Comparing acoustic features for robust ASR in fixed and cellular network applications

Article OPEN
Wet, F. de; Cranen, B.; Veth, J.M. de; Boves, L.W.J.;
  • References (10)

    [1] J. de Veth and L. Boves. Channel normalization techniques for autom atic speech recognition over the telephone. Speech Com m unication, 25:149-164, 1998.

    [2] J. de Veth, B. Cranen and L. Boves. Acoustic backing off in the local distance com putation for robust autom atic speech recognition. In Proceedings o f IC SL P '98, pages 1427-1430, Sydney, Australia, 1998.

    [3] J. de Veth, B. Cranen, F. de Wet and L. Boves. Acoustic pre-processing for optimal effectivity of missing feature theory. In Proceedings o f Eurospeech '99, pages 65-68, Budapest, Hungary, September 1999.

    [4] J. de Veth, F. de Wet, B. Cranen and L. Boves. Missing feature theory in ASR: make sure you miss the right type of features. In Workshop on robust methods fo r speech recognition in adverse conditions, pages 231-234, Tampere, Finland, 1999.

    [5] E. A. den Os, T. I. Boogaart, L. Boves and E. Klabbers. The D utch Polyphone corpus. In Proceedings of Eurospeech '95, pages 825-828, Madrid, 1995.

    [6] ETSI. Draft ETSI EN 300 726 V6.0.0; Digital cellular systems (phase 2); Enhanced Full R ate (EFR) speech transcoding, h ttp://w w w .etsi.o rg /, 1999.

    [7] K. K. Paliwal. On the use of Line Spectral Frequency param eters for speech recognition. Digital Signal Processing, 2:80-87, 1992.

    [8] T. F. Quatieri, R. B. Dunn, D. A. Reynolds and J. P. Campbell. Speaker and language recognition using speech coding parameters. In Proceedings o f Eurospeech '99, pages 787-790, Budapest, Hungary, September 1999.

    [9] L. F. Willems. Robust formant analysis. In IP O A nnual report 21, pages 34-40, Eindhoven, The Netherlands, 1986.

    [10] S. Young, J. Jansen, J. Odell, D. Ollason and P. Woodland. The H T K Book (for H T K Version 2.1). Cambridge University, Cambridge, UK, 1995.

  • Metrics
Share - Bookmark

  • Download from
  • Cite this publication