Automatic identification of bird species: A comparison between kNN and SOM classifiers

This paper presents a system for automatic bird identification, which uses audio input. The experiments have been conducted on three groups of birds, which were created basing finishing on classification, the system is fully automated. The main problem in automatic bird recognition (ABR) is the choice of proper features and classifiers. Identification has been made using two classifiers-kNN (k Nearest Neighbor) and SOM (Self Organizing Maps). System has been tested using data extracted from natural environment.

[1]  Xiaoli Z. Fern,et al.  Audio Classification of Bird Species: A Statistical Manifold Approach , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[2]  Aki Härmä.  Automatic identification of bird species based on sinusoidal modeling of syllables , 2003, ICASSP.

[3]  Chih-Hsun Chou,et al.  On the Studies of Syllable Segmentation and Improving MFCCs for Automatic Birdsong Recognition , 2008, 2008 IEEE Asia-Pacific Services Computing Conference.

[4]  S.-A. Selouani,et al.  Automatic birdsong recognition based on autoregressive time-delay neural networks , 2005, 2005 ICSC Congress on Computational Intelligence Methods and Applications.

[5]  Xiaoli Z. Fern,et al.  A Syllable-Level Probabilistic Framework for Bird Species Identification , 2009, 2009 International Conference on Machine Learning and Applications.

[6]  E. D. Chesmore,et al.  Application of time domain signal coding and artificial neural networks to passive acoustical identification of animals , 2001 .

[7]  D. Niewiadomy,et al.  Implementation of MFCC vector generation in classification context , 2008 .

[8]  T. S. Brandes,et al.  Feature Vector Selection and Use With Hidden Markov Models to Identify Frequency-Modulated Bioacoustic Signals Amidst Noise , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[9]  Jinhai Cai,et al.  Sensor Network for the Monitoring of Ecosystem: Bird Species Recognition , 2007, 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information.

[10]  Renate Sitte,et al.  Comparison of techniques for environmental sound recognition , 2003, Pattern Recognit. Lett..

[11]  Chang-Hsing Lee,et al.  Bird Species Recognition by Comparing the HMMs of the Syllables , 2007, Second International Conference on Innovative Computing, Informatio and Control (ICICIC 2007).

[12]  Panu Somervuo,et al.  Analyzing Bird Song Syllables on the Self-Organizing Map , 2003 .

[13]  H. C. Card,et al.  A comparison of backpropagation and statistical classifiers for bird identification , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[14]  Charles E. Taylor,et al.  Targeting Input Data for Acoustic Bird Species Recognition Using Data Mining and HMMs , 2007, Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007).