SUBSPACE MODELS FOR SPEECH TRANSITIONS USING PRINCIPAL CURVES
K. Reinhard and M. Niranjan
November 1998
In this paper we report on attempting to capture segmental transition information for speech recognition tasks. The slowly varying dynamics of spectral trajectories carries much discriminant information that is very crudely modelled by traditional approaches such as HMMs. In attempts such as recurrent neural networks there is the hope, but not convincing demonstration, that such transitional information could be captured. We start from the very different position of explicitly capturing the trajectory of short time spectral parameter vectors on a subspace in which the temporal sequence information is preserved (Time Constrained Principal Component Analysis). We use the Principal Curve algorithm of Hastie and Stuetzle to describe the temporal evolution in terms of a parameterised curve. On the difficult problem of /bee/, /dee/ and /gee/ we are able to retain discriminatory information with a small number of parameters. Experimental illustrations present results on ISOLET and TIMIT database.
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.