Please use this identifier to cite or link to this item:
http://dspace.unimap.edu.my:80/xmlui/handle/123456789/26409
Title: | Speech stuttering assessment using sample entropy and Least Square Support Vector Machine |
Authors: | Muthusamy, Hariharan, Dr. Vijean, Vikneswaran Chong, Yen Fook Sazali, Yaacob, Prof. Dr. hari@unimap.edu.my |
Keywords: | Bark scale Erb Scale Least square support vector machine Mel scale Sample entropy Sample entropy Wavelet packet decomposition |
Issue Date: | Mar-2012 |
Publisher: | Institute of Electrical and Electronics Engineers (IEEE) |
Citation: | p. 240-245 |
Abstract: | This work is intended to discuss the performance of sample entropy feature for the recognition of stuttered events. The data for the analysis is taken from the UCLASS database. Manual segmentation is performed to identify the stuttered events prior to the feature extraction process. Wavelet packet decomposition is performed, and the sample entropy features are extracted using three different filter banks, Bark scale, Mel scale and Erb scale. The extracted features are tested using Least Square Support Vector Machine (LS SVM) for the identification of repetition and prolongation. Ten fold cross validation method is used to ensure the reliability of the results. The experimental investigations reveal that the proposed method shows promising results in distinguishing between the two stuttering events. |
Description: | Link to publisher's homepage at http://ieeexplore.ieee.org/ |
URI: | http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6194726 http://dspace.unimap.edu.my/123456789/26409 |
ISBN: | 978-146730961-5 |
Appears in Collections: | Sazali Yaacob, Prof. Dr. Conference Papers Hariharan Muthusamy, Dr. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Speech stuttering assessment using sample entropy and Least Square Support Vector Machine.pdf | 28.12 kB | Adobe PDF | View/Open |
Items in UniMAP Library Digital Repository are protected by copyright, with all rights reserved, unless otherwise indicated.