Languages at Vienna University of Technology.
  • WS 2011 to 2016 Lecture on Computational Semantics at Institute of Computer Languages at Vienna University of Technology.

Organizing