Investigation of Subwords Confidence Performance in Chinese Speech Verification
Chengli Sun · Zhongwen xinxi xuebao · 2008
A Minimum Classification Error(MCE) criterion based sub-words weighting parameters estimation algorithm is proposed in which the sub-word weighting parameters are derived by the MCE training.Investigation of the contribution of different sub-words on the word-level confidence measure show that Finals significantly outperform the Initials with more reliability and stability in confidence performance,and Finals have more discriminative power than those of Initials.Experiment on keyword spotting system with 130 keywords shows that the system with different sub-word weighting contribution achieved a relative Equal Error Rate(EER) reduction of 3.05% compared with the equal weighting contribution case.