Text-independent pronunciation evaluation based on phone-level Gaussian classifier

This paper presents a novel text-independent pronunciation evaluation method. The method aims at testing the mandarin Putonghua pronunciation proficiency of the dialectal speakers from every area of China. In the proposed method, 5 pronunciation proficiency levels are assigned for each phone; accordingly, 5 Single Gaussian classifiers are created to represent the 5 levels for a phone. 4 phone-level features are described and used in the classifiers. In the testing step, phone-level output probabilities are combined to get the sentence-level likelihood.

I. Introduction

Computer-assisted language learning (CALL) system can provide many potential benefits to both the foreign language learner and teacher [1]. Native people can also use them to test and improve their official accent skills. It can save many human resources, make the learning environment more flexible and provide many interactive ways to make the learning more attractive.