Classification of sonorant consonants utilizing empirical mode decomposition

Author

Ashrafi, Ashkan ; Wenndt, Stanley

Author_Institution

Dept. of Electr. & Comput. Eng., San Diego State Univ., San Diego, CA, USA

fYear

2014

Firstpage

843

Lastpage

846

Abstract

In this paper, a method to classify nasal utterance among sonorant consonants utilizing empirical mode decomposition (EMD) is introduced. In this method, each audio signal is divided into overlapping 20 millisecond frames. Then each frame´s signal is decomposed by using the EMD. Four different features are extracted from each frame to create a vector. These vectors are employed to train a support vector machine (SVM) with radial basis functions. A different set of audio signals are used to validate the SVM model. The results show an overall correct identification rate of 91.19% for nasals and 89.74% for semivowels.

Keywords

audio signal processing; feature extraction; radial basis function networks; signal classification; speech processing; support vector machines; EMD; SVM model; audio signal; empirical mode decomposition; feature extraction; frame signal decomposition; identification rate; nasal utterance classification; radial basis functions; semivowels; sonorant consonant classification; support vector machine training; Acoustics; Databases; Fourier transforms; Speech; Speech processing; Support vector machines; Empirical mode decomposition; Nasals; Semivowels; Sonorant consonants; Support vector machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Signals, Systems and Computers, 2014 48th Asilomar Conference on

Print_ISBN

978-1-4799-8295-0

Type

conf

DOI

10.1109/ACSSC.2014.7094569

Filename

7094569