Detecting tone errors in continuous Mandarin speech

This paper proposes a new approach for detecting tone errors in continuous Mandarin speech. In the training phase, tone variations are modeled with context-depended MSD-HMM which considers six contextual factors instead of two in traditional triphone HMM. In the evaluation phase, the goodness of tone pronunciation is measured by Kullback-Leibler divergence (KLD) between the expected tone model and the most representative tone model. When the KLD between the two models is larger than a threshold, the tone is detected as a pronunciation error. In the ROC curve, we get the equal error rate at 2.6%.