5th International Conference on Spoken Language Processing

Sydney, Australia
November 30 - December 4, 1998

Analysis Of Disordered Speech Signal Using Wavelet Transform

Cheol-Woo Jo, Dae-Hyun Kim

Changwon National University, Korea

In this paper a method to analyze pathological speech signal using wavelet transform is suggested. Pathological speech signal is commercially available pathological voice database and analyzed by the suggested method. Normal speech signal is also from the same database and analyzed as well. Then the results are compared to find the differences between normal and pathological speech. Three level wavelet transform is used. Normalized energy ratios between the levels and normalized peak-to-peak values are used as parameters. As a result, it was possible to distinguish between normal and pathological speech signal.

Full Paper

Bibliographic reference.  Jo, Cheol-Woo / Kim, Dae-Hyun (1998): "Analysis of disordered speech signal using wavelet transform", In ICSLP-1998, paper 0691.