2026-10-24T09:23:38Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/3893 2021-12-13T01:13:20Z 1582963302567:1597824273898 user-ucsy

Audio Classification using Gaussian Mixture Model Myint, Yuzana Swe, Ei Mon Mon This paper describes the work done on thedevelopment of an audio classification system. Audio recordingsare classified into basic audio types such as speech or music.Audio classification is processed in two parts, feature extractionand classification, which makes it suitable for differentapplications. In first part, input audio signal is transformed intofeature vectors, carrying characteristics information about thesignal. Audio Features for this task include Short Time Energy(SE), Zero Crossing Rate (ZC) and Mel Frequency CepstralCoefficient (MFCC). The second part classify feature vector intospeech or music. Gaussian Mixture Model (GMM) is used forclassification task. The overall accuracy rate of this paper getsaround 93%. 2009-08-03 http://hdl.handle.net/20.500.12678/0000003893 https://meral.edu.mm/records/3893