A System Demonstration of a Framework for Computer Assisted Pronunciation Training

Abstract

In this paper, we demonstrate a system implementation of a framework for computer assisted pronunciation training for second language learner (L2). This framework supports an iterative improvement of the automatic pronunciation error recognition and classification by allowing integration of annotated error data. The annotated error data is acquired via an annotation tool for linguists. This paper will give a detailed description of the annotation tool and explains the error types. Furthermore, it will present the automatic error recognition method and the methods for automatic visual and audio feedback. This system demonstrates a novel approach to interactive and individualized learning for pronunciation training.