FACTOR ANALYSED HIDDEN MARKOV MODELS FOR SPEECH RECOGNITION
A-V.I. Rosti & M.J.F. Gales
April 4, 2003
Recently various techniques to improve the correlation model of feature vector elements in speech recognition systems have been proposed. Such techniques include semi-tied covariance HMMs and systems based on factor analysis. All these schemes have been shown to improve the speech recognition performance without dramatically increasing the number of model parameters compared to standard diagonal covariance Gaussian mixture HMMs. This paper introduces a general form of acoustic model, the factor analysed HMM. A variety of configurations of this model and parameter sharing schemes, some of which correspond to standard systems are examined. An EM algorithm for the parameter optimisation is presented along with a number of methods to increase the efficiency of training. The performance of FAHMMs on medium to large vocabulary continuous speech recognition tasks is investigated. The experiments show that without elaborate complexity control an equivalent or better performance compared to a standard diagonal covariance Gaussian mixture HMM system can be achieved with considerably fewer parameters.
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.