Audio Classification: A Comprehensive Survey of Research

Conference: Recent Trends in Information Processing, Computing, Electrical and Electronics
Author(s): Arshi Khan, Garbita Gupta, Smita Shandilya, Shishir K. Shandilya Year: 2017
Grenze ID: 02.IPCEE.2017.1.33 Page: 208-214

Abstract

Data mining is define as to extract knowledge from large amount of data. Data mining has a research application in\nthe field of audio, speech processing and spoken word language, so as to get useful data from large amount of data. In this\npaper we have described about audio mining to extract useful audio signals for classification of audio data. Various audio\nfeatures like Mel frequency Cepstral Coefficient (MFCC), Linear Predictive Coefficient (LPC), Compactness, Spectral Flux\n(SF), Band Periodicity (BP), Zero Crossing Rate (ZCR) etc are used to classify audio data into various classes. Various\nclassification algorithms such as Naive Bayes, SVM and PNN are used to classify audio data into defined classes. Using\nvarious performance parameters such as True Positive (TP) Rate, False Positive (FP) Rate etc., results of various classification\nalgorithms are compared.

<< BACK

IPCEE - 2017