Animal Sound Classification Using A Convolutional Neural Network

Emre Sasmaz, F. Boray Tek

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

33 Citations (Scopus)

Abstract

In this paper, we investigate the problem of animal sound classification using deep learning and propose a system based on convolutional neural network architecture. As the input to the network, sound files were preprocessed to extract Mel Frequency Cepstral Coefficients (MFCC) using LibROSA library. To train and test the system we have collected 875 animal sound samples from an online sound source site for 10 different animal types. We report classification confusion matrices and the results obtained by different gradient descent optimizers. The best accuracy of 75% was obtained by Nesterov-accelerated Adaptive Moment Estimation (Nadam).

Original languageEnglish
Title of host publicationUBMK 2018 - 3rd International Conference on Computer Science and Engineering
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages625-629
Number of pages5
ISBN (Electronic)9781538678930
DOIs
Publication statusPublished - 6 Dec 2018
Externally publishedYes
Event3rd International Conference on Computer Science and Engineering, UBMK 2018 - Sarajevo, Bosnia and Herzegovina
Duration: 20 Sept 201823 Sept 2018

Publication series

NameUBMK 2018 - 3rd International Conference on Computer Science and Engineering

Conference

Conference3rd International Conference on Computer Science and Engineering, UBMK 2018
Country/TerritoryBosnia and Herzegovina
CitySarajevo
Period20/09/1823/09/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

Keywords

  • Animal sound classification
  • Confusion Matrix (CF)
  • Convolution Neural Network (CNN)
  • Mel Frequency Cepstral Coefficient (MFCC)

Fingerprint

Dive into the research topics of 'Animal Sound Classification Using A Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this