Error Pattern Detection Integrating Generative and Discriminative Learning for Computer-Aided Pronunciation Training

摘要

Computer-Assisted Language Learning tries to have computers serve as virtual language tutors to help people in learning non-native languages in the globalized world nowadays. In this paper we propose a framework to in corporate specially designed discriminative models with carefully trained generative models for the task of pro nunciation error pattern detection. For each phoneme we train one or more SVMs with varying targets and dif ferent weights to integrate with HMM/GMMs for opti mizing the detection performance from different aspects. Experiments show this integration framework effectively enhance mispronunciation detection performance.