CDF-Matching for Automatic Tone Error Detection in Mandarin Call System
Si Wei, Hai‐Kun Wang, Qingsheng Liu, Ren-Hua Wang · 2007
This paper introduces a tone pronunciation error detection algorithm for Mandarin CALL system. HMM is introduced to build tone model. FO after CDF-matching normalization is used as the feature of tone model. Tone error detection algorithm is based on the posterior probability calculated from HMM tone models. Comparing to the other normalization methods, CDF-matching can get better tone error detection performance with CC's increasing from 0.76 to 0.79, which is close to that between human evaluators (0.83).