Acoustic confusions degrade the accuracy of pronunciation assessment severely in Computer Assisted Language Learning (CALL) systems. This paper presents our recent study on optimal modeling of the acoustic confusions. We change the traditional mandarin syllable structure, which is composed of initial and final, to a novel phoneme structure. Several phoneme splitting strategies are investigated, and the question list used for building and merging decision tree is studied. The questions are special to each phoneme splitting strategy. Experiments show that the optimal phoneme splitting strategy outperforms the traditional initial-final structure in our CALL system, with relative 11.05% ASER improvement for nasal finals. This idea may be extended to improve the performance of automatic speech recognition (ASR).
Bibliographic reference. Ge, Fengpei / Pan, Fuping / Liu, Changliang / Dong, Bin / Yan, Yonghong (2008): "Forward optimal modeling of acoustic confusions in Mandarin CALL system", In INTERSPEECH-2008, 2815-2818.