Affiliation:
1. Fuqing Branch of Fujian Normal University
Abstract
In order to evaluate the speaker's pronunciation quality, a speech evaluation system based on MFCC is designed by using some techniques including pre-processing, feature extraction and pattern matching and so on. The MFCC parameters of the standard speech and those of the original speech are extracted. The result is given by the mechanism. Experimental results show that the scores assessed by the system is relating to people’s subjective feeling closely. The software is developed by VC++ and runs on windows XP.
Publisher
Trans Tech Publications, Ltd.
Reference11 articles.
1. S.M. Witt, S.J. Young: Phone-level Pronunciation Scoring and Assessment for Interactive Language Learning. in: Speech Communication 30(2000), p.95.
2. JiangChun Chen, J.R. Jang, Junyi Li and MingChun Wu: Automatic pronunciation assessment for Mandarin Chinese. In Proceedings of ICME(2004), p. (1979).
3. Minhua Li, Ruwei Dai, Yaodong Li: Pattern Recognition and Artificial Intelligence. In Chinese. Vol. 21(2008), p.469.
4. J. Gros, F. Mihelic, N. Pavesic, in: Proceedings of ISIE. Vol. 1(1999),P. 213.
5. Weixia Li, Robert F. Kubichek. Output-based objective speech quality measurement using continuous hidden Markov models, in: Seventh International Symposium on Signal Processing and Its Applications( 2003), p.389.