Automatic Recognition of Pelung and Canary Bird Sounds Using Machine Learning and Signal Enhancement
DOI:
https://doi.org/10.26418/positron.v15i1.93137Abstract
Bird sound classification is a valuable tool in ecological monitoring and species identification, particularly for non-invasive assessment in natural environments. However, challenges such as limited labeled data and environmental noise often reduce the reliability of classification models. This study presents a lightweight bird sound classification pipeline that integrates signal preprocessing, audio augmentation, and machine learning to address these issues. Two bird species with distinct vocal characteristics, Pelung (a crossbreed involving Bangkok chickens) and Canary (Serinus canaria), were used as case subjects. A total of 40 original 2-second audio clips were extracted from longer field recordings, then processed through frame-based energy attenuation, bandpass filtering (1"“8 kHz), and RMS normalization. Ten augmentation techniques were applied to each original file to improve generalization, generating 400 augmented files for model training. Feature extraction was performed using 13-dimensional Mel Frequency Cepstral Coefficients (MFCCs), and Principal Component Analysis (PCA) was used to visualize the effect of filtering. Classification was conducted using a Support Vector Machine (SVM) with a radial basis function (RBF) kernel. Results showed that filtering improved classification accuracy from 90% to 95% on the original data. Furthermore, using only augmented data for training and original data for testing yielded 100% classification accuracy, demonstrating excellent generalization. This study highlights the effectiveness of combining adaptive preprocessing and augmentation for reliable bird sound classification under limited and noisy conditions.References
40% of World’s Birds Are in Decline. In: https://www.allaboutbirds.org/news/2018-global-report-40-of-worlds-birds-are-in-decline/ (accessed 06 May 2025)
Blake J. G., Loiselle B.A., Sharp declines in observation and capture rates of Amazon birds in absence of human disturbance., Glob Ecol Conserv, Vol. 51, article e02902, 2024. https://doi.org/10.1016/j.gecco.2024.e02902
Dunn E. H., Bart J., Collins B. T., et al. Monitoring bird populations in small geographic areas. Occasional Paper of the Canadian Wildlife Service. SPEC. ISS., pp 1-59., 2006.https://pubs.usgs.gov/publication/70030252
Mariyappan M., Rajendran M., Velu S. et al., Ecological Role and Ecosystem Services of Birds: A Review. International Journal of Environment and Climate Change, Vol 13 (6), pp. 76–87., 2023 https://doi.org/10.9734/ijecc/2023/v13i61800
Neate-Clegg M. H. C., Horns J. J., Adler F. R., et al., Monitoring the world’s bird populations with community science data. Biol Conserv, Vol 248, article 108653, 2020. https://doi.org/10.1016/j.biocon.2020.108653
Ducrettet M., Forget P. M., Ulloa J. S., et al., Monitoring canopy bird activity in disturbed landscapes with automatic recorders: A case study in the tropics. Biol Conserv, Vol 245, article 108574, 2020. https://doi.org/10.1016/j.biocon.2020.108574
Penar W., Magiera A., Klocek C,. Applications of bioacoustics in animal ecology. Ecological Complexity, Vol 43, article 100847, 2020. https://doi.org/10.1016/j.ecocom.2020.100847
Teixeira D., Maron M., van Rensburg B. J. Bioacoustic monitoring of animal vocal behavior for conservation. Conserv Science and Practice, Vol 1 (8), article e72., 2019, https://doi.org/10.1111/csp2.72
Zhang C., Zhang Y., Zheng X., et al., Influence of recording devices and environmental noise on acoustic index scores: Implications for bird sound-based assessments. Ecological Indicators, Vol. 159, article 111759, 2024 https://doi.org/10.1016/j.ecolind.2024.111759
RÃos-Chelén A. A., McDonald A. N., Berger A., et al., Do birds vocalize at higher pitch in noise, or is it a matter of measurement? Behavioral Ecology and Sociobiology Vol 71, article 29, 2017, https://doi.org/10.1007/s00265-016-2243-7
Quinn C. A., Burns P., Gill G., et al., Soundscape classification with convolutional neural networks reveals temporal and geographic patterns in ecoacoustic data. Ecological Indicators Vol. 138, article 108831, 2022, https://doi.org/10.1016/j.ecolind.2022.108831
Wei Y. C., Chen W. L., Tuanmu M. N., et al., Advanced montane bird monitoring using self-supervised learning and transformer on passive acoustic data. Ecological Informatics Vol. 84, article 102927, 2024, https://doi.org/10.1016/j.ecoinf.2024.102927
Stowell D., Plumbley M. D., Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning. PeerJ, article e488, 2014:. https://doi.org/10.7717/peerj.488
Incze A, Jancso H-B, Szil Z, et al. Bird Sound Recognition Using a Convolutional Neural Network. 2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY), Subotica, Serbia, 2018, pp. 000295-000300, doi: https://10.1109/SISY.2018.8524677
Salamon J., Jacoby C., Bello J. P., A dataset and taxonomy for urban sound research. In Proceedings of the 22nd ACM international conference on Multimedia (MM '14). Association for Computing Machinery, New York, NY, USA, pp. 1041–1044, 2014 https://doi.org/10.1145/2647868.2655045.
Himawan I., Towsey M., Roe P., 3D Convolutional Recurrent Neural Networks For Bird Sound Detection. In: Workshop on Detection and Classification of Acoustic Scenes and Events, 2018, https://dcase.community/documents/challenge2018/technical_reports/DCASE2018_Himawan_45.pdf
Clark M. L., Salas L., Baligar S., et al. The effect of soundscape composition on bird vocalization classification in a citizen science biodiversity monitoring project. Ecological Informatics Vol 75, article 102065, 2023, https://doi.org/10.1016/j.ecoinf.2023.102065
Zhang S., Gao Y., Cai J., et al., A Novel Bird Sound Recognition Method Based on Multifeature Fusion and a Transformer Encoder., Sensors, 23 (19), article 8099, 2023, https://doi.org/10.3390/s23198099
Sevilla A., Glotin H. Audio Bird Classification with Inception-v4 extended with Time and Time-Frequency Attention Mechanisms., Conference and Labs of the Evaluation Forum, Vol 1866, article 177, 2017, https://doi.org/https://ceur-ws.org/Vol-1866/paper_177.pdf
Asmara I. Y., Garnida D., Partasasmita R. (2020) Short communication: Duration and volume of crowing of pelung chickens of West Java, Indonesia., Biodiversitas, Vol 21 (2), pp. 748–752, 2020, https://smujo.id/biodiv/article/view/5127
Fishbein A. R., Lawson S. L., Dooling R. J., Ball G. F. How canaries listen to their song: Species-specific shape of auditory perception. The Journal of the Acoustical Society of America Vol 145, pp. 562–574, 2019, https://doi.org/10.1121/1.5087692
The Basics of Sound for Birders. In: https://paulcohen.se/odds-and-ends/the-basics-of-sound-for-birders/. https://paulcohen.se/odds-and-ends/the-basics-of-sound-for-birders/. Accessed 23 May 2025
Molau S., Pitz M., Schliitel R., Ney H., Computing Mel-Frequency Cepstral Coefficients On The Power Spectrum. 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing Proceedings (Cat No01CH37221)., article 940770, 2001, https://doi.org/DOI:10.1109/ICASSP.2001.940770
Joshi S., Parandkar P., A Review of Feature Extraction Technique for Automatic Speech Recognition. International Journal of Science and Research, Vol 4 (2), article 335274. https://journals.indexcopernicus.com/api/file/viewByFileId/335274.pdf
Ganchev T., Fakotakis N., Kokkinakis G. Comparative Evaluation of Various MFCC Implementations on the Speaker Verification Task, In Proc. of the SPECOM2005, pp. 191–194. https://doi.org/https://api.semanticscholar.org/CorpusID:18140609
Shlens J (2014) A Tutorial on Principal Component Analysis. ArXiv 1–13. https://doi.org/10.1.1.115.3503
Downloads
Published
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
This work is licensed under a Creative Commons Attribution 4.0 International License.
