{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T04:24:43Z","timestamp":1751343883282,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1145\/3702336.3702344","type":"proceedings-article","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T06:18:21Z","timestamp":1732774701000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Vocalizations of the Parus minor Bird: Taxonomy and Automatic Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0314-2699","authenticated-orcid":false,"given":"Artem","family":"Abzaliev","sequence":"first","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7659-376X","authenticated-orcid":false,"given":"Katsumi","family":"Ibaraki","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1548-3618","authenticated-orcid":false,"given":"Kohei","family":"Shibata","sequence":"additional","affiliation":[{"name":"Independent Researcher, Kamakura, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0767-6703","authenticated-orcid":false,"given":"Rada","family":"Mihalcea","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"e_1_3_3_2_2_2","first-page":"16480","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Abzaliev Artem","year":"2024","unstructured":"Artem Abzaliev, Humberto Perez-Espinosa, and Rada Mihalcea. 2024. Towards Dog Bark Decoding: Leveraging Human Speech Processing for Automated Bark Classification. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, Torino, Italia, 16480\u201316486. https:\/\/aclanthology.org\/2024.lrec-main.1432"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Daniel\u00a0L Bowling and W\u00a0Tecumseh Fitch. 2015. Do animal communication systems have phonemes? Trends in Cognitive Sciences 19 10 (2015) 555\u2013557.","DOI":"10.1016\/j.tics.2015.08.011"},{"key":"e_1_3_3_2_4_2","unstructured":"Andrew Brock Soham De Samuel\u00a0L. Smith and Karen Simonyan. 2021. High-Performance Large-Scale Image Recognition Without Normalization. arxiv:https:\/\/arXiv.org\/abs\/2102.06171\u00a0[cs.CV]"},{"key":"e_1_3_3_2_5_2","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared\u00a0D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et\u00a0al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Clive\u00a0K Catchpole. 1987. Bird song sexual selection and female choice. Trends in Ecology & Evolution 2 4 (1987) 94\u201397.","DOI":"10.1016\/0169-5347(87)90165-0"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Myl\u00e8ne Dutour Toshitaka\u00a0N Suzuki and David Wheatcroft. 2020. Great tit responses to the calls of an unfamiliar species suggest conserved perception of call ordering. Behavioral Ecology and Sociobiology 74 (2020) 1\u20139.","DOI":"10.1007\/s00265-020-2820-7"},{"key":"e_1_3_3_2_8_2","unstructured":"Alexandre D\u00e9fossez Jade Copet Gabriel Synnaeve and Yossi Adi. 2022. High Fidelity Neural Audio Compression. arxiv:https:\/\/arXiv.org\/abs\/2210.13438\u00a0[eess.AS]"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Sabrina Engesser Jodie\u00a0MS Crane James\u00a0L Savage Andrew\u00a0F Russell and Simon\u00a0W Townsend. 2015. Experimental evidence for phonemic contrasts in a nonhuman vocal system. PLoS biology 13 6 (2015) e1002171.","DOI":"10.1371\/journal.pbio.1002171"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Todd Freeberg Jeffrey Lucas and Indrikis Krams. 2012. The Complex Call of the Carolina Chickadee What can the chick-a-dee call teach us about communication and language? American Scientist 100 (04 2012) 398\u2013407. 10.1511\/2012.98.398","DOI":"10.1511\/2012.98.398"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Logan\u00a0S James Herie Sun Kazuhiro Wada and Jon\u00a0T Sakata. 2020. Statistical learning for vocal sequence acquisition in a songbird. Scientific reports 10 1 (2020) 2248.","DOI":"10.1038\/s41598-020-58983-8"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander\u00a0C. Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. 2023. Segment Anything. arxiv:https:\/\/arXiv.org\/abs\/2304.02643\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2304.02643","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Yi Luo and Nima Mesgarani. 2019. Conv-TasNet: Surpassing Ideal Time\u2013Frequency Magnitude Masking for Speech Separation. IEEE\/ACM Transactions on Audio Speech and Language Processing 27 8 (Aug. 2019) 1256\u20131266. 10.1109\/taslp.2019.2915167 https:\/\/dl.acm.org\/doi\/10.1109\/taslp.2019.2915167","DOI":"10.1109\/taslp.2019.2915167"},{"key":"e_1_3_3_2_15_2","volume-title":"Nature\u2019s music: the science of birdsong","author":"Marler Peter\u00a0R","year":"2004","unstructured":"Peter\u00a0R Marler and Hans Slabbekoorn. 2004. Nature\u2019s music: the science of birdsong. Elsevier."},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2680"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Pratyusha Sharma Shane Gero Roger Payne David\u00a0F Gruber Daniela Rus Antonio Torralba and Jacob Andreas. 2024. Contextual and combinatorial structure in sperm whale vocalisations. Nature Communications 15 1 (2024) 3617.","DOI":"10.1038\/s41467-024-47221-8"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"CN Slobodchikoff and J Placer. 2006. Acoustic structures in the alarm calls of Gunnison\u2019s prairie dogs. The Journal of the Acoustical Society of America 119 5 (2006) 3153\u20133160.","DOI":"10.1121\/1.2185489"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Con\u00a0N Slobodchikoff Andrea Paseka and Jennifer\u00a0L Verdolin. 2009. Prairie dog alarm calls encode labels about predator colors. Animal cognition 12 (2009) 435\u2013439.","DOI":"10.1007\/s10071-008-0203-y"},{"key":"e_1_3_3_2_20_2","unstructured":"Mohammad\u00a0S. Sorower. 2010. A Literature Survey on Algorithms for Multi-label Learning. https:\/\/api.semanticscholar.org\/CorpusID:13222909"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Toshitaka\u00a0N. Suzuki. 2014. Communication about predator type by a bird using discrete graded and combinatorial variation in alarm calls. Animal Behaviour 87 (2014) 59\u201365. 10.1016\/j.anbehav.2013.10.009","DOI":"10.1016\/j.anbehav.2013.10.009"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Toshitaka\u00a0N Suzuki. 2016. Semantic communication in birds: evidence from field research over the past two decades. Ecological Research 31 (2016) 307\u2013319.","DOI":"10.1007\/s11284-016-1339-x"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Toshitaka\u00a0N Suzuki. 2019. Imagery in wild birds: retrieval of visual information from referential alarm calls. Learning & Behavior 47 (2019) 111\u2013114.","DOI":"10.3758\/s13420-019-00374-9"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Toshitaka\u00a0N Suzuki. 2021. Animal linguistics: exploring referentiality and compositionality in bird calls. Ecological Research 36 2 (2021) 221\u2013231.","DOI":"10.1111\/1440-1703.12200"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Toshitaka\u00a0N Suzuki David Wheatcroft and Michael Griesser. 2016. Experimental evidence for compositional syntax in bird calls. Nature communications 7 1 (2016) 10986.","DOI":"10.1038\/ncomms10986"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Toshitaka\u00a0N Suzuki David Wheatcroft and Michael Griesser. 2017. Wild birds use an ordering rule to decode novel call sequences. Current Biology 27 15 (2017) 2331\u20132336.","DOI":"10.1016\/j.cub.2017.06.031"},{"key":"e_1_3_3_2_27_2","unstructured":"Ross Wightman Hugo Touvron and Herv\u00e9 J\u00e9gou. 2021. ResNet strikes back: An improved training procedure in timm. arxiv:https:\/\/arXiv.org\/abs\/2110.00476\u00a0[cs.CV]"},{"key":"e_1_3_3_2_28_2","unstructured":"Kele Xu Dawei Feng Haibo Mi Boqing Zhu Dezhi Wang Lilun Zhang Hengxing Cai and Shuwen Liu. 2018. Mixup-Based Acoustic Scene Classification Using Multi-Channel Convolutional Neural Network. arxiv:https:\/\/arXiv.org\/abs\/1805.07319\u00a0[cs.CV]"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Neil Zeghidour Alejandro Luebs Ahmed Omran Jan Skoglund and Marco Tagliasacchi. 2021. SoundStream: An End-to-End Neural Audio Codec. arxiv:https:\/\/arXiv.org\/abs\/2107.03312\u00a0[cs.SD]","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"e_1_3_3_2_30_2","unstructured":"Hongyi Zhang Moustapha Cisse Yann\u00a0N. Dauphin and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. arxiv:https:\/\/arXiv.org\/abs\/1710.09412\u00a0[cs.LG]"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Li Zhang Jiangping Yu Chao Shen Dake Yin Longru Jin Wei Liang and Haitao Wang. 2022. Geographic variation in note types of alarm calls in Japanese tits (Parus minor). Animals 12 18 (2022) 2342.","DOI":"10.3390\/ani12182342"}],"event":{"name":"ACI 2024: The International Conference on Animal-Computer Interaction","acronym":"ACI 2024","location":"Glasgow United Kingdom"},"container-title":["Proceedings of the International Conference on Animal-Computer Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702336.3702344","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3702336.3702344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:09Z","timestamp":1750295889000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3702336.3702344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":30,"alternative-id":["10.1145\/3702336.3702344","10.1145\/3702336"],"URL":"https:\/\/doi.org\/10.1145\/3702336.3702344","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2024-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}