{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T17:00:06Z","timestamp":1773162006870,"version":"3.50.1"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031082764","type":"print"},{"value":"9783031082771","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-08277-1_16","type":"book-chapter","created":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T12:13:01Z","timestamp":1655381581000},"page":"189-203","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Bat Echolocation Call Detection and\u00a0Species Recognition by\u00a0Transformers with\u00a0Self-attention"],"prefix":"10.1007","author":[{"given":"Hicham","family":"Bellafkir","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Vogelbacher","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jannis","family":"Gottwald","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"M\u00fchling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaus","family":"Korfhage","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patrick","family":"Lampe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Frie\u00df","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Nauss","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernd","family":"Freisleben","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,17]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Aide, T.M., Corrada-Bravo, C., Campos-Cerqueira, M., Milan, C., Vega, G., Alvarez, R.: Real-time bioacoustics monitoring and automated species identification. PeerJ 1, e103 (2013)","DOI":"10.7717\/peerj.103"},{"key":"16_CR2","doi-asserted-by":"publisher","unstructured":"Chen, X., Zhao, J., Chen, Y., Zhou, W., Hughes, A.C.: Automatic standardized processing and identification of tropical bat calls using deep learning approaches. Biol. Conserv. 241, 108269 (2020). https:\/\/doi.org\/10.1016\/j.biocon.2019.108269","DOI":"10.1016\/j.biocon.2019.108269"},{"key":"16_CR3","unstructured":"Cordonnier, J., Loukas, A., Jaggi, M.: On the relationship between self-attention and convolutional layers. In: 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia (2020)"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2020, Seattle, WA, USA, June 13\u201319, 2020, pp. 10575\u201310584. Computer Vision Foundation\/IEEE (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01059","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"16_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations, ICLR 2021, Austria (2021)"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Frick, W.F., Kingston, T., Flanders, J.: A review of the major threats and challenges to global bat conservation. Ann. N. Y. Acad. Sci. 1469(1), 5\u201325 (2020). https:\/\/doi.org\/10.1111\/nyas.14045","DOI":"10.1111\/nyas.14045"},{"key":"16_CR7","doi-asserted-by":"publisher","unstructured":"Gemmeke, J.F., et al.: Audio set: an ontology and human-labeled dataset for audio events. In: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 776\u2013780 (2017). https:\/\/doi.org\/10.1109\/ICASSP.2017.7952261","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"16_CR8","doi-asserted-by":"publisher","unstructured":"Gong, Y., Chung, Y., Glass, J.R.: AST: audio spectrogram transformer. In: Interspeech 2021, pp. 571\u2013575 (2021). https:\/\/doi.org\/10.21437\/Interspeech.2021-698","DOI":"10.21437\/Interspeech.2021-698"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR10","doi-asserted-by":"publisher","unstructured":"Jones, G., Jacobs, D.S., Kunz, T.H., Willig, M.R., Racey, P.A.: Carpe noctem: the importance of bats as bioindicators. Endang Species Res. 8, 93\u2013115 (2009). https:\/\/doi.org\/10.3354\/esr00182","DOI":"10.3354\/esr00182"},{"key":"16_CR11","doi-asserted-by":"publisher","unstructured":"Jones, K.E., et al.: Indicator bats program: a system for the global acoustic monitoring of bats. Biodivers. Monit. Conserv. 211\u2013247 (2013). https:\/\/doi.org\/10.1002\/9781118490747.ch10","DOI":"10.1002\/9781118490747.ch10"},{"key":"16_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, 2015, San Diego, CA, USA (2015). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"16_CR13","doi-asserted-by":"publisher","unstructured":"Kobayashi, K., Masuda, K., Haga, C., Matsui, T., Fukui, D., Machimura, T.: Development of a species identification system of japanese bats from echolocation calls using convolutional neural networks. Ecol. Inform. 62 (2021). https:\/\/doi.org\/10.1016\/j.ecoinf.2021.101253","DOI":"10.1016\/j.ecoinf.2021.101253"},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Kunz, T.H.: Ecology of Bats. Springer, Boston, MA, 1 edn. (1982). https:\/\/doi.org\/10.1007\/978-1-4613-3421-7","DOI":"10.1007\/978-1-4613-3421-7"},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Kunz, T.H., Braun de Torrez, E., Bauer, D., Lobova, T., Fleming, T.H.: Ecosystem services provided by bats. Ann. N. Y. Acad. Sci. 1223(1), 1\u201338 (2011). https:\/\/doi.org\/10.1111\/j.1749-6632.2011.06004.x","DOI":"10.1111\/j.1749-6632.2011.06004.x"},{"key":"16_CR16","doi-asserted-by":"publisher","unstructured":"Mac Aodha, O., et al.: Bat detective-deep learning tools for bat acoustic signal detection. PLoS Comput. Biol. 14(3) (2018). https:\/\/doi.org\/10.1371\/journal.pcbi.1005995","DOI":"10.1371\/journal.pcbi.1005995"},{"key":"16_CR17","doi-asserted-by":"publisher","unstructured":"Newson, S.E., Evans, H.E., Gillings, S.: A novel citizen science approach for large-scale standardised monitoring of bat activity and distribution, evaluated in eastern England. Biol. Conserv. 191, 38\u201349 (2015). https:\/\/doi.org\/10.1016\/j.biocon.2015.06.009","DOI":"10.1016\/j.biocon.2015.06.009"},{"key":"16_CR18","doi-asserted-by":"publisher","unstructured":"Park, D.S., et al.: Specaugment: a simple data augmentation method for automatic speech recognition. Interspeech 2019 (2019). https:\/\/doi.org\/10.21437\/interspeech.2019-2680","DOI":"10.21437\/interspeech.2019-2680"},{"key":"16_CR19","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch. In: NIPS-W (2017)"},{"key":"16_CR20","doi-asserted-by":"publisher","unstructured":"Paumen, Y., M\u00e4lzer, M., Alipek, S., Moll, J., L\u00fcdtke, B., Schauer-Weisshahn, H.: Development and test of a bat calls detection and classification method based on convolutional neural networks. Bioacoustics, 1\u201312 (2021). https:\/\/doi.org\/10.1080\/09524622.2021.1978863","DOI":"10.1080\/09524622.2021.1978863"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"Roemer, C., Julien, J.F., Bas, Y.: An automatic classifier of bat sonotypes around the world. Methods Ecol. Evol. 101526 (2021). https:\/\/doi.org\/10.1111\/2041-210X.13721","DOI":"10.1111\/2041-210X.13721"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Schwab, E., Pogrebnoj, S., Freund, M., Flossmann, F., Vogl, S., Frommolt, K.H.: Automated bat call classification using deep convolutional neural networks (2021). https:\/\/www.researchgate.net\/publication\/350978565_Automated_Bat_Call_Classification_using_Deep_Convolutional_Neural_Networks","DOI":"10.1080\/09524622.2022.2050816"},{"key":"16_CR23","volume-title":"Europ\u00e4ische Flederm\u00e4use","author":"R Skiba","year":"2003","unstructured":"Skiba, R.: Europ\u00e4ische Flederm\u00e4use. Westarp Wissenschaften, Hohenwarsleben (2003)"},{"key":"16_CR24","doi-asserted-by":"publisher","unstructured":"Tabak, M.A., Murray, K.L., Lombardi, J.A., Bay, K.J.: Automated classification of bat echolocation call recordings with artificial intelligence. Ecol. Inform. 68, 101526 (2022). https:\/\/doi.org\/10.1016\/j.ecoinf.2021.101526","DOI":"10.1016\/j.ecoinf.2021.101526"},{"key":"16_CR25","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: 38th International Conference on Machine Learning, PMLR 139, pp. 10347\u201310357 (2021)"},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Wightman, R.: Pytorch image models (2019). https:\/\/github.com\/rwightman\/pytorch-image-models. https:\/\/doi.org\/10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Yang, Y.Y., et al.: Torchaudio: building blocks for audio and speech processing. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, Singapore (2022)","DOI":"10.1109\/ICASSP43922.2022.9747236"},{"key":"16_CR28","doi-asserted-by":"publisher","unstructured":"Yu, J., Li, J., Yu, Z., Huang, Q.: Multimodal transformer with multi-view visual representation for image captioning. IEEE Trans. Circ. Syst. Video Technol. 30(12), 4467\u20134480 (2020). https:\/\/doi.org\/10.1109\/TCSVT.2019.2947482","DOI":"10.1109\/TCSVT.2019.2947482"},{"key":"16_CR29","doi-asserted-by":"publisher","unstructured":"Zualkernan, I., Judas, J., Mahbub, T., Bhagwagar, A., Chand, P.: A tiny CNN architecture for identifying bat species from echolocation calls. In: 2020 IEEE \/ ITU International Conference on Artificial Intelligence for Good (AI4G), pp. 81\u201386 (2020). https:\/\/doi.org\/10.1109\/AI4G50087.2020.9311084","DOI":"10.1109\/AI4G50087.2020.9311084"}],"container-title":["Communications in Computer and Information Science","Intelligent Systems and Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08277-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,16]],"date-time":"2022-06-16T12:17:10Z","timestamp":1655381830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08277-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031082764","9783031082771"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08277-1_16","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Systems and Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hammamet","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tunisia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 March 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ispr22022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ispr2022.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"91","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"24% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}