ABSTRACT
This paper deals with techniques for automatic recognition of bird species based on audio recordings of their sounds. Perceptual features, Mel-frequency cepstral coefficients are extracted from the sound files. For dimensionality reduction Mean computation, Principal Component Analysis and Vector Quantization is used and compared. Classification is carried out using k-nearest neighbour classifier. In our experiment, classification accuracy of 82% is achieved for the classification of ten bird species.
- T. Brandes. 2008. Automated sound recording and analysis techniques for bird surveys and conservation. Bird Conservation International, 18, 163--173 Google ScholarCross Ref
- C. Lee and C. Han. 2008. Automatic classification of bird species from their sounds using two-dimensional cepstral coefficients, IEEE Transactions on speech and Audio Processing, Vol. 16, Issue 8, 1541--1550 Google ScholarDigital Library
- A. Kumar. 2003. Acoustic communication in birds, differences in songs and calls, their production and biological significance. Resonance, 44--54 H. Kim, N. Moreau and T. Sikora. 2004. Audio Classification based onGoogle Scholar
- MPEG-7 Spectral Basis Representations. IEEE Transactions. on Circuits and Systems for Video Technology. Vol. 14, Issue 5, 716--724Google Scholar
- E. Wold, T. Blum, D. Keislar, and J. Wheaton. 1996. Content-Based Classification, Search, and Retrieval of Audio. IEEE MultiMedia, 27--36. DOI:http://dx.doi.org/10.1109/93.556537 Google ScholarDigital Library
- P. Dhanalaxmi, S. Palanivel and V. Ramalingam. 2008. Classification of Audio Signals using SVM and RBFNN. Expert System with Applications, vol. 36, Issue 3, 6069--6075. DOI:10.1016/j.eswa.2008.06.126 Google ScholarDigital Library
- P. Somervuo, A. Harma and S. Fagurland. 2006. Parametric representations of bird sounds for automatic species recognition. IEEE Transactions on Audio, Speech and Language Processing, 14(6), 2252--2263 Google ScholarDigital Library
- S. Anderson, A. Dave and D. Margoliash. 1996. Template-based automatic recognition of birdsong syllables from continuous recordings. J. Acoust. Soc. Amer., Vol. 100, No. 2, 1209--1219 Google ScholarCross Ref
- J. Kogan and D. Margoliash. 1998. Automated recognition of bird song elements from continuous recordings using dynamic time warping and hidden Markov models: A comparative study. J. Acoust. Soc. Amer., Vol. 103, No. 4, 2187--2196 Google ScholarCross Ref
- E. Vilches, I. Escobar, E. Vallejo and C. Taylor. 2006. Data mining applied to acoustic bird species recognition. In Proc. of the 18th International Conference on Pattern Recognition. DOI: 0-7695-2521-0/06 Google ScholarDigital Library
- A. Härmä and P. Somervuo. 2004. Classification of the harmonic structure in bird vocalization. In Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Vol. 5, 701--704Google Scholar
- A. Selin, J. Turunen, and J. Tanttu 2007. Wavelets in recognition of bird sounds. EURASIP Journal on Advances in Signal Processing, 9 pagesGoogle Scholar
- A. Bang and P. Rege. 2014. Classification of Bird Species based on Bioacoustics International Journal of Advances in Computer Science and its Applications, Vol 4, Issue 1, 184--188Google Scholar
- M. Lopes, A. Koerich, C. Cilla and C. Kaestner. 2011. Feature set comparison for automatic bird species identification. Proc. of IEEE International Conference on System, Man, Cybern., Anchorage, 965--970 Google ScholarCross Ref
- M. Acevedo, C. Bravo, H. Bravo, L. Rivera and T. Aide. 2009. Automated classification of bird and amphibian calls using machine learning: A comparison of methods. Ecological Informatics, Vol. 4, 206--214 Google ScholarCross Ref
- K. Qian, Z. Zhang, A. Baird, F. Ringeval, and B. Schuller. 2015. Bird Sounds Classification by Large Scale Acoustic Features and Extreme Machine Learning. Proc. of GlobalSIP, Orlando, Florida, USA, 1317--1321. DOI:10.1109/GlobalSIP.2015.7418412 Google ScholarCross Ref
- K. Qian, Z. Zhang, A Baird, and B. Schuller. 2017. Active Learning for Bird Sounds Classification. J. of ActaAcustica United with Acustica, 361--364. DOI 10.3813/AAA.919064Google Scholar
- D. Stowell, L. Gill, and D. Clayton. 2016. Detailed temporal structure of communication networks in groups of songbirds. J. R. Soc. Interface 13: 20160296. DOI: http://dx.doi.org/10.1098/rsif.2016.0296 Google ScholarCross Ref
- D. Stowell, E. Benetos, and L. Gill. 2017. On-Bird Sound Recordings: Automatic Acoustic Recognition of Activities and Contexts. ACM Transactions on Audio, Speech, and Language Processing. Vol. 25, Issue 6, 1193--1206 Google ScholarDigital Library
- Xeno-canto. URL: www.zeno-canto.orgGoogle Scholar
- S. Boll. 1979. Suppression of acoustic noise in speech using spectral subtraction. IEEE Transactions Acoustics Speech Signal Processing, Vol. 27, 113--120 Google ScholarCross Ref
- L. Rabiner, B. Juang and B. Yegnanarayana. Fundamentals of Speech Recognition. Pearson Education. Chapter 3 & 4Google Scholar
- R. Duda, P. Hart and D. Stork, Pattern Classification. (2nded.). Wiley Publication. Chapter 3 and 4Google Scholar
- J. Shlens. 2009. A Tutorial on Principal Component AnalysisGoogle Scholar
- Y. Linde, A. Buzo and R. Gray. 1980. An algorithm for Vector Quantizer Design. IEEE Transactions on Communications, Vol.1, 84--95 Google ScholarCross Ref
Index Terms
- Recognition of Bird Species from their Sounds using Data Reduction Techniques
Recommendations
Bird Species Recognition Using Unsupervised Modeling of Individual Vocalization Elements
This paper investigates acoustic modeling for recognition of bird species from audio field recordings. First, the acoustic scene is decomposed into isolated segments, corresponding to detected sinusoids. Each segment is represented by a sequence of the ...
Bird species recognition using support vector machines
Automatic identification of bird species by their vocalization is studied in this paper. Bird sounds are represented with two different parametric representations: (i) the mel-cepstrum parameters and (ii) a set of low-level signal parameters, both of ...
Automatic bird species recognition based on birds vocalization
This paper deals with a project of Automatic Bird Species Recognition Based on Bird Vocalization. Eighteen bird species of 6 different families were analyzed. At first, human factor cepstral coefficients representing the given signal were calculated ...
Comments