LifeCLEF Bird Identification Task 2017

The LifeCLEF challenge BirdCLEF offers a large-scale proving ground for system-oriented evaluation of bird species identification based on audio recordings of their sounds. One of its strengths is that it uses data collected through Xeno-canto, the worldwide community of bird sound recordists. This ensures that BirdCLEF is close to the conditions of real-world application, in particular with regard to the number of species in the training set (1500). The main novelty of the 2017 edition of BirdCLEF was the inclusion of soundscape recordings containing time-coded bird species annotations in addition to the usual Xeno-canto recordings that focus on a single foreground species. This paper reports an overview of the systems developed by the five participating research groups, the methodology of the evaluation of their performance, and an analysis and discussion of the results obtained.

[1]  Thomas Lidy,et al.  A Multi-modal Deep Neural Network approach to Bird-song Identication , 2017, CLEF.

[2]  Björn Schuller,et al.  Opensmile: the munich versatile and fast open-source audio feature extractor , 2010, ACM Multimedia.

[3]  M. O'Neill,et al.  Automated species identification: why not? , 2004, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[4]  Paul Roe,et al.  A toolbox for animal call recognition , 2012 .

[5]  Dan Stowell,et al.  Automatic large-scale classification of bird sounds is strongly improved by unsupervised feature learning , 2014, PeerJ.

[6]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[7]  Olivier Buisson,et al.  Instance-based bird species identication with undiscriminant features pruning - LifeCLEF 2014 , 2014 .

[8]  Mario Lasseck,et al.  Improved Automatic Bird Identification through Decision Tree based Feature Selection and Bagging , 2015, CLEF.

[9]  Thomas Hofmann,et al.  Audio Based Bird Species Identification using Deep Learning Techniques , 2016, CLEF.

[10]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Dan Stowell,et al.  Audio-only Bird Classification Using Unsupervised Feature Learning , 2014, CLEF.

[12]  Hervé Glotin,et al.  Audio Bird Classification with Inception-v4 extended with Time and Time-Frequency Attention Mechanisms , 2017, CLEF.

[13]  Joakim Andén,et al.  Multiscale Scattering for Audio Classification , 2011, ISMIR.

[14]  P. Raven,et al.  Taxonomy: Impediment or Expedient? , 2004, Science.

[15]  Serguei A. Mokhov.  Study of best algorithm combinations for speech processing tasks in machine learning using median vs. mean clusters in MARF , 2008, C3S2E '08.

[16]  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.

[17]  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.

[18]  Iván V. Meza,et al.  SVM Candidates and Sparse Representation for Bird Identification , 2014, CLEF.

[19]  Tran Huy Dat,et al.  Bird Classification using Ensemble Classifiers , 2014, CLEF.

[20]  Grigorios Tsoumakas,et al.  The 9th annual MLSP competition: New methods for acoustic classification of multiple simultaneous bird species in a noisy environment , 2013, 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP).

[21]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.

[22]  Tran Huy Dat,et al.  Bird Classication using Ensemble Classiers , 2014 .

[23]  Sven Koitka,et al.  Recognizing Bird Species in Audio Files Using Transfer Learning , 2017, CLEF.

[24]  Dan Stowell.  BirdCLEF 2015 Submission: Unsupervised Feature Learning from Audio , 2015, CLEF.

[25]  Itheri Yahiaoui,et al.  Interactive plant identification based on social image data , 2014, Ecol. Informatics.

[26]  Frans Wiering,et al.  A Deep Neural Network Approach to the LifeCLEF 2014 Bird Task , 2014, CLEF.

[27]  Stefan Kahl,et al.  Large-Scale Bird Sound Classification using Convolutional Neural Networks , 2017, CLEF.

[28]  Hervé Glotin,et al.  LifeCLEF 2014: Multimedia Life Species Identification Challenges , 2014, CLEF.

[29]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[30]  Mario Lasseck.  Large-scale Identification of Birds in Audio Recordings , 2014, CLEF.

[31]  Robert B. Fisher,et al.  Overview of the LifeCLEF 2014 Fish Task , 2014, CLEF.

[32]  Dah-Jye Lee,et al.  Contour matching for a fish recognition and migration-monitoring system , 2004, SPIE Optics East.

[33]  Alex A. Freitas,et al.  A survey of hierarchical classification across different application domains , 2010, Data Mining and Knowledge Discovery.

[34]  Xiaoli Z. Fern,et al.  Acoustic classification of multiple simultaneous bird species: a multi-instance multi-label approach. , 2012, The Journal of the Acoustical Society of America.

[35]  Hervé Glotin,et al.  Clusterized Mel Filter Cepstral Coefficients and Support Vector Machines for Bird Song Identification , 2014 .

[36]  Olivier Buisson,et al.  Shared Nearest Neighbors Match Kernel for Bird Songs Identification - LifeCLEF 2015 Challenge , 2015, CLEF.

[37]  Li WangDong-Chen He,et al.  Texture classification using texture spectrum , 1990, Pattern Recognit..

[38]  Serguei A. Mokhov.  A MARFCLEF Approach to LifeCLEF 2015 Tasks , 2015, CLEF.