Abstract for liu_icassp2004



X. Liu & M. J. F. Gales

May 2004

State-of-the-art large vocabulary speech recognition systems are highly complex. Many techniques affect both system complexity and recognition performance. The need to determine the appropriate complexity without having to build each possible system has lead to the development of automatic complexity control criteria. In this paper further experiments are carried out using a recently proposed criterion based on marginalizing an MMI growth function. The use of this criterion is much detailed for determining the appropriate dimensionality in a multiple HLDA system and the number of components per state. A scheme for also using this criterion for model compression is described. Experimental results on a spontaneous telephone speech recognition task are described. Initial system compression experiments are inconclusive. However, comparing a standard state-of-the-art system with one generated using complexity control shows a reduction in word error rate.

| (ftp:) liu_icassp2004.pdf | (http:) liu_icassp2004.pdf | (ftp:) liu_icassp2004.ps.gz | (http:) liu_icassp2004.ps.gz |

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.