Statistical correlation analysis between lip contour parameters and formant parameters for Mandarin monophthongs
View/ Open
Author(s)
Wu, Junru
Pan, Xiaosheng
Kong, Jiangping
Liew, Alan Wee-Chung
Griffith University Author(s)
Year published
2008
Metadata
Show full item recordAbstract
In this study we examine quantitatively the correlation between the geometric lip contour parameters and the formant parameters for Mandarin monophthongs, and carry out a multiple linear regression study between the two parameters. We explicitly analyze the relationship between different geometric lip parameters and the formant parameters, which have some linguistic significance instead of the usual acoustic parameters such as MFCC. We analyzed the linguistic meaning of the regression formula, and found it in accord with the classical result on the relationship between vocaltrack and speech acoustics. And those regions with ...
View more >In this study we examine quantitatively the correlation between the geometric lip contour parameters and the formant parameters for Mandarin monophthongs, and carry out a multiple linear regression study between the two parameters. We explicitly analyze the relationship between different geometric lip parameters and the formant parameters, which have some linguistic significance instead of the usual acoustic parameters such as MFCC. We analyzed the linguistic meaning of the regression formula, and found it in accord with the classical result on the relationship between vocaltrack and speech acoustics. And those regions with relatively poor effect of estimation are related to specific phonetic conditions.
View less >
View more >In this study we examine quantitatively the correlation between the geometric lip contour parameters and the formant parameters for Mandarin monophthongs, and carry out a multiple linear regression study between the two parameters. We explicitly analyze the relationship between different geometric lip parameters and the formant parameters, which have some linguistic significance instead of the usual acoustic parameters such as MFCC. We analyzed the linguistic meaning of the regression formula, and found it in accord with the classical result on the relationship between vocaltrack and speech acoustics. And those regions with relatively poor effect of estimation are related to specific phonetic conditions.
View less >
Conference Title
Proceedings of the International Conference on Auditory-Visual Speech Processing 2008
Copyright Statement
© 2008 ISCA and the Authors. The attached file is reproduced here in accordance with the copyright policy of the publisher. For information about this conference please refer to the conference’s website or contact the authors.
Subject
Pattern Recognition and Data Mining