Open Access
Subscription or Fee Access
Sound-based Bird Classification Using Perceptual Features and Machine Learning: A Gaussian Mixture Model
Abstract
Classification of birds based on their sound patterns and identification of bird species found in the chirping sounds of birds were experimented with using the feature extraction method. This work is beneficial in ornithology to study birds and their behavior based on their sounds. The proposed methods can automatically classify birds by different sound processing. The audio file of a bird’s sound recording is first cut into smaller samples, and then the Fourier transform is utilized to analyze the frequencies in each instance. Features are extracted through the Perceptual Linear Prediction Cepstral Coefficients method, which can identify specific characteristics unique to each bird species. The clustering process is done using the Gaussian Mixture Model employed here to classify the birds into the respective classes; the last method is applying the testing procedure. It has been done to test our model’s accuracy in categorizing the various birds by their sounds. This work on the classification of birds using respective sounds has provided high accuracy for most birds, and the overall accuracy is 92%.
References
Scott Brandes TS. Automated sound recording and analysis techniques for bird surveys and conservation. Bird Conserv Int. 2008; 18 (Suppl 1): S163–S173. doi: 10.1017/S09592709080
Fagerlund S, Laine UK. New parametric representations of bird sounds for automatic classification. Proceeding of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP); 2014 May 04–09; Florence, Italy: IEEE; 2014. 8247–8251 pp. doi: 10.1109/ICASSP.
6855209.
Lee CH, Han CC, Chuang CC. Automatic classification of bird species from their sounds using two-dimensional cepstral coefficients. IEEE Trans Aud Speech Lang Process. 2008; 16 (8): 1541–1550. doi: 10.1109/TASL.2008.2005345.
Raghuram MA, Chavan NR, Belur R, Koolagudi SG. Bird classification based on their sound patterns. Int J Speech Technol. 2016; 19 (4): 791–804. doi: 10.1007/s10772-016-9372-2.
Ramashini M, Abas PE, Grafe U, De Silva LC. Bird sounds classification using linear discriminant analysis. Proceeding of the 4th International Conference and Workshops on Recent Advances and Innovations in Engineering (ICRAIE); 2019 November 27–29; Kedah, Malaysia: IEEE; 2019. 1–6 pp. doi: 10.1109/ICRAIE47735.2019.9037645.
Selin A, Turunen J, Tanttu JT. Wavelets in recognition of bird sounds. EURASIP J Adv Signal Process. 2006; 2007 (1): 1–9. doi: 10.1155/2007/51806.
Stowell D, Plumbley MD. Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning. PeerJ. 2014; 2: e488. doi: 10.7717/peerj.488, PMID 25083350.
Tuncer T, Akbal E, Dogan S. Multileveled ternary pattern and iterative ReliefF based bird sound classification. Appl Acoust. 2021; 176: 107866. doi: 10.1016/j.apacoust.2020.107866.
Xie J, Hu K, Zhu M, Yu J, Zhu Q. Investigation of different CNN-based models for improved bird sound classification. IEEE Access. 2019; 7: 175353–175361. doi: 10.1109/ACCESS.2019.
Sprengel E, Jaggi M, Kilcher Y, Hofmann T. (2016). Audio based bird species identification using deep learning techniques. [Online] Available at https://ceur-ws.org/Vol-1609/16090547.pdf]
Koh CY, Chang JY, Tai CL, Huang DY, Hsieh HH, Liu YW. (2019). Bird sound classification using convolutional neural networks. [Online] Available at https://ceur-ws.org/Vol-2380/
paper_68.pdf
Madhavi A, Pamnani R. Deep learning based audio classifier for bird species. J Sci Res. 2018; 3: 228–233.
Mehyadin AE, Abdulazeez AM, Hasan DA, Saeed JN. Birds sound classification based on machine learning algorithms. Asian J Res Comput Sci. 2021; 9: 68530.
Incze A, Jancsó HB, Szilágyi Z, Farkas A, Sulyok C. Bird sound recognition using a convolutional neural network. Proceedings of the 16th International Symposium on Intelligent Systems and Informatics (SISY); 2018 September 13–15; Subotica, Serbia: IEEE Publications. 2018. 295–300 pp. doi: 10.1109/SISY.2018.8524677.
Aggarwal S, Sehgal S. Classification of bird Species using Audio processing and Deep Neural Network. Proceedings of the Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT); 2022 August 11–12; Kannur, India: IEEE Publications; 2022. 138–143 pp. doi: 10.1109/ICICICT54557.2022.9917735.
Gupta G, Kshirsagar M, Zhong M, Gholami S, Ferres JL. Comparing recurrent convolutional neural networks for large scale bird species classification. Sci Rep. 2021; 11 (1): 17085. doi: 10.1038/s41598-021-96446-w, PMID 34429468.
Permana SDH, Saputra G, Arifitama B, Yaddarabullah W, Caesarendra W, Rahim R. Classification of bird sounds as an early warning method of forest fires using Convolutional Neural Network (CNN) algorithm. J King Saud Univ Comput Inf Sci. 2022; 34 (7): 4345–4357. doi: 10.1016/j.jksuci.2021.04.013.
Hasan NI. (2022). Bird species classification and acoustic features selection based on distributed neural network with two stage windowing of short-term features. [Online] Available at https://arxiv.org/abs/2201.00124
Qian K, Zhang Z, Baird A, Schuller B. Active learning for bird sound classification via a kernel-based extreme learning machine. J Acoust Soc Am. 2017; 142 (4): 1796. doi: 10.1121/1.5004570, PMID 29092546.
Eichinski P, Alexander C, Roe P, Parsons S, Fuller S. A convolutional neural network bird species recognizer built from little data by iteratively training, detecting, and labeling. Front Ecol Evol. 2022; 10. doi: 10.3389/fevo.2022.810330.
Revathi A, Sasikaladevi N, Nagakrishnan R, Jeyalakshmi C. Robust emotion recognition from speech: gamma tone features and models. Int J Speech Technol. 2018; 21 (3): 723–739. doi: 10.1007/s10772-018-9546-1.
Arunachalam R. A strategic approach to recognize the speech of the children with hearing impairment: different sets of features and models. Multimedia Tool Appl. 2019; 78 (15): 20787–20808. doi: 10.1007/s11042-019-7329-6.
Srikanth MR, Murthy HA. Discriminative training of Gaussian mixture speaker models: A new approach. Proceedings of the National Conference on Communications (NCC); 2010 January 29–31; Chennai, India: IEEE; 2010. 1–5 pp. doi: 10.1109/NCC.2010.5430204.
Refbacks
- There are currently no refbacks.