Search Contact information
University of Cambridge Home Department of Engineering
University of Cambridge > Engineering Department > Machine Intelligence Lab

Abstract for beattie_tr92

Cambridge University Engineering Department Technical Report CUED/F-INFENG/TR92

HIDDEN MARKOV MODEL STATE-BASED NOISE CANCELLATION

V. L. Beattie and S. J. Young

February 1992

This report summarizes the work done at Cambridge University Engineering Department on developing noise-robust algorithms within a Hidden Markov Model recognition system. The aim of this research has been to develop noise-robust algorithms for use within the HMM recognition framework, as opposed to noise cancellation or compensation at the preprocessing level. Such algorithms can take advantage of the clean speech model presented by the HMMs themselves. This research formed part of ESPRIT Project p.2101, ``Adverse-Environment Recognition of Speech'' (ARS).


| (ftp:) beattie_tr92.ps.Z | (http:) beattie_tr92.ps.Z | (ftp:) beattie_tr92.tex.Z | (http:) beattie_tr92.tex.Z |
PDF (automatically generated from original PostScript document - may be badly aliased on screen):
  (ftp:) beattie_tr92.pdf | (http:) beattie_tr92.pdf

If you have difficulty viewing files that end '.gz', which are gzip compressed, then you may be able to find tools to uncompress them at the gzip web site.

If you have difficulty viewing files that are in PostScript, (ending '.ps' or '.ps.gz'), then you may be able to find tools to view them at the gsview web site.

We have attempted to provide automatically generated PDF copies of documents for which only PostScript versions have previously been available. These are clearly marked in the database - due to the nature of the automatic conversion process, they are likely to be badly aliased when viewed at default resolution on screen by acroread.

© 2005 Cambridge University Engineering Dept
Information provided by milab-maintainer