Missing data techniques for robust speech recognition

  title={Missing data techniques for robust speech recognition},
  author={Martin Cooke and Andrew C. Morris and Phil D. Green},
In noisy listening conditions, the information available on which to base speech recognition decisions is necessarily incomplete: some spectro-temporal regions are dominated by other sources. We report on the application of a variety of techniques for missing data in speech recognition. These techniques may be based on marginal distributions or on reconstruction of missing parts of the spectrum. Application of these ideas in the Resource Management task shows performance which is robust to… CONTINUE READING
Highly Cited
This paper has 122 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 73 extracted citations

122 Citations

Citations per Year
Semantic Scholar estimates that this publication has 122 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 11 references

Auditory organisation and speech perception : Arguments for an integrated computational theory ”

  • J. S. Garofolo, D. S. Pallett
  • ESCA ETRW on The Auditory Basis of Speech…
  • 1996

Missing data techniques for robust speech recognition ”

  • S. J. Hanson, J. D. Cowan, M. Cooke, A. Morris, P. Green
  • Proc .
  • 1996

Auditory scene analysis and HMM recognition of speech in noise ”

  • H Hermansky, S. Tibrewala, M. Pavel
  • Proc . ICASSP
  • 1995

Use of the CD - ROM for speech database storage and exchange ’

  • Z. Ghahramani, M. I. Jordan
  • Proc . Euro . Conf . Speech Communication and…
  • 1989

Dilogarithms and Associated Functions

  • L. Lewin
  • 1958
1 Excerpt

Similar Papers

Loading similar papers…