Sixth European Conference on Speech Communication and Technology
(EUROSPEECH'99)

Budapest, Hungary
September 5-9, 1999

An Effective Scoring Method for Speaking Skill Evaluation System

Zhanjiang Song, Fang Zheng, Mingxing Xu, Wenhu Wu

Speech Lab., Dept. of Computer Science & Technology, Tsinghua University, Beijing, China

The Speaking Skill Evaluation (SSE) technologies are derived from speech recognition technologies and are used for language learning and instructing. In this paper, an effective automatic pronunciation scoring method for SSE systems is proposed. The Center-Distance Continuous Probability Model (CDCPM) is incorporated to model the speech. The Merging-Based Syllable Detection Automaton (MBSDA) and the Non-Linear Partition (NLP) method are used to perform the time alignment. And the Critical Area Percentage (CAP) based scoring method is used to score the learnerís pronunciations or reject invalid utterances. Subjective assessments show that this method is concise, fast, and effective. The SSE system based on it has achieved a satisfying performance.


Full Paper (PDF)   Gnu-Zipped Postscript

Bibliographic reference.  Song, Zhanjiang / Zheng, Fang / Xu, Mingxing / Wu, Wenhu (1999): "An effective scoring method for speaking skill evaluation system", In EUROSPEECH'99, 187-190.