Speech-Understanding Systems The Communication Technology of Tomorrow?

  • Klaus Zünkler


This article will give an outline of the development of a technology which leads to a man-machine communication with natural language. Different applications and projects in the framework of speech processing are presented. A closer look at the SPICOS system (Siemens, Philips, IPO Continuous Speech Recognition and Understanding of fluently spoken language) shows the integration and use of higher, linguistic knowledge sources into the process of acoustic recognition of speech units.


Language Model Speech Signal Semantic Network Dialogue System Continuous Speech 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. /1/.
    A. Aktas and H. Höge. Real-time recognition of subword units on a hybrid multiDSP/ASIC based acoustic-frontend. In Proc. of the ICASSP 1989,Glasgow, pp. 616–619.Google Scholar
  2. /2/.
    A. Aktas and H. Höge. Multi-DSP and VQ-ASIC Based acoustic front-end for real-time speech processing tasks. In Proceedings of Eurospeech, Paris 1989, pp. 586–589.Google Scholar
  3. /3/.
    H.-U. Block, M. Gehrke, H. Haugeneder, R. Hunze. Probleme der Wissensrepräsentation in Beratungssystemen. In WISBER series, report 7, April 1986.Google Scholar
  4. /4/.
    H. Höge, B. Littel, E. Marschall, O. Schmidbauer and R. Sommer. Syllable-based Acoustic-Phonetic Decoding and Wordhypotheses Generation in Fluently Spoken Speech. In Proc. of the ICASSP 1986,Tokyo, pp. 1561–1564.Google Scholar
  5. /5/.
    H. Ney, A. Noll, D. Mergel and A. Paeseler. Overview of speech recognition in the SPICOS system. In Recent Advances of Speech Understanding and Dialogue Systems, NATO ASI series F46, Springer, Berlin 1988,pp. 305–309.Google Scholar
  6. /6/.
    A. Paeseler and H. Ney. Continuous speech recognition using a stochastic language model. In Proc. of the ICASSP 1989,Glasgow, pp. 1139–1142.Google Scholar
  7. /7/.
    O. Schmidbauer. Bereitstellung von normierten Formant-Parametern zur Erkennung fließender Sprache. In Proceedings SPEECH 88, 7-th FASE symposium,pp 1257–1264.Google Scholar
  8. /8/.
    O. Schmidbauer. Robust statistic modeling of systematic variabilities in continuous speech incorporating acoustic-articulatory relations. In Proc. of the ICASSP 1989,pp. 616–619.Google Scholar
  9. /9/.
    C.L. Sidner. Focusing in the Comprehension of Definite Anaphora. in Computational Models of Discourse, editors: Brady, Michael and Berwich, MIT Cambridge, pp. 267–330.Google Scholar
  10. /10/.
    V. Steinbiss. Sentence-hypotheses generation in a continuous-speech recognition system. In Proceedings of Eurospeech, Paris 1989, pp. 51–54.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1990

Authors and Affiliations

  • Klaus Zünkler
    • 1
  1. 1.Siemens AGGermany

Personalised recommendations