A SVOR based method for automatic scoring of prosody quality in Mandarin speech

Author

Jia, Hui-bin ; Qi, Yin-cheng

Author_Institution

Dept. of Electron. & Commun., North China Electron. Power Univ., Baoding, China

Volume

4

fYear

2010

fDate

11-14 July 2010

Firstpage

2109

Lastpage

2114

Abstract

Automatic Scoring of prosody quality in Mandarin is an essential part of computer-aided language learning system. In the paper, a method is investigated to automatically score prosody quality in Mandarin speech. The method is based on prosody comparison between the tested and standard sentence. The prosodic similarities are calculated from three aspects: tone, intonation and rhythm. Based on these similarities, a ranking algorithm named SVOR is proposed to predict the prosody quality score. Compared to SVM algorithm, the algorithm shows the better performance. It shows that human scoring of prosody quality is of ranking. In addition, detailed analyses of human scoring at the sentence-level are given.

Keywords

computer aided instruction; linguistics; natural languages; regression analysis; speech recognition; support vector machines; Mandarin speech; SVOR based method; computer-aided language learning system; prosody quality automatic scoring; support vector ordinal regression; Algorithm design and analysis; Correlation; Databases; Humans; Prediction algorithms; Rhythm; Speech; Automatic Scoring; Prosody Quality; SVM; SVOR;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics (ICMLC), 2010 International Conference on

Conference_Location

Qingdao

Print_ISBN

978-1-4244-6526-2

Type

conf

DOI

10.1109/ICMLC.2010.5580495

Filename

5580495