In my PhD project, I developed the incremental processing toolkit and its modules for incremental speech recognition (built on by Google to implement online speech-to-text) and incremental speech synthesis (still awaiting commercialization...).

Since its inception more than a decade ago, new toolkits have sprung to life which is why I do not recommend using InproTK anymore. Nevertheless, the original (still mostly useable) code base is available at A partial, more modular version (on the way towards inprotk2) is at

Collaborators on this project.

  • David Schlangen, thesis advisor
  • Okko Buss
  • Casey Kennington
  • Michaela Atterer
  • many more research students and other collaborators

Related Publications:

  • Timo Baumann (2013).
    "Incremental Spoken Dialogue Processing: Architecture and Lower-level Components".
    PhD thesis, Universität Bielefeld, Germany.
    URN, pdf, Deutsche Kurzfassung, position paper in defense of the thesis, disputation slides, bibtex
  • Kerstin Fischer, Lakshadeep Naik, Rosalyn M. Langedijk, Timo Baumann, Matou\vs Jel\'\inek and Oskar Palinko (2021).
    "Initiating Human-Robot Interactions Using Incremental Speech Adaptation".
    in: Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction. New York, USA. Association for Computing Machinery, 421–425.
    DOI, pdf, bibtex
  • Norbert Krüger, Fischer, Kerstin, Manoonpong, Poramate, Palinko, Oskar, Bodenhagen, Leon, Baumann, Timo, Kjærum, Jens, Rano, Ignacio, Naik, Lakshadeep, Juel, William Kristian, Haarslev, Frederik, Ignasov, Jevgeni, Marchetti, Emanuela, Langedijk, Rosalyn Melissa, Kollakidou, Avgi, Jeppesen, Kasper Camillus, Heidtmann, Conny and Dalgaard, Lars (2021).
    "The SMOOTH-Robot: A Modular, Interactive Service Robot".
    Frontiers in Robotics and AI, 8:294. .
    DOI, URL, bibtex
  • Timo Baumann and Felix Lindner (2015).
    "Incremental Speech Production for Polite and Natural Personal-Space Intrusion".
    in: Social Robotics, Proceedings of the 7th International Conference, ICSR 2015. Paris, France. Springer, pages 72-82.
    DOI, pdf, video, bibtex
  • Timo Baumann and David Schlangen (2012).
    "Inpro_iSS: A Component for Just-In-Time Incremental Speech Synthesis".
    in: Procs of ACL 2012 System Demos. Jeju, Korea.
    URN, pdf, poster, bibtex
  • Timo Baumann and David Schlangen (2012).
    "The InproTK 2012 Release".
    in: Proceedings of the NAACL-HLT Workshop on Future direction sand needs in the Spoken Dialog Community: Tools and Data. Montréal, Canada, pages 29-32.
    URN, pdf, poster, bibtex
  • Timo Baumann, Okko Buß and David Schlangen (2010).
    "InproTK in Action: Open-Source Software for Building German-Speaking Incremental Spoken Dialogue Systems".
    in: Elektronische Sprachsignalverarbeitung (ESSV 2010). Berlin, Germany. TUDpress.
    URN, pdf, slides, bibtex


This project was primarily funded as part of David Schlangen's DFG Emmy Noether group at Potsdam University, as well as through a grant by Daimler and Benz foundation 2014-2017.


Page last modified on November 26, 2021, at 03:57 PM
Powered by PmWiki