Jw. Hung et al., New approaches for domain transformation and parameter combination for improved accuracy in parallel model combination (PMC) techniques, IEEE SPEECH, 9(8), 2001, pp. 842-855
Parallel model combination (PMC) techniques have been very successful and p
opularly used in many applications to improve the performance of speech rec
ognition systems under noisy environments. However, it is believed that som
e assumptions and approximations made in this approach, primarily in the do
main transformation and parameter combination processes, are not necessaril
y accurate enough in certain practical situations, which may degrade the ac
hievable performance of PMC. In this paper, the possible sources that cause
the performance degradation in these processes are carefully analyzed and
discussed. Three new approaches, including the truncated Gaussian approach
and the split mixture approach for domain transformation process and the es
timated cross-term approach for parameter combination process, are proposed
in this paper in order to handle these problems, minimize such degradation
, and improve the accuracy of the PMC techniques. These proposed approaches
were analyzed and discussed with two recognition tasks, one relatively sim
ple, and the other more complicated and realistic. Both sets of experiments
showed that these proposed approaches are able to provide significant impr
ovements over the original PMC method, especially when the SNR condition is
worse.