Bird Call Identification-Reference-Cited by-同舟云学术

Bird Call Identification

Published:2024-05-10 Issue: Volume: Page:
ISSN:
Container-title:
language:
Short-container-title:

Author:

Singh Parvinder¹,Mulyan Muskan¹

Affiliation:

1. Deenbandhu Chhotu Ram University of Science and Technology

Abstract

The paper purposes an approach identify the bird species given their chirping sounds. The paper proposes Convolutional Neural Network architecture for classifying the species. In our proposed approach, we first convert the audio files to Mel spectrogram and use them for classification. We built a CNN model with three Convolutional layers, and then tuned parameters like number of epochs, learning rate, dropout percentage and size of convolutional matrix. The training dataset consists of 1485 audio clips containing 40 distinct species found across South Africa. The designed set of model achieved accuracy in the range of 32–52% on the test dataset.

Publisher

Research Square Platform LLC

Reference18 articles.

1. Investigation of Different CNN-Based Models for Improved Bird Sound Classification;Jie X;IEEE Access,2019

2. Identifying bird species by their calls in Soundscapes;Maclean K;Springer Appl Intell,2023

3. Weerasena H, Manesh J, Dineth E, Heshan F, Sulochana S. C. G. and e. al, Continuous Automatic Bioacoustics Monitoring of Bird Calls with Local Processing on Node Level, TENCON 2018–2018 IEEE Region 10 Conference, pp. 0235–0239, 2018.

4. Höchst J, Bellafkir H, Lampe P, Vogelbacher M, Mühling M, Schneider D. and e. al, Bird@Edge: Bird Species Recognition at the Edge, Springer International Conference on Networked Systems, vol. 13464, pp. 69–86, 2022.

5. Shivam M, Ghatak R, Singh VK, Singh SK, Mahato A. Bird Call Recognition using Acoustic based Feature Selection approach in Machine Learning, IEEE International Conference on Multimedia and Expo (ICME), pp. 1–5, 2013.