{"type":"ScholarlyArticle","title":"Demo: Enhancing Wildlife Acoustic Data Annotation Efficiency through Transfer and Active Learning","authors":[{"name":"Hannes Kath","slug":"hannes-kath","given":"Hannes","family":"Kath","affiliation":"Interactive Machine Leraning , German Research Center for Artificial Intelligence (DFKI) , Germany; Applied Artificial Intelligence , Carl von Ossietzky University of Oldenburg , Germany"},{"name":"Patricia P. Serafini","slug":"patricia-p-serafini","given":"Patricia P.","family":"Serafini","affiliation":"National Center for Wild Bird Conservation and Research (CEMAVE) , Chico Mendes Institute for Biodiversity Conservation (ICMBio) , Brazil; Universidade Federal de Santa Catarina (UFSC) , Brazil"},{"name":"Ivan B. Campos","slug":"ivan-b-campos","given":"Ivan B.","family":"Campos","affiliation":"National Center for Wild Bird Conservation and Research (CEMAVE) , Chico Mendes Institute for Biodiversity Conservation (ICMBio) , Brazil; Departamento de Biologia Geral , Universidade Federal de Minas Gerais (UFMG) , Brazil"},{"name":"Thiago S. Gouvêa","slug":"thiago-s-gouvea","given":"Thiago","family":"S. Gouvêa","affiliation":"Interactive Machine Leraning , German Research Center for Artificial Intelligence (DFKI) , Germany; Applied Artificial Intelligence , Carl von Ossietzky University of Oldenburg , Germany"},{"name":"Daniel Sonntag","slug":"daniel-sonntag","given":"Daniel","family":"Sonntag","affiliation":"Interactive Machine Leraning , German Research Center for Artificial Intelligence (DFKI) , Germany; Applied Artificial Intelligence , Carl von Ossietzky University of Oldenburg , Germany"}],"abstract":"Passive Acoustic Monitoring (PAM) has become a key technology in wildlife monitoring, generating large amounts of acoustic data. However, the effective application of machine learning methods for sound event detection in PAM datasets is highly dependent on the accessibility of annotated data, a process that can be labour intensive. As a team of domain experts and machine learning researchers, in this paper we present a no-code annotation tool designed for PAM datasets that incorporates transfer learning and active learning strategies to address the data annotation challenge inherent in PAM. Transfer learning is applied to use pre-trained models to compute meaningful embeddings from the PAM audio files. Active learning iteratively identifies the most informative samples and then presents them to the user for annotation. This iterative approach improves the performance of the model compared to random sample selection. In a preliminary evaluation of the tool, a domain expert annotated part of a real PAM data set. Compared to conventional tools, the workflow of the proposed tool showed a speed improvement of 2-4 times. Further enhancements, such as the incorporation of sound examples, have the potential to further improve efficiency.","doi":"10.24963/ijcai.2024/1010","url":"https://ijcai.org/proceedings/2024/1010","pdf":"https://ijcai.org/proceedings/2024/1010.pdf","markdown":"https://ijcai.org/proceedings/2024/1010.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/1010","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Demo Track","track":"Demo Track","number":1010,"pages":{"first":8691,"last":8695},"keywords":["Machine Learning: ML: Few-shot learning","Machine Learning: ML: Applications","Multidisciplinary Topics and Applications: MDA: Computational sustainability","Machine Learning: ML: Active learning","Machine Learning: ML: Classification"],"videos":[],"references":[{"position":1,"raw":"[Cardinale et al., 2012] Bradley J. Cardinale, J. Emmett Duffy, Andrew Gonzalez, David U Hooper, Charles Per- rings, Patrick A. Venail, Anita Narwani, Georgina M. Mace, David Tilman, David A. Wardle, Ann Kinzig, Gretchen C. Daily, Michel Loreau, J. Grace, Anne Lari- gauderie, Diane S. Srivastava, and Shahid Naeem. Biodi- versity loss and its impact on humanity. Nature, 486:59- 67, 2012.","title":"Biodiversity loss and its impact on humanity","authors":"J Bradley, J Emmett Cardinale, Andrew Duffy, David U Gonzalez, Charles Hooper, Patrick A Perrings, Anita Venail, Georgina M Narwani, David Mace, David A Tilman, Ann Wardle, Gretchen C Kinzig, Daily, J Michel Loreau, Anne Grace, Diane S Larigauderie, Shahid Srivastava, Naeem","year":"2012","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cañas et al., 2023] Juan Cañas, María Toro-Gómez, Larissa Sugai, et al. A dataset for benchmarking neotropical anu- ran calls identification in passive acoustic monitoring. Sci- entific Data, 10(1):771, 2023.","title":"A dataset for benchmarking neotropical anuran calls identification in passive acoustic monitoring","authors":"Juan Cañas, María Toro-Gómez, Larissa Sugai","year":"2023","venue":"Scientific Data","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ghani et al., 2023] Burooj Ghani, Tom Denton, Stefan Kahl, and Holger Klinck. Global birdsong embeddings enable superior transfer learning for bioacoustic classifi- cation. Scientific Reports, 13(1):22876, 2023.","title":"Global birdsong embeddings enable superior transfer learning for bioacoustic classification","authors":"Ghani","year":"2023","venue":"Scientific Reports","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gouvêa et al., 2022] Thiago S. Gouvêa, Ilira Troshani, Marc Herrlich, and Daniel Sonntag. Annotating sound events through interactive design of interpretable features. In Stefan Schlobach, María Pérez-Ortiz, and Myrthe Tiel- man, editors, HHAI 2022: Augmenting Human Intel- lect -Proceedings of the First International Conference on Hybrid Human-Artificial Intelligence, Amsterdam, The Netherlands, 13-17 June 2022, volume 354 of Frontiers in Artificial Intelligence and Applications, pages 305-306. IOS Press, 2022.","title":"Annotating sound events through interactive design of interpretable features","authors":"S Thiago, Ilira Gouvêa, Marc Troshani, Daniel Herrlich, Sonntag","year":"2022","venue":"HHAI 2022: Augmenting Human Intellect -Proceedings of the First International Conference on Hybrid Human-Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Gouvêa et al., 2023] Thiago Gouvêa, Hannes Kath, Ilira Troshani, et al. Interactive Machine Learning Solutions for Acoustic Monitoring of Animal Wildlife in Biosphere Re- serves. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pages 6405- 6413, Macau, SAR China, 2023.","title":"Interactive Machine Learning Solutions for Acoustic Monitoring of Animal Wildlife in Biosphere Reserves","authors":"Thiago Gouvêa, Hannes Kath, Ilira Troshani","year":"2023","venue":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2023/711"},{"position":6,"raw":"[IPBES, 2019] IPBES. Summary for policymakers of the global assessment report on biodiversity and ecosystem services. Technical report, Zenodo, November 2019. Ver- sion Number: summary for policy makers.","title":"IPBES. Summary for policymakers of the global assessment report on biodiversity and ecosystem services","authors":null,"year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Kadir et al., 2023] Abdul Kadir, Hasan Alam, and Daniel Sonntag. Edgeal: An edge estimation based active learning approach for oct segmentation. In Medical Image Comput- ing and Computer Assisted Intervention -MICCAI 2023, pages 79-89, 2023.","title":"Edgeal: An edge estimation based active learning approach for oct segmentation","authors":"Abdul Kadir, Hasan Alam, Daniel Sonntag","year":"2023","venue":"Medical Image Computing and Computer Assisted Intervention -MICCAI 2023","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kahl et al., 2021] Stefan Kahl, Connor Wood, Maximilian Eibl, and Holger Klinck. BirdNET: A deep learning solu- tion for avian diversity monitoring. Ecological Informat- ics, 61:101236, 2021.","title":"BirdNET: A deep learning solution for avian diversity monitoring","authors":"Stefan Kahl, Connor Wood, Maximilian Eibl, Holger Klinck","year":"2021","venue":"Ecological Informatics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"4 https://cst.dfki.de/ [Kath et al., 2023] Hannes Kath, Thiago Gouvêa, and Daniel Sonntag. A Human-in-the-Loop Tool for Annotating Pas- sive Acoustic Monitoring Datasets. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pages 7140-7144, Macau, SAR China, 2023.","title":"A Human-in-the-Loop Tool for Annotating Passive Acoustic Monitoring Datasets","authors":"Kath","year":"2023","venue":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","doi":null,"url":"https://cst","internal_url":"/proceedings/2023/835"},{"position":10,"raw":"[Kath et al., 2024a] Hannes Kath, Patricia P. Serafini, Ivan Braga Campos, Thiago S Gouvêa, and Daniel Sonntag. Leveraging Transfer Learning and Active Learning for Sound Event Detection in Passive Acoustic Monitoring of Wildlife. In 3rd Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE), Vancouver, Canada, 2024.","title":"Leveraging Transfer Learning and Active Learning for Sound Event Detection in Passive Acoustic Monitoring of Wildlife","authors":"Kath","year":"2024","venue":"3rd Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kath et al., 2024b] Hannes Kath, Thiago S Gouvêa, and Daniel Sonntag. Active learning in multi-label classifica- tion of bioacoustic data. Under review, 2024.","title":"Active learning in multi-label classification of bioacoustic data","authors":"Kath","year":"2024","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lüers et al., 2024] Bengt Lüers, Patricia P. Serafini, Ivan Braga Campos, Thiago S Gouvêa, and Daniel Son- ntag. BirdNET-Annotator: AI-Assisted Strong Labelling of Bird Sound Datasets. In 3rd Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE), Vancouver, Canada, 2024.","title":"BirdNET-Annotator: AI-Assisted Strong Labelling of Bird Sound Datasets","authors":"Bengt Lüers, Patricia P Serafini, Ivan Braga Campos, Thiago S Gouvêa, Daniel Sonntag","year":"2024","venue":"3rd Annual AAAI Workshop on AI to Accelerate Science and Engineering (AI2ASE)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Michaud et al., 2022] Félix Michaud, Jérôme Sueur, Maxime LE Cesne, and Sylvain Haupert. Unsupervised classification to improve the quality of a bird song recording dataset. ArXiv, abs/2302.07560, 2022.","title":"Unsupervised classification to improve the quality of a bird song recording dataset","authors":"Félix Michaud, Jérôme Sueur, Maxime Le Cesne, Sylvain Haupert","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Perry et al., 2021] Sean Perry, Vaibhav Tiwari, Nishant Bal- aji, Erika Joun, Jacob Ayers, Mathias Tobler, Ian Ingram, Ryan Kastner, and Curt Schurgers. Pyrenote: a web-based, manual annotation tool for passive acoustic monitoring. In IEEE 18th International Conference on Mobile Ad Hoc and Smart Systems, MASS 2021, Denver, CO, USA, Oc- tober 4-7, 2021, pages 633-638. IEEE, 2021.","title":"Pyrenote: a web-based, manual annotation tool for passive acoustic monitoring","authors":"Sean Perry, Vaibhav Tiwari, Nishant Balaji, Erika Joun, Jacob Ayers, Mathias Tobler, Ian Ingram, Ryan Kastner, Curt Schurgers","year":"2021","venue":"IEEE 18th International Conference on Mobile Ad Hoc and Smart Systems, MASS 2021","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ross et al., 2023] Samuel Ross, Darren O'Connell, Jessica Deichmann, et al. Passive acoustic monitoring provides a fresh perspective on fundamental ecological questions. Functional Ecology, 37(4):959-975, 2023.","title":"Passive acoustic monitoring provides a fresh perspective on fundamental ecological questions","authors":"Ross","year":"2023","venue":"Functional Ecology","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Solsona-Berga et al., 2020] Alba Solsona-Berga, Kaitlin E. Frasier, Simone Baumann-Pickering, Sean M. Wiggins, and John A. Hildebrand. Detedit: A graphical user in- terface for annotating and editing events detected in long- term acoustic monitoring data. PLoS Comput. Biol., 16(1), 2020.","title":"Detedit: A graphical user interface for annotating and editing events detected in longterm acoustic monitoring data","authors":"Solsona-Berga","year":"2020","venue":"PLoS Comput. Biol","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sueur et al., 2008] Jérôme Sueur, Sandrine Pavoine, Olivier Hamerlynck, and Stéphanie Duvail. Rapid Acoustic Sur- vey for Biodiversity Appraisal. PLOS ONE, 3(12):e4065, 2008.","title":"Rapid Acoustic Survey for Biodiversity Appraisal","authors":"Jérôme Sueur, Sandrine Pavoine, Olivier Hamerlynck, Stéphanie Duvail","year":"2008","venue":"PLOS ONE","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sugai and Llusia, 2019] Larissa Sugai and Diego Llusia. Bioacoustic time capsules: Using acoustic monitoring to document biodiversity. Ecological Indicators, 99:149- 152, 2019.","title":"Bioacoustic time capsules: Using acoustic monitoring to document biodiversity","authors":"Larissa Sugai, Diego Llusia","year":"2019","venue":"Ecological Indicators","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sugai et al., 2019] Larissa Sugai, Thiago Silva, José Ribeiro, and Diego Llusia. Terrestrial Passive Acoustic Monitoring: Review and Perspectives. BioScience, 69(1):15-25, 2019.","title":"Terrestrial Passive Acoustic Monitoring: Review and Perspectives","authors":"Larissa Sugai, Thiago Silva, José Ribeiro, Diego Llusia","year":"2019","venue":"BioScience","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tkachenko et al., 2020] Maxim Tkachenko, Mikhail Ma- lyuk, Andrey Holmanyuk, and Nikolai Liubimov. Label Studio: Data labeling software, 2020.","title":"Label Studio: Data labeling software","authors":"Tkachenko","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tuia et al., 2022] Devis Tuia, Benjamin Kellenberger, Sara Beery, Blair R. Costelloe, Silvia Zuffi, Benjamin Risse, Alexander Mathis, Mackenzie W. Mathis, Frank van Langevelde, Tilo Burghardt, Roland Kays, Holger Klinck, Martin Wikelski, Iain D. Couzin, Grant van Horn, Mar- garet C. Crofoot, Charles V. Stewart, and Tanya Berger- Wolf. Perspectives in machine learning for wildlife con- servation. Nature Communications, 13(1):792, February 2022. Number: 1 Publisher: Nature Publishing Group.","title":"Perspectives in machine learning for wildlife conservation","authors":"Devis Tuia, Benjamin Kellenberger, Sara Beery, Blair R Costelloe, Silvia Zuffi, Benjamin Risse, Alexander Mathis, Mackenzie W Mathis, Frank Van Langevelde, Tilo Burghardt, Roland Kays, Holger Klinck, Martin Wikelski, Iain D Couzin, Margaret C Grant Van Horn, Charles V Crofoot, Tanya Stewart, Berger-Wolf","year":"2022","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ulloa et al., 2021] Juan Sebastián Ulloa, Sylvain Haupert, Juan Felipe Latorre, Thierry Aubin, and Jérôme Sueur. scikit-maad: An open-source and modular toolbox for quantitative soundscape analysis in Python. Methods in Ecology and Evolution, pages 2041-210X.13711, Septem- ber 2021.","title":"scikit-maad: An open-source and modular toolbox for quantitative soundscape analysis in Python","authors":"Juan Sebastián, Ulloa, Sylvain Haupert, Juan, Felipe Latorre, Thierry Aubin, Jérôme Sueur","year":"2021","venue":"Methods in Ecology and Evolution","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}