Automatic Voice Quality Measurement Based on Efficient Combination of Multiple Features

Author

Lee, Ji-Yeoun ; Jeong, Sangbae ; Hahn, Minsoo ; Choi, Hong-Shik

Author_Institution

Inf. & Commun. Univ., Daejeon

fYear

2008

Firstpage

1272

Lastpage

1275

Abstract

This work proposes higher-order statistics (HOS)- based features to improve classification performance of voice quality measurement. They are means and variances of skewness and kurtosis which show meaningful differences in normal, breathy, and rough voices. Jitter, shimmer, and harmonic to noise ratio (HNR) are implemented as conventional features. The performances are measured by classification and regression tree (CART) analysis. Specifically, the CART-based method by utilizing both conventional and HOS-based features is shown to be an effective for voice quality measurement, with an 89.7% classification rate.

Keywords

feature extraction; medical signal processing; patient diagnosis; regression analysis; signal classification; speech; speech processing; automatic voice quality measurement; breathy voices; classification and regression tree analysis; harmonic to noise ratio; higher-order statistics; jitter; kurtosis; multiple features; normal voices; rough voices; shimmer; skewness; voice classification; Acoustic measurements; Classification tree analysis; Higher order statistics; Jitter; Pathology; Performance analysis; Performance evaluation; Regression tree analysis; Signal to noise ratio; Vibration measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Bioinformatics and Biomedical Engineering, 2008. ICBBE 2008. The 2nd International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-1747-6

Electronic_ISBN

978-1-4244-1748-3

Type

conf

DOI

10.1109/ICBBE.2008.646

Filename

4535526