{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:57:49Z","timestamp":1780930669867,"version":"3.54.1"},"reference-count":94,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006360","name":"Bundesministerium f\u00fcr Wirtschaft und Klimaschutz","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006360","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Ecological Informatics"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.ecoinf.2026.103765","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T16:10:47Z","timestamp":1777306247000},"page":"103765","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":3,"special_numbering":"C","title":["Foundation models for bioacoustics \u2013 A comparative review"],"prefix":"10.1016","volume":"96","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8519-3571","authenticated-orcid":false,"given":"Raphael","family":"Schwinger","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8396-1585","authenticated-orcid":false,"given":"Paria","family":"Vali Zadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6552-3270","authenticated-orcid":false,"given":"Lukas","family":"Rauch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2527-9078","authenticated-orcid":false,"given":"Mats","family":"Kurz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8928-0477","authenticated-orcid":false,"given":"Tom","family":"Hauschild","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1637-6822","authenticated-orcid":false,"given":"Sam","family":"Lapp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5825-8915","authenticated-orcid":false,"given":"Sven","family":"Tomforde","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"7","key":"10.1016\/j.ecoinf.2026.103765_b1","doi-asserted-by":"crossref","DOI":"10.3390\/jmse9070685","article-title":"On the importance of passive acoustic monitoring filters","volume":"9","author":"Aguiar","year":"2021","journal-title":"J. Mar. Sci. Eng."},{"key":"10.1016\/j.ecoinf.2026.103765_b2","series-title":"International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume":"vol. 162","author":"Baevski","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b3","series-title":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, Virtual","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"10.1016\/j.ecoinf.2026.103765_b4","series-title":"Unsupervised learning on a DIET: Datum index as target free of self-supervision, reconstruction, projector head","author":"Balestriero","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b5","series-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103765_b6","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1038\/s41597-023-02666-2","article-title":"A dataset for benchmarking neotropical anuran calls identification in passive acoustic monitoring","volume":"10","author":"Canas","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.ecoinf.2026.103765_b7","series-title":"Interspeech 2024","first-page":"132","article-title":"Investigating self-supervised speech models\u2019 ability to classify animal vocalizations: The case of gibbon\u2019s vocal signatures","author":"Cauzinille","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b8","series-title":"Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, December 10 - 15, 2024","article-title":"The inaturalist sounds dataset","author":"Chasmai","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b9","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022","first-page":"646","article-title":"HTS-AT: a hierarchical token-semantic audio transformer for sound classification and detection","author":"Chen","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b10","series-title":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada","first-page":"8928","article-title":"This looks like that: Deep learning for interpretable image recognition","author":"Chen","year":"2019"},{"key":"10.1016\/j.ecoinf.2026.103765_b11","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI 2024, Jeju, South Korea, August 3-9, 2024","first-page":"3807","article-title":"EAT: self-supervised pre-training with efficient audio transformer","author":"Chen","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b12","series-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume":"vol. 202","author":"Chen","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b13","series-title":"2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2020, Barcelona, Spain, May 4-8, 2020","first-page":"721","article-title":"Vggsound: A large-scale audio-visual dataset","author":"Chen","year":"2020"},{"key":"10.1016\/j.ecoinf.2026.103765_b14","series-title":"An annotated set of audio recordings of eastern North American birds containing frequency, time, and species information","author":"Chronister","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b15","series-title":"A collection of fully-annotated soundscape recordings from the southern Sierra Nevada mountain range","author":"Clapp","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b16","series-title":"Advances in Artificial Intelligence - 17th Conference of the Spanish Association for Artificial Intelligence, CAEPIA 2016, Salamanca, Spain, September 14-16, 2016. Proceedings","first-page":"37","article-title":"How to correctly evaluate an automatic bioacoustics classification method","volume":"vol. 9868","author":"Colonna","year":"2016"},{"issue":"6","key":"10.1016\/j.ecoinf.2026.103765_b17","doi-asserted-by":"crossref","first-page":"2575","DOI":"10.1111\/1365-2664.13229","article-title":"Comparing the sampling performance of sound recorders versus point counts in bird surveys: A meta-analysis","volume":"55","author":"Darras","year":"2018","journal-title":"J. Appl. Ecol."},{"key":"10.1016\/j.ecoinf.2026.103765_b18","series-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021"},{"key":"10.1016\/j.ecoinf.2026.103765_b19","doi-asserted-by":"crossref","DOI":"10.1002\/rse2.201","article-title":"Automated detection of hainan gibbon calls for passive acoustic monitoring","author":"Dufourq","year":"2021","journal-title":"Remote. Sens. Ecol. Conserv."},{"key":"10.1016\/j.ecoinf.2026.103765_b20","series-title":"The search for squawk: Agile modeling in bioacoustics","author":"Dumoulin","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103765_b21","series-title":"Forty-First International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024","article-title":"Scalable pre-training of large autoregressive image models","author":"El-Nouby","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b22","series-title":"InsectSet459: an open dataset of insect sounds for bioacoustic machine learning","author":"Faiss","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103765_b23","series-title":"fbravosanchez\/NIPS4bplus","author":"fbravosanchez","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b24","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1109\/TASLP.2021.3133208","article-title":"FSD50k: An open dataset of human-labeled sound events","volume":"30","author":"Fonseca","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Proc."},{"key":"10.1016\/j.ecoinf.2026.103765_b25","series-title":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2017, New Orleans, la, USA, March 5-9, 2017","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"Gemmeke","year":"2017"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103765_b26","doi-asserted-by":"crossref","first-page":"22876","DOI":"10.1038\/s41598-023-49989-z","article-title":"Global birdsong embeddings enable superior transfer learning for bioacoustic classification","volume":"13","author":"Ghani","year":"2023","journal-title":"Sci. Rep."},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103765_b27","doi-asserted-by":"crossref","first-page":"16273","DOI":"10.1038\/s41598-025-00996-2","article-title":"Impact of transfer learning methods and dataset characteristics on generalization in birdsong classification","volume":"15","author":"Ghani","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.ecoinf.2026.103765_b28","series-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b29","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023","first-page":"1","article-title":"AVES: animal vocalization encoder based on self-supervision","author":"Hagiwara","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b30","series-title":"Introducing BirdAVES: Self-supervised audio foundation model for birds - earth species project","author":"Hagiwara","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b31","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing ICASSP 2023, Rhodes Island, Greece, June 4-10, 2023","first-page":"1","article-title":"BEANS: the benchmark of animal sounds","author":"Hagiwara","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b32","series-title":"BIRB: A generalization benchmark for information retrieval in bioacoustics","author":"Hamer","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2025.103081","article-title":"AudioProtoPNet: An interpretable deep learning model for bird sound classification","volume":"87","author":"Heinrich","year":"2025","journal-title":"Ecol. Inform."},{"issue":"5","key":"10.1016\/j.ecoinf.2026.103765_b34","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1080\/09524622.2023.2209052","article-title":"Passive acoustic monitoring in terrestrial vertebrates: a review","volume":"32","author":"Hoefer","year":"2023","journal-title":"Bioacoustics"},{"key":"10.1016\/j.ecoinf.2026.103765_b35","series-title":"A collection of fully-annotated soundscape recordings from the southwestern amazon basin","author":"Hopping","year":"2022"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103765_b36","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1186\/s40537-022-00652-w","article-title":"Transfer learning: a friendly introduction","volume":"9","author":"Hosna","year":"2022","journal-title":"J. Big Data"},{"key":"10.1016\/j.ecoinf.2026.103765_b37","series-title":"Cornell birdcall identification","author":"Howard","year":"2020"},{"key":"10.1016\/j.ecoinf.2026.103765_b38","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.ecoinf.2026.103765_b39","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, la, USA, June 18-24, 2022","first-page":"9058","article-title":"Pushing the limits of simple pipelines for few-shot learning: External data and fine-tuning make a difference","author":"Hu","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b40","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b41","series-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, la, USA, November 28 - December 9, 2022","article-title":"Masked autoencoders that listen","author":"Huang","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b42","series-title":"A collection of fully-annotated soundscape recordings from the Northeastern United States","author":"Kahl","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b43","series-title":"A collection of fully-annotated soundscape recordings from the Western United States","author":"Kahl","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b44","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2021.101236","article-title":"BirdNET: A deep learning solution for avian diversity monitoring","volume":"61","author":"Kahl","year":"2021","journal-title":"Ecol. Inform."},{"key":"10.1016\/j.ecoinf.2026.103765_b45","series-title":"Proceedings of the 2024 International Conference on Information Technology for Social Good","first-page":"22","article-title":"Active and transfer learning for efficient identification of species in multi-label bioacoustic datasets","author":"Kath","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b46","series-title":"Clustering and novel class recognition: evaluating bioacoustic deep learning feature extractors","author":"Kather","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103765_b47","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"119","article-title":"Audiocaps: Generating captions for audios in the wild","author":"Kim","year":"2019"},{"key":"10.1016\/j.ecoinf.2026.103765_b48","article-title":"HumBugDB: A large-scale acoustic mosquito dataset","volume":"vol. 1","author":"Kiskin","year":"2021"},{"key":"10.1016\/j.ecoinf.2026.103765_b49","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","author":"Kumar","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b50","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2020.101113","article-title":"A pipeline for identification of bird and frog species in tropical soundscape recordings using a convolutional neural network","volume":"59","author":"LeBien","year":"2020","journal-title":"Ecol. Inform."},{"key":"10.1016\/j.ecoinf.2026.103765_b51","series-title":"International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume":"vol. 202","author":"Li","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b52","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, la, USA, June 18-24, 2022","first-page":"11966","article-title":"A ConvNet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b53","series-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"10.1016\/j.ecoinf.2026.103765_b54","series-title":"7th International Conference on Learning Representations, ICLR 2019, New Orleans, la, USA, May 6-9, 2019","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"10.1016\/j.ecoinf.2026.103765_b55","series-title":"BirdVox-DCASE-20k: a dataset for bird audio detection in 10-second clips","author":"Lostanlen","year":"2018"},{"issue":"6783","key":"10.1016\/j.ecoinf.2026.103765_b56","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/35012251","article-title":"Systematic conservation planning","volume":"405","author":"Margules","year":"2000","journal-title":"Nature"},{"key":"10.1016\/j.ecoinf.2026.103765_b57","series-title":"Perch 2.0: The bittern lesson for bioacoustics","author":"van Merri\u00ebnboer","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103765_b58","doi-asserted-by":"crossref","DOI":"10.3389\/fbirs.2024.1369756","article-title":"Birds, bats and beyond: evaluating generalization in bioacoustics models","volume":"3","author":"van Merrienboer","year":"2024","journal-title":"Front. Bird Sci."},{"key":"10.1016\/j.ecoinf.2026.103765_b59","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecoinf.2022.101952","article-title":"Unsupervised classification to improve the quality of a bird song recording dataset","volume":"74","author":"Michaud","year":"2023","journal-title":"Ecol. Inform."},{"key":"10.1016\/j.ecoinf.2026.103765_b60","series-title":"Proceedings of the Workshop on Detection and Classification of Acoustic Scenes and Events 2021","article-title":"Few-shot bioacoustic event detection: A new task at the DCASE 2021 challenge","author":"Morfi","year":"2021"},{"key":"10.1016\/j.ecoinf.2026.103765_b61","series-title":"Domain-invariant representation learning of bird sounds","author":"Moummad","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b62","series-title":"A collection of fully-annotated soundscape recordings from the Island of Hawai\u2019i","author":"Navine","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b63","first-page":"1","article-title":"BYOL for audio: Exploring pre-trained general-purpose audio representations","volume":"PP","author":"Niizumi","year":"2022","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.ecoinf.2026.103765_b64","series-title":"Hawaiian islands cetacean and ecosystem assessment survey (HICEAS) towed array data","author":"NOAA Pacific Islands Fisheries Science Center","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b65","series-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b66","series-title":"Interspeech 2019, 20th Annual Conference of the International Speech Communication Association, Graz, Austria, 15-19 September 2019","first-page":"2613","article-title":"Specaugment: A simple data augmentation method for automatic speech recognition","author":"Park","year":"2019"},{"key":"10.1016\/j.ecoinf.2026.103765_b67","series-title":"Proceedings of the 23rd ACM International Conference on Multimedia","first-page":"1015","article-title":"ESC: Dataset for environmental sound classification","author":"Piczak","year":"2015"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103765_b68","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2017.143","article-title":"An annotated dataset of Egyptian fruit bat vocalizations across varying contexts and during vocal ontogeny","volume":"4","author":"Prat","year":"2017","journal-title":"Sci. Data"},{"key":"10.1016\/j.ecoinf.2026.103765_b69","series-title":"OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts","author":"Priem","year":"2022"},{"key":"10.1016\/j.ecoinf.2026.103765_b70","series-title":"Towards deep active learning in avian bioacoustics","author":"Rauch","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b71","series-title":"Can masked autoencoders also listen to birds?","author":"Rauch","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103765_b72","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Birdset: A large-scale dataset for audio classification in avian bioacoustics","author":"Rauch","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103765_b73","series-title":"Speaker recognition from raw waveform with SincNet","author":"Ravanelli","year":"2018"},{"key":"10.1016\/j.ecoinf.2026.103765_b74","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"NatureLM-audio: an audio-language foundation model for bioacoustics","author":"Robinson","year":"2025"},{"key":"10.1016\/j.ecoinf.2026.103765_b75","series-title":"IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2024, Seoul, Republic of Korea, April 14-19, 2024","first-page":"1316","article-title":"Transferable models for bioacoustics with human language supervision","author":"Robinson","year":"2024"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103765_b76","article-title":"The watkins marine mammal sound database: An online, freely accessible resource","volume":"27","author":"Sayigh","year":"2017","journal-title":"Proc. Meet. Acoust."},{"key":"10.1016\/j.ecoinf.2026.103765_b77","series-title":"Animal2vec and meerkat: A self-supervised transformer for rare-event raw audio input and a large-scale reference dataset for bioacoustics","author":"Sch\u00e4fer-Zimmermann","year":"2024"},{"issue":"12","key":"10.1016\/j.ecoinf.2026.103765_b78","doi-asserted-by":"crossref","first-page":"2765","DOI":"10.1007\/s10531-017-1388-7","article-title":"Building capacity in biodiversity monitoring at the global scale","volume":"26","author":"Schmeller","year":"2017","journal-title":"Biodivers. Conserv."},{"key":"10.1016\/j.ecoinf.2026.103765_b79","series-title":"Why Birds Matter: Avian Ecological Function and Ecosystem Services","author":"Sekercioglu","year":"2016"},{"key":"10.1016\/j.ecoinf.2026.103765_b80","series-title":"Curriculum learning: A survey","author":"Soviany","year":"2021"},{"key":"10.1016\/j.ecoinf.2026.103765_b81","doi-asserted-by":"crossref","first-page":"1743","DOI":"10.1038\/s41559-023-02162-1","article-title":"Data leakage jeopardizes ecological applications of machine learning","volume":"7","author":"Stock","year":"2023","journal-title":"Nat. Ecol. Evol."},{"key":"10.1016\/j.ecoinf.2026.103765_b82","doi-asserted-by":"crossref","DOI":"10.7717\/peerj.13152","article-title":"Computational bioacoustics with deep learning: a review and roadmap","volume":"10","author":"Stowell","year":"2022","journal-title":"PeerJ"},{"issue":"1","key":"10.1016\/j.ecoinf.2026.103765_b83","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1093\/biosci\/biy147","article-title":"Terrestrial passive acoustic monitoring: Review and perspectives","volume":"69","author":"Sugai","year":"2019","journal-title":"BioScience"},{"key":"10.1016\/j.ecoinf.2026.103765_b84","series-title":"Proceedings of the 36th International Conference on Machine Learning, ICML 2019, 9-15 June 2019, Long Beach, California, USA","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume":"vol. 97","author":"Tan","year":"2019"},{"issue":"4","key":"10.1016\/j.ecoinf.2026.103765_b85","doi-asserted-by":"crossref","DOI":"10.3390\/jimaging8040096","article-title":"Convolutional neural networks for the identification of African lions from individual vocalizations","volume":"8","author":"Trapanotto","year":"2022","journal-title":"J. Imaging"},{"key":"10.1016\/j.ecoinf.2026.103765_b86","series-title":"A collection of fully-annotated soundscape recordings from neotropical coffee farms in Colombia and costa rica","author":"Vega-Hidalgo","year":"2023"},{"key":"10.1016\/j.ecoinf.2026.103765_b87","series-title":"CLEF (Working Notes)","article-title":"The xeno-canto collection and its relation to sound recognition and classification","author":"Vellinga","year":"2015"},{"key":"10.1016\/j.ecoinf.2026.103765_b88","series-title":"Simpleshot: Revisiting nearest-neighbor classification for few-shot learning","author":"Wang","year":"2019"},{"key":"10.1016\/j.ecoinf.2026.103765_b89","series-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"10.1016\/j.ecoinf.2026.103765_b90","article-title":"Simulated soundscapes and transfer learning boost the performance of acoustic classifiers under data scarcity","author":"Weldy","year":"2025","journal-title":"USGS Publ. Wareh."},{"key":"10.1016\/j.ecoinf.2026.103765_b91","series-title":"Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics","author":"Williams","year":"2024"},{"key":"10.1016\/j.ecoinf.2026.103765_b92","series-title":"2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, October 10-17, 2021","first-page":"22","article-title":"Cvt: Introducing convolutions to vision transformers","author":"Wu","year":"2021"},{"issue":"2","key":"10.1016\/j.ecoinf.2026.103765_b93","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.anbehav.2003.07.016","article-title":"Barking in domestic dogs: context specificity and individual identification","volume":"68","author":"Yin","year":"2004","journal-title":"Anim. Behav."},{"key":"10.1016\/j.ecoinf.2026.103765_b94","series-title":"6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings","article-title":"Mixup: Beyond empirical risk minimization","author":"Zhang","year":"2018"}],"container-title":["Ecological Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574954126001718?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574954126001718?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T03:35:09Z","timestamp":1780544109000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1574954126001718"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":94,"alternative-id":["S1574954126001718"],"URL":"https:\/\/doi.org\/10.1016\/j.ecoinf.2026.103765","relation":{},"ISSN":["1574-9541"],"issn-type":[{"value":"1574-9541","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Foundation models for bioacoustics \u2013 A comparative review","name":"articletitle","label":"Article Title"},{"value":"Ecological Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ecoinf.2026.103765","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"103765"}}