Classification of Functional-Meanings of Non-isolated Discourse Particles in Human-Human-Interaction

  • Alicia Flores Lotz
  • Ingo Siegert
  • Andreas Wendemuth
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9731)

Abstract

To enable a natural interaction with future technical systems, not only the meaning of the pure spoken text, but also meta-information such as attention or turn-taking has to be perceived and processed. This further information is effectively transmitted by semantic and prosodic cues, without interrupting the speaker. For the German language we rely on previous empirically discovered seven types of form-function-concurrences on the isolated discourse particle (DP) “hm”.

In this paper we present an improved automatic classification-method towards non-isolated DPs in human-human interaction (HHI). We show that classifiers trained on (HCI)-data can be used to robustly evaluate the contours of DPs in both HCI and HHI by performing a classifier adaptation to HHI data. We also discuss the problem of the pitch-contour extraction due to the unvoiced “hm”-utterances, leading to gaps and/or jumps in the signal and hence to confusions in form-type classifications. This can be alleviated by our investigation of contours with high extraction completion grade. We also show that for the acoustical evaluation of the functional-meaning, the idealized form-function prototypes by Schmidt are not suitable in case of naturalistic HHI. However, the precision of acoustical-meaning prediction with our classifier remains high.

Keywords

Human-human interaction Human-computer interaction discourse particles Automatic form-function classification 

Notes

Acknowledgment

The work presented was done within the Transregional Collaborative Research Centre SFB/TRR 62 “Companion-Technology for Cognitive Technical Systems” (www.sfb-trr-62.de) funded by the German Research Foundation (DFG).

References

  1. 1.
    Allwood, J., Nivre, J., Ahlsén, E.: On the semantics and pragmatics of linguistic feedback. J. Semant. 9(1), 1–26 (1992)CrossRefGoogle Scholar
  2. 2.
    Biundo, S., Wendemuth, A.: Companion-technology for cognitive technical systems. Künstliche Intelligenz 30(1), 71–75 (2016)CrossRefGoogle Scholar
  3. 3.
    Böck, R., Siegert, I., Haase, M., Lange, J., Wendemuth, A.: ikannotate – a tool for labelling, transcription, and annotation of emotionally coloured speech. In: D’Mello, S., Graesser, A., Schuller, B., Martin, J.-C. (eds.) ACII 2011, Part I. LNCS, vol. 6974, pp. 25–34. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  4. 4.
    Buschmeier, H., Malisz, Z., Skubisz, J., Wlodarczak, M., Wachsmuth, I., Kopp, S., Wagner, P.: Alico: a multimodal corpus for the study of active listening. In: Proceeding of the 9th LREC 2014, Reykjavik, Iceland (2014)Google Scholar
  5. 5.
    Fischer, K., Wrede, B., Brindöpke, C., Johanntokrax, M.: Quantitative und funktionale Analysen von Diskurspartikeln im computer Talk. Int. J. Lang. Data Process. 20(1–2), 85–100 (1996)Google Scholar
  6. 6.
    Giles, H., Coupland, N.: Language: Contexts and Consequences. Cengage Learning, Boston (1991)Google Scholar
  7. 7.
    Lotz, A.F.: Differentiation von Form-Funktions-Verläufen des Diskurs Partikels "hm" über unterschiedliche mathemathische Herangehensweisen. Master’s thesis, Otto von Guericke University Magdeburg (2014)Google Scholar
  8. 8.
    Lotz, A.F., Siegert, I., Wendemuth, A.: Automatic differentiation of form-function-relations of the discourse particle “hm" in a naturalistic human-computer interaction. In: Günther, W. (ed.) Elektronische Sprachsignalverarbeitung 2015, Studientexte zur Sprachkommunikation, vol. 78, pp. 172–179. TUDpress (2015)Google Scholar
  9. 9.
    Paschen, H.: Die Funktion der Diskurspartikel HM. Master’s thesis, University Mainz (1995)Google Scholar
  10. 10.
    Rösner, D., Haase, M., Bauer, T., Günther, S., Krüger, J., Frommer, J.: Desiderata for the design of companion systems - insights from a large scale wizard of oz experiment. Künstliche Intelligenz 30(1), 53–61 (2016)CrossRefGoogle Scholar
  11. 11.
    Rösner, D., Frommer, J., Friesen, R., Haase, M., Lange, J., Otto, M.: Last minute: a multimodal corpus of speech-based user-companion interactions. In: Proceeding of the 8th LREC 2012, pp. 2559–2566, Istanbul, Turkey (2012)Google Scholar
  12. 12.
    Schmidt, J.E.: Bausteine der intonation. In: Neue Wege der Intonationsforschung, Germanistische Linguistik, vol. 157–158, pp. 9–32, Georg Olms Verlag (2001)Google Scholar
  13. 13.
    Siegert, I., Böck, R., Wendemuth, A.: Inter-rater reliability for emotion annotation in human-computer interaction: comparison and methodological improvements. J. Multimodal User Interfaces 8(1), 17–28 (2014)CrossRefGoogle Scholar
  14. 14.
    Siegert, I., Haase, M., Prylipko, D., Wendemuth, A.: Discourse particles and user characteristics in naturalistic human-computer interaction. In: Kurosu, M. (ed.) HCI 2014, Part II. LNCS, vol. 8511, pp. 492–501. Springer, Heidelberg (2014)Google Scholar
  15. 15.
    Siegert, I., Prylipko, D., Hartmann, K., Bück, R., Wendemuth, A.: Investigating the form-function-relation of the discourse particle “hm" in a naturalistic human-computer interaction. In: Bassis, S., Esposito, A., Morabito, F.C. (eds.) Recent Advances of Neural Networks Models and Applications. SIST, vol. 26, pp. 387–394. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  16. 16.
    Sievers, E.: Grundzüge der Phonetik, 5th edn. Breitkopf Härtel, Leipzig (1901)Google Scholar
  17. 17.
    Wendemuth, A.: Grundlagen der stochastischen Sprachverarbeitung. Oldenbourg, Munich (2004)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Alicia Flores Lotz
    • 1
  • Ingo Siegert
    • 1
  • Andreas Wendemuth
    • 1
  1. 1.Institute of Information and Communication Engineering, Cognitive Systems GroupOtto von Guericke UniversityMagdeburgGermany

Personalised recommendations