====== Bioacoustics ====== I like bird songs, sonograms, pattern recognition and machine learning for signal processing and want to learn it. This is my scratchpad to note ideas and links in the hope that I will find some time to follow this path. ===== Data, Experimental Sites ===== === Oregon State Experimental Forest === * [[http://andrewsforest.oregonstate.edu/lter/|HJ Andrews Experimental Forest (Oregon) - Long Term Ecological Research]] * [[http://www.lternet.edu/sites/and|The Long Term Ecological Research Network]] === Xeno-Canto Worldwide Bird Song Acoustic Archive === * http://www.xeno-canto.org/ * e.g. "Wiesenpieper", [[http://www.xeno-canto.org/explore?query=Anthus+pratensis|anthus pratensis]] ===== Research Groups ===== ===== Projects ===== * http://www.amibio-project.eu/en ===== Pattern Recognition Approaches ===== ==== Machine Learning for Signal Processing (MLSP) ==== * MLSP 2013 Bird Classification Challenge: https://www.kaggle.com/c/mlsp-2013-birds * MLSP 2013, Challenge Overview: http://mlsp2013.conwiz.dk/files/mlsp13birdchallenge.pdf * MLSP 2013, Gabor Fodor, der Gewinner. Daten und Software: https://github.com/gaborfodor/MLSP_2013 * MLSP 2013, Gabor Fodor Paper: http://kaggle.a.ssl.fastly.net/blobs/download/forum-message-attachment-files/903/mlsp_2013_beluga.pdf * Machine Learning in Python: http://scikit-learn.org/stable/index.html ===== Equipment ===== * Wildlife Acoustics Songmeter: \\ http://www.wildlifeacoustics.com/products/song-meter-sm3 * Direction Microphone (dish): http://www.telinga.com/ ===== Software ===== * http://openaudio.eu/ * http://sourceforge.net/projects/soundruler/ * http://www.birds.cornell.edu/brp/software * http://www.birds.cornell.edu/brp/raven/RavenOverview.html * http://sourceforge.net/projects/opensmile/ * http://www.audeering.com/research/opensmile * http://sourceforge.net/directory/science-engineering/ai/machinelearning/os:windows/freshness:recently-updated/ * http://sourceforge.net/projects/openart/ ===== Literature ===== Automatic bird sound detection: Applications and tools \\ Ilyas Potamitis (1), Olaf Jahn (2), Klaus Riede (2) \\ 1 Department of Music Technology and Acoustics, Tech. Educ. Institute of Crete, Crete, Greece \\ 2 Zoologisches Forschungsmuseum Alexander Koenig, 53113 Bonn, Germany \\ http://www.amibio-project.eu/sites/default/files/documents/pub/amibio_is12_paper_v7.pdf openSMILE – The Munich Versatile and Fast Open-Source Audio Feature Extractor\\ Florian Eyben (eyben@tum.de), Martin Wöllmer (woellmer@tum.de), Björn Schuller (schuller@tum.de) \\ Institute for Human-Machine Communication, Technische Universität München \\ http://mediatum.ub.tum.de/doc/1082431/5473.pdf