Phone-dependent transformation of posterior probability measure for automatic pronunciation quality evaluation
Ke Yan · 2014
Posterior probability measure is widely accepted as the most promising feature for automatic pronunciation quality evaluation. However, this measure is not phonetically consistent. This work presents a novel trainable phone-dependent transformation of posterior probability to deal with the problem. Both linear and non-linear transforms are investigated. Close form solution is found for linear transformation and gradient-based method is derived for nonlinear transformation. Experimental results on the database of 3685 people showed significant improvement. The cross-correlation between human and machine scores increases from 0.582 to 0.760.