Abstract:This paper mainly concerns the problem of confidence measure
estimation for Spoken Term Detection (STD). The detecting precision
is always a main obstacle to make STD system to be applicable in
real-world. In this context, a multi-source knowledge fusion
strategy was proposed to improve the qualification of confidence
measure of detected spoken term which is mainly estimated by
posterior probability before. For lattice based STD system, a
collection of optimal predictive information of detected term is
extracted, and the hidden-units Conditional Random Fields
(hidden-units CRFs) is adopted to combine these information into a
normalized conditional probability to stand for an alternative score
of detected term. More precisely, the discriminative ability of
multi-source knowledge fusion based confidence measure is proved to
be superior to the posterior based confidence measure first. And
then, the new proposed confidence measure was combined with the
posterior to improve detecting precision and decrease False Alarm
rate (FA) in a lattice-based STD system for Conversional Telephone
Speech (CTS). Experimental results show that the new proposed
confidence measure has strong complimentary effect and improve the
detecting precision about 17\% over the baseline system in high
precision area.
Xinglong Gao;Jielin Pan;Yonghong Yan. A Multi-source Knowledge Fusion Strategy to Improve Confidence Measure in a Lattice-based Spoken Term Detection System[J]. , 2014, 11(11): 3783-3792.
Xinglong Gao;Jielin Pan;Yonghong Yan. A Multi-source Knowledge Fusion Strategy to Improve Confidence Measure in a Lattice-based Spoken Term Detection System. , 2014, 11(11): 3783-3792.