This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
||||||||
|
Paper Details
Paper Title
Comparative Analysis of Random Forests and Inception-v3 for Broadcast Audio Classification
Authors
  Kamatchy B,  P. Dhanalakshmi
Abstract
This paper focuses on the comparative analysis of two different audio pattern classifiers for classifying TV broadcast audio data into one of five categories namely Advertisement, Cartoon, News, Songs and Sports. For Classifying TV broadcast audio data, machine learning algorithm Random Forests and deep learning pretrained model Inception -v3 are implemented and the results are compared. In this comparative analysis, the pretrained model Inception-v3 exhibits increased efficiency in classifying the broadcast audio data.
Keywords- Audio Segmentation, Mel Frequency Cepstral Coefficients (MFCC), Audio Classification, Inception-v3, Random Forests, Spectrogram, Transfer learning.
Publication Details
Unique Identification Number - IJEDR2004034Page Number(s) - 206-210Pubished in - Volume 8 | Issue 4 | December 2020DOI (Digital Object Identifier) -    Publisher - IJEDR (ISSN - 2321-9939)
Cite this Article
  Kamatchy B,  P. Dhanalakshmi,   "Comparative Analysis of Random Forests and Inception-v3 for Broadcast Audio Classification", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.8, Issue 4, pp.206-210, December 2020, Available at :http://www.ijedr.org/papers/IJEDR2004034.pdf
Article Preview
|
|
||||||
|