AnuraSet: A dataset for benchmarking neotropical anuran calls identification in passive acoustic monitoring
Creators
-
Cañas, Juan Sebastián1
-
Toro Gómez, Maria Paula1
-
Moreira Sugai, Larissa Sayuri2
-
Benítez Restrepo, Hernán Darío3
-
Rudas, Jorge1
-
Posso Bautista, Breyner1
-
Toledo, Luis Felipe4
-
Dena, Simone5
-
De Souza, Franco Leandro6
-
De Oliveira, Selvino Neckel7
- Da Rosa, Anderson7
-
Carvalho-Rocha, Vítor7
-
Bernardy, José Vinícius8
-
Massao Moreira Sugai , José Luiz8
-
dos Santos, Carolina Emília8
-
Pereira Bastos, Rogério8
-
Llusia, Diego9
-
Ulloa, Juan Sebastián1
- 1. Instituto de Investigación de Recursos Biológicos Alexander von Humboldt, Avenida Paseo Bolívar 16-20, Bogotá, Colombia
- 2. K. Lisa Yang Center for Conservation Bioacoustics, Cornell Lab of Ornithology, Cornell University, 159 Sapsucker woods road, 14850, Ithaca, New York, USA
- 3. Pontificia Universidad Javeriana Seccional Cali, Calle 18 No 118-250, Cali, Valle del Cauca, Colombia.
- 4. Universidade Estadual de Campinas: Campinas, SP, BR
- 5. University of Campinas: Campinas, São Paulo, BR
- 6. Universidade Federal de Mato Grosso do Sul
- 7. Universidade Federal de Santa Catarina: Florianópolis, SC, BR
- 8. Universidade Federal de Goiás: Goiania, GO, BR
- 9. Terrestrial Ecology Group, Departamento de Ecología, Universidad Autónoma de Madrid, C/ Darwin, 2, Ciudad Universitaria de Cantoblanco, Facultad de Ciencias, Edificio de Biología, 28049 Madrid, Spain
Description
Global change is predicted to induce shifts in anuran acoustic behavior, which can be studied through passive acoustic monitoring (PAM). Understanding changes in calling behavior requires the identification of anuran species, which is challenging due to the particular characteristics of neotropical soundscapes. In this paper, we introduce a large-scale multi-species dataset of anuran amphibians calls recorded by PAM, that comprises 27 hours of expert annotations for 42 different species from two Brazilian biomes. We provide open access to the dataset, including the raw recordings, experimental setup code, and a benchmark with a baseline model of the fine-grained categorization problem. Additionally, we highlight the challenges of the dataset to encourage machine learning researchers to solve the problem of anuran call identification towards conservation policy. All our experiments and resources can be found on our GitHub repository https://github.com/soundclim/anuraset.