Generalized Segment Posterior Probability for Automatic Mandarin Pronunciation Evaluation
Zheng Jing, Chao Huang, Min Chu, Frank K. Soong, Weiping Ye · 2007
In this paper, we investigate the automatic pronunciation evaluation method for native Mandarin. Multi-space distribution (MSD) hidden Markov model (HMM) is adopted to train the gold standard model. Machine scores derived from the generalized segment posterior probability on both syllables and phone level are proposed and investigated to measure the goodness of pronunciation (GOP). They are evaluated on the database collected internally and shown better performance than other well-known methods. In addition, detailed analyses of human scoring such as inter/intra-rater on utterance/speaker level are also given.