{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T10:43:31Z","timestamp":1785926611271,"version":"3.56.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032028129","type":"print"},{"value":"9783032028136","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-02813-6_4","type":"book-chapter","created":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T07:15:47Z","timestamp":1756624547000},"page":"47-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Intermediate-Task Transfer Learning for\u00a0Bioacoustic Data"],"prefix":"10.1007","author":[{"given":"Hannes","family":"Kath","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thiago S.","family":"Gouv\u00eaa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Sonntag","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,1]]},"reference":[{"key":"4_CR1","doi-asserted-by":"publisher","unstructured":"Azizpour, H., Razavian, A.S., Sullivan, J., Maki, A., Carlsson, S.: From generic to specific deep representations for visual recognition. In: CVPR Workshop, pp. 36\u201345. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/CVPRW.2015.7301270","DOI":"10.1109\/CVPRW.2015.7301270"},{"key":"4_CR2","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: NeurIPS, pp. 12449\u201312460 (2020)"},{"key":"4_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2023.102241","volume":"77","author":"T Bicudo","year":"2023","unstructured":"Bicudo, T., Llusia, D., Anci\u00e3es, M., Gil, D.: Poor performance of acoustic indices as proxies for bird diversity in a fragmented Amazonian landscape. Eco. Inform. 77, 102241 (2023). https:\/\/doi.org\/10.1016\/j.ecoinf.2023.102241","journal-title":"Eco. Inform."},{"key":"4_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecolind.2020.106953","volume":"120","author":"IB Campos","year":"2021","unstructured":"Campos, I.B., Fewster, R., Truskinger, A., Towsey, M., et al.: Assessing the potential of acoustic indices for protected area monitoring in the Serra do Cip\u00f3 National Park. Brazil. Ecol. Indicators 120, 106953 (2021). https:\/\/doi.org\/10.1016\/j.ecolind.2020.106953","journal-title":"Brazil. Ecol. Indicators"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Carthy, R., Oli, M., Wooding, J., Berish, J., Meyer, W.: Analysis of gopher tortoise population estimation techniques. Tech. rep, US Army Engineer Research and Development Center, Construction Engineering (2005)","DOI":"10.21236\/ADA444540"},{"key":"4_CR6","doi-asserted-by":"publisher","unstructured":"Ca\u00f1as, J.S., Toro-G\u00f3mez, M.P., Sugai, L.S.M., Ben\u00edtez\u00a0Restrepo, H.D., et\u00a0al.: A dataset for benchmarking neotropical anuran calls identification in passive acoustic monitoring. Sci. Data 10(1), 771 (2023). https:\/\/doi.org\/10.1038\/s41597-023-02666-2","DOI":"10.1038\/s41597-023-02666-2"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., et\u00a0al.: ImageNet: a large-scale hierarchical image database. In: CVPR, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"4_CR8","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/V1\/N19-1423","DOI":"10.18653\/V1\/N19-1423"},{"key":"4_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2022.101688","volume":"70","author":"E Dufourq","year":"2022","unstructured":"Dufourq, E., Batist, C., Foquet, R., Durbach, I.: Passive acoustic monitoring of animal populations with transfer learning. Eco. Inform. 70, 101688 (2022). https:\/\/doi.org\/10.1016\/j.ecoinf.2022.101688","journal-title":"Eco. Inform."},{"key":"4_CR10","doi-asserted-by":"publisher","unstructured":"Florentin, J., Dutoit, T., Verlinden, O.: Detection and identification of European woodpeckers with deep convolutional neural networks. Ecol. Informatics 55 (2020). https:\/\/doi.org\/10.1016\/J.ECOINF.2019.101023","DOI":"10.1016\/J.ECOINF.2019.101023"},{"key":"4_CR11","doi-asserted-by":"publisher","unstructured":"Gemmeke, J.F., Ellis, D.P.W., Freedman, D., Jansen, A., et\u00a0al.: Audio Set: an ontology and human-labeled dataset for audio events. In: ICASSP, pp. 776\u2013780 (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952261","DOI":"10.1109\/ICASSP.2017.7952261"},{"issue":"1","key":"4_CR12","doi-asserted-by":"publisher","first-page":"22876","DOI":"10.1038\/s41598-023-49989-z","volume":"13","author":"B Ghani","year":"2023","unstructured":"Ghani, B., Denton, T., Kahl, S., Klinck, H.: Global birdsong embeddings enable superior transfer learning for bioacoustic classification. Sci. Rep. 13(1), 22876 (2023). https:\/\/doi.org\/10.1038\/s41598-023-49989-z","journal-title":"Sci. Rep."},{"key":"4_CR13","unstructured":"Google research: Google bird vocalization classifier: a global bird embedding and classification model (2023). https:\/\/tfhub.dev\/google\/bird-vocalization-classifier\/4"},{"key":"4_CR14","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Computer Vision ECCV 2016, pp. 630\u2013645. Springer International Publishing, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"4_CR15","doi-asserted-by":"publisher","unstructured":"Hershey, S., Chaudhuri, S., Ellis, D.P., Gemmeke, J.F., et\u00a0al.: CNN architectures for large-scale audio classification. In: ICASSP, pp. 131\u2013135 (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952132","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"4_CR16","doi-asserted-by":"publisher","unstructured":"Hill, A., Prince, P., Pi\u00f1a-Covarrubias, E., Doncaster, C., et\u00a0al.: AudioMoth: evaluation of a smart open acoustic device for monitoring biodiversity and the environment. Methods Ecol. Evol. 9 (2017). https:\/\/doi.org\/10.1111\/2041-210X.12955","DOI":"10.1111\/2041-210X.12955"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Huang, P.Y., Xu, H., Li, J., Baevski, A., et\u00a0al.: Masked autoencoders that listen. In: NeurIPS, pp. 28708\u201328720 (2022)","DOI":"10.52202\/068431-2081"},{"key":"4_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2021.101236","volume":"61","author":"S Kahl","year":"2021","unstructured":"Kahl, S., Wood, C.M., Eibl, M., Klinck, H.: BirdNet: a deep learning solution for avian diversity monitoring. Eco. Inform. 61, 101236 (2021). https:\/\/doi.org\/10.1016\/j.ecoinf.2021.101236","journal-title":"Eco. Inform."},{"key":"4_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102710","volume":"82","author":"H Kath","year":"2024","unstructured":"Kath, H., Serafini, P.P., Campos, I.B., Gouv\u00eaa, T.S., Sonntag, D.: Leveraging transfer learning and active learning for data annotation in passive acoustic monitoring of wildlife. Eco. Inform. 82, 102710 (2024). https:\/\/doi.org\/10.1016\/j.ecoinf.2024.102710","journal-title":"Eco. Inform."},{"key":"4_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2020.101113","volume":"59","author":"J LeBien","year":"2020","unstructured":"LeBien, J., Zhong, M., Campos-Cerqueira, M., Velev, J.P., et al.: A pipeline for identification of bird and frog species in tropical soundscape recordings using a convolutional neural network. Eco. Inform. 59, 101113 (2020). https:\/\/doi.org\/10.1016\/j.ecoinf.2020.101113","journal-title":"Eco. Inform."},{"key":"4_CR21","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., et\u00a0al.: RoBERTa: a robustly optimized BERT pretraining approach. CoRR abs\/1907.11692 (2019)"},{"key":"4_CR22","unstructured":"L\u00fcers, B., Serafini, P.P., Campos, I.B., Gouv\u00eaa, T.S., Sonntag, D.: 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)"},{"key":"4_CR23","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.landurbplan.2017.01.014","volume":"162","author":"RB Machado","year":"2017","unstructured":"Machado, R.B., Aguiar, L., Jones, G.: Do acoustic indices reflect the characteristics of bird communities in the savannas of Central Brazil? Landsc. Urban Plan. 162, 36\u201343 (2017). https:\/\/doi.org\/10.1016\/j.landurbplan.2017.01.014","journal-title":"Landsc. Urban Plan."},{"issue":"12","key":"4_CR24","doi-asserted-by":"publisher","first-page":"9298","DOI":"10.1109\/TPAMI.2021.3129870","volume":"44","author":"T Mensink","year":"2022","unstructured":"Mensink, T., Uijlings, J.R.R., Kuznetsova, A., Gygli, M., Ferrari, V.: Factors of influence for transfer learning across diverse appearance domains and task types. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 9298\u20139314 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3129870","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2023.102258","volume":"77","author":"I Nolasco","year":"2023","unstructured":"Nolasco, I., Singh, S., Morfi, V., Lostanlen, V., et al.: Learning to detect an animal sound from five examples. Eco. Inform. 77, 102258 (2023). https:\/\/doi.org\/10.1016\/j.ecoinf.2023.102258","journal-title":"Eco. Inform."},{"key":"4_CR26","unstructured":"Phang, J., F\u00e9vry, T., Bowman, S.R.: Sentence encoders on stilts: supplementary training on intermediate labeled-data tasks. CoRR abs\/1811.01088 (2018)"},{"issue":"2","key":"4_CR27","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1046\/j.1365-2664.2000.00499.x","volume":"37","author":"AJ Plumptre","year":"2000","unstructured":"Plumptre, A.J.: Monitoring mammal populations with line transect techniques in African forests. J. Appl. Ecol. 37(2), 356\u2013368 (2000)","journal-title":"J. Appl. Ecol."},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Pruksachatkun, Y., Phang, J., Liu, H., Htut, P.M., et\u00a0al.: Intermediate-task transfer learning with pretrained models for natural language understanding: when and why does it work? CoRR abs\/2005.00628 (2020)","DOI":"10.18653\/v1\/2020.acl-main.467"},{"key":"4_CR29","doi-asserted-by":"publisher","unstructured":"Rauch, L., Schwinger, R., Wirth, M., Heinrich, R., et\u00a0al.: BirdSet: a multi-task benchmark for classification in avian bioacoustics. CoRR abs\/2403.10380 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2403.10380","DOI":"10.48550\/ARXIV.2403.10380"},{"issue":"4","key":"4_CR30","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1111\/1365-2435.14275","volume":"37","author":"SRJ Ross","year":"2023","unstructured":"Ross, S.R.J., O\u2019Connell, D.P., Deichmann, J.L., Desjonqu\u00e8res, C., et al.: Passive acoustic monitoring provides a fresh perspective on fundamental ecological questions. Funct. Ecol. 37(4), 959\u2013975 (2023)","journal-title":"Funct. Ecol."},{"key":"4_CR31","doi-asserted-by":"publisher","unstructured":"Sethi, S.S., Bick, A., Ewers, R.M., Klinck, H., et\u00a0al.: Limits to the accurate and generalizable use of soundscapes to monitor biodiversity. Nat. Ecol. Evol., 1\u20136 (2023). https:\/\/doi.org\/10.1038\/s41559-023-02148-z","DOI":"10.1038\/s41559-023-02148-z"},{"key":"4_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)"},{"key":"4_CR33","volume-title":"Computational Sustainability and Technology (CST)","author":"D Sonntag","year":"2025","unstructured":"Sonntag, D.: Computational Sustainability and Technology (CST). Tech. rep, German Research Center for AI (2025)"},{"issue":"4","key":"4_CR34","doi-asserted-by":"publisher","first-page":"772","DOI":"10.3813\/AAA.918757","volume":"100","author":"J Sueur","year":"2014","unstructured":"Sueur, J., Farina, A., Gasc, A., Pieretti, N., Pavoine, S.: Acoustic indices for biodiversity assessment and landscape investigation. Acta Acust. Acust. 100(4), 772\u2013781 (2014). https:\/\/doi.org\/10.3813\/AAA.918757","journal-title":"Acta Acust. Acust."},{"issue":"12","key":"4_CR35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0004065","volume":"3","author":"J Sueur","year":"2008","unstructured":"Sueur, J., Pavoine, S., Hamerlynck, O., Duvail, S.: Rapid acoustic survey for biodiversity appraisal. PLoS ONE 3(12), e4065 (2008)","journal-title":"PLoS ONE"},{"key":"4_CR36","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/j.ecolind.2018.12.021","volume":"99","author":"L Sugai","year":"2019","unstructured":"Sugai, L., Llusia, D.: Bioacoustic time capsules: using acoustic monitoring to document biodiversity. Ecol. Ind. 99, 149\u2013152 (2019)","journal-title":"Ecol. Ind."},{"issue":"1","key":"4_CR37","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1093\/biosci\/biy147","volume":"69","author":"LSM Sugai","year":"2019","unstructured":"Sugai, L.S.M., Silva, T.S.F., Ribeiro, J.W., Llusia, D.: Terrestrial passive acoustic monitoring: review and perspectives. Bioscience 69(1), 15\u201325 (2019). https:\/\/doi.org\/10.1093\/biosci\/biy147","journal-title":"Bioscience"},{"key":"4_CR38","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2024.102471","volume":"80","author":"B Swaminathan","year":"2024","unstructured":"Swaminathan, B., Jagadeesh, M., Vairavasundaram, S.: Multi-label classification for acoustic bird species detection using transfer learning approach. Eco. Inform. 80, 102471 (2024). https:\/\/doi.org\/10.1016\/j.ecoinf.2024.102471","journal-title":"Eco. Inform."},{"key":"4_CR39","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: ICML, vol.\u00a097, pp. 6105\u20136114. PMLR (2019)"},{"key":"4_CR40","unstructured":"United Nations: Transforming our world: the 2030 agenda for sustainable development. Resolution A\/RES\/70\/1, United Nations General Assembly (2015). https:\/\/sdgs.un.org\/2030agenda, adopted on 25 September 2015"},{"key":"4_CR41","doi-asserted-by":"publisher","unstructured":"Wang, A., Hula, J., Xia, P., Pappagari, R., et\u00a0al.: Can you tell me how to get past sesame street? sentence-level pretraining beyond language modeling. In: ACL, pp. 4465\u20134476. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/V1\/P19-1439","DOI":"10.18653\/V1\/P19-1439"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Weldy, M.J., Denton, T., Fleishman, A.B., Tolchin, J., et\u00a0al.: Audio tagging of avian dawn chorus recordings in California, Oregon and Washington. Biodivers. Data J. 12, e118315 (2024)","DOI":"10.3897\/BDJ.12.e118315"},{"key":"4_CR43","volume-title":"Biodiversity","year":"1988","unstructured":"Wilson, E., University, H. (eds.): Biodiversity. The National Academies Press, Washington, DC (1988)"},{"key":"4_CR44","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? In: NeurIPS, pp. 3320\u20133328 (2014)"}],"container-title":["Lecture Notes in Computer Science","KI 2025: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02813-6_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T09:43:26Z","timestamp":1785923006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02813-6_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,1]]},"ISBN":["9783032028129","9783032028136"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02813-6_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,1]]},"assertion":[{"value":"1 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Artificial Intelligence (K\u00fcnstliche Intelligenz)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Potsdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"48","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ki2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ki2025.gi.de\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}