Classification of group-specific variations in songs within House Wren species using machine learning models |
| |
| Affiliation: | 1. Department of Geography, University of Florida, Turlington Hall, 3141, 330 Newell Dr, Gainesville, FL 32611, United States of America;2. Harvard Forest, Harvard University, 324 North Main Street, Petersham, MA 01366-9504, United States of America;1. Nature Coast Biological Station, Institute of Food and Agricultural Sciences, University of Florida, 552 1st St, Cedar Key, FL 32625, USA;2. Fisheries and Aquatic Sciences, Institute of Food and Agricultural Sciences, University of Florida, 136 Newins-Ziegler Hall, Gainesville, FL 32611-0410, USA;3. MERIDIAN, Halifax, Nova Scotia, Canada;4. Dalhousie University, 6299 South St, Halifax, NS B3H 4R2, Canada;5. Department of Biological Sciences, Simon Fraser University, 8888 University Dr W, Burnaby, BC V5A 1S6, Canada;6. Department of Biology, University of Victoria, 3800 Finnerty Road, Victoria, BC V8P 5C2, Canada;7. Instituto Oceanográfico, Universidade de São Paulo, Praça do Oceanográfico, 191 - CEP: 05508-120, Cidade Universitária, São Paulo (SP), Brazil;8. The Fish Listener, Waquoit, MA, USA;9. Soil, Water, and Ecosystem Sciences Department, Institute of Food and Agricultural Sciences, University of Florida, 1692 McCarty Dr, Gainesville, FL 32603, USA;10. Faculty of Computer Science, Dalhousie University, 6050 University Ave, Halifax, NS B3H 1W5, Canada;11. Institute of Computer Science, Polish Academy of Sciences, Jana Kazimierza 5, 01-248 Warszawa, Poland;1. ICAR-Central Marine Fisheries Research Institute, Kochi, Kerala, India;2. Cochin University of Science and Technology, Kochi, Kerala, India;3. Nansen Environmental Research Centre India, Amenity Centre, Kerala University of Fisheries and Ocean Sciences, Kochi, Kerala, India |
| |
| Abstract: | Songbirds have shown variation in vocalizations across different populations and different geographical ranges. Such variations can over time lead to divergence in song characteristics, sometimes referred to as dialects. House Wren (Troglodytes aedon) is one such widely distributed bird species that has shown variation in its song characteristics within different populations. Traditionally, such studies have been conducted using manual approaches for classification. In this work we explore the use of machine learning models that can assist in performing classification of bird songs at a conspecific level. Two machine learning techniques, the random forest and a shallow feed forward neural network, are fed with pre-computed sound features to classify vocal variation in House Wren species across different reported population groups and latitudinal areas. A randomized approach is employed to create balanced subsets of sounds from different locations for repeated classification runs in order to provide a reliable estimate of performance. It is observed that such an automated approach is able to classify variations in songs within House Wren with high accuracy. We were also able to confirm the latitudinal variation of House Wren songs reported in previous studies. Given these results, we believe, such a purely data-driven way of analyzing bird songs in general can provide useful hints to biologists on where to look for interesting patterns in order to understand the evolutionary divergence in song characteristics. |
| |
| Keywords: | Bioacoustics Ornithology Machine learning Machine hearing Bird vocalisations |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
