Evaluation of a Sparse Representation-Based Classifier For Bird Phrase Classification Under Limited Data Conditions

This paper evaluates the performance of a sparse representation-based (SR) classifier for a limited data, bird phrase classification task. The evaluation database contains 32 unique phrases segmented from songs of the Cassin’s Vireo (Vireo cassinii). Spectrographic features were extracted from each phrase-segmented audio file, followed by dimension reduction using principal component analysis (PCA). A performance comparison to the nearest subspace (NS) and support vector machine (SVM) classifiers was conducted. The SR classifier outperforms the NS and SVM classifiers, with a maximum absolute improvement of 3.4% observed when there are only four tokens per phrase in the training set.

[1]  Q. Mcnemar.  Note on the sampling error of the difference between correlated proportions or percentages , 1947, Psychometrika.

[2]  P. Slater,et al.  Bird Song: Biological Themes and Variations , 1995 .

[3]  Jorma T. Laaksonen.  Subspace Classifiers in Recognition of Handwritten Digits , 1997 .

[4]  J A Kogan,et al.  Automated recognition of bird song elements from continuous recordings using dynamic time warping and hidden Markov models: a comparative study. , 1998, The Journal of the Acoustical Society of America.

[5]  Bo Zhang,et al.  Support vector machine learning for image retrieval , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[6]  Christopher B. Goguen,et al.  Cassin's Vireo (Vireo cassinii) , 2002 .

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

[8]  Panu Somervuo,et al.  Bird song recognition based on syllable pair histograms , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[9]  J. M. Jenkins,et al.  The appropriate use of Zipf's law in animal communication studies , 2005, Animal Behaviour.

[10]  E. Candes,et al.  11-magic : Recovery of sparse signals via convex programming , 2005 .

[11]  Zhixin Chen,et al.  Semi-automatic classification of bird vocalizations using spectral peak tracks. , 2006, The Journal of the Acoustical Society of America.

[12]  Allen Y. Yang,et al.  Feature Selection in Face Recognition: A Sparse Representation Perspective , 2007 .

[13]  Charles E Taylor,et al.  Automated species recognition of antbirds in a Mexican rainforest using hidden Markov models. , 2008, The Journal of the Acoustical Society of America.

[14]  Louis Ranjard,et al.  Unsupervised bird song syllable classification using evolving neural networks. , 2008, The Journal of the Acoustical Society of America.

[15]  T. Scott Brandes,et al.  Automated sound recording and analysis techniques for bird surveys and conservation , 2008, Bird Conservation International.

[16]  Héctor Corrada Bravo,et al.  Automated classification of bird and amphibian calls using machine learning: A comparison of methods , 2009, Ecol. Informatics.

[17]  Charles E. Taylor,et al.  Territorial dynamics of Mexican Ant‐thrushes Formicarius moniliger revealed by individual recognition of their songs , 2011 .

[18]  D. Mennill.  Individual distinctiveness in avian vocalizations and the spatial monitoring of behaviour , 2011 .

[19]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[20]  Wei Chu,et al.  Noise robust bird song detection using syllable pattern-based hidden Markov models , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[21]  Luis J. Villanueva-Rivera,et al.  Soundscape Ecology: The Science of Sound in the Landscape , 2011 .

[22]  Charles E. Taylor,et al.  Structural Design Principles of Complex Bird Songs: A Network-Based Approach , 2012, PloS one.