INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
This paper presents our experiments on acoustic scene classification. Classification of acoustic scene to extract the audio features is a tough task because of the diversity in their nature. Extracting the appropriate features is an important task for increasing the efficiency of the classification. Using MFCC features alone will not achieve a maximum efficiency in characterization of acoustic scenes. Here we use MFCC algorithm along with MP Algorithm to classify the acoustic scenes. Here we use Support Vector Machine Algorithm to train the machine. Classifier model is built using libSVM for training samples and the machine is then able to recognize various acoustic Scenes. Results shows that Acoustic scene classification achieves better accuracy when MP algorithm is used along with MFCC.
"Acoustic Event Classification using MFCC and MP Algorithm", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.2, Issue 5, page no.28 - 31, April-2017, Available :http://www.ijsdr.org/papers/IJSDR1705006.pdf
Downloads:
000337212
Publication Details:
Published Paper ID: IJSDR1705006
Registration ID:170246
Published In: Volume 2 Issue 5, April-2017
DOI (Digital Object Identifier):
Page No: 28 - 31
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn