2024-03-29T12:47:39Z
https://meral.edu.mm/oai
oai:meral.edu.mm:recid/4200
2022-03-24T23:12:02Z
1582963302567:1597824273898
user-ucsy
Audio Classification Framework based on DSVM
Lin, K Zin
The explanation of how a decision made isimportant for accepting the machine learningtechnology, especially for applications such asmultimedia. SVMs have shown strong generalizationability in a number of application areas, includingaudio classification. However, the poorcomprehensibility hinders the success of the SVM foraudio class prediction. On the other hand, a decisiontree has good comprehensibility. This approachcombines the SVM with decision tree. We use theSVM as a decision of binary tree to select stronginstances to generate rules; it is known as decisionSVM (DSVM). We considered eight audio classes:silence, non-silence, speech with music, speech withnoise, music with environment sound, instrumentalmusic, environmental sound and noise. Thisclassification and analysis is intended to analyze thestructure of the sports video.
2009-12-30
http://hdl.handle.net/20.500.12678/0000004200
https://meral.edu.mm/records/4200