{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T18:54:10Z","timestamp":1774292050577,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447250","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1316-1320","source":"Crossref","is-referenced-by-count":5,"title":["Transferable Models for Bioacoustics with Human Language Supervision"],"prefix":"10.1109","author":[{"given":"David","family":"Robinson","sequence":"first","affiliation":[]},{"given":"Adelaide","family":"Robinson","sequence":"additional","affiliation":[{"name":"University of California,Santa Barbara"}]},{"given":"Lily","family":"Akrapongpisak","sequence":"additional","affiliation":[{"name":"University of Queensland"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Principles of animal communication","author":"Bradbury","year":"2011"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecocom.2020.100847"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.12730"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/eap.1954"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.13152"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096686"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2021.101236"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1111\/1365-2435.14275"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095642"},{"key":"ref11","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Finetuned Language Models Are Zero-Shot Learners","author":"Wei","year":"2022","journal-title":"ICLR"},{"key":"ref13","author":"Bermant","year":"2022","journal-title":"Bioacoustic Event Detection with Self-Supervised Contrastive Learning"},{"key":"ref14","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref17","article-title":"iNaturalist"},{"key":"ref18","article-title":"Animal sound archive"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/2.0000358"},{"key":"ref20","article-title":"Xeno-canto: Bird sounds from around the world"},{"key":"ref21","article-title":"Chatgpt","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref23","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume":"1","author":"Devlin","year":"2018","journal-title":"NAACL"},{"key":"ref24","first-page":"142","article-title":"Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition","author":"Tjong","year":"2003","journal-title":"NAACL"},{"key":"ref25","article-title":"Gbif occurrence download","year":"2023"},{"key":"ref26","article-title":"AudioCaps: Generating Captions for Audios in The Wild","author":"Kim","year":"2019","journal-title":"NAACL"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref30","author":"Liu","year":"2019","journal-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach"},{"key":"ref31","volume-title":"Neural networks: a comprehensive foundation","author":"Haykin","year":"1994"},{"key":"ref32","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"Nair","year":"2010","journal-title":"ICML"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.143"},{"key":"ref34","article-title":"Cornell Birdcall Identification","author":"Howard","year":"2020"},{"key":"ref35","article-title":"Humbugdb: A large-scale acoustic mosquito dataset","author":"Kiskin","year":"2021","journal-title":"NeurIPS"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.anbehav.2003.07.016"},{"key":"ref37","author":"Nolasco","year":"2022","journal-title":"Few-shot bioacoustic sound event detection at the dcase2022 challenge"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/ecy.3329"},{"key":"ref39","article-title":"Hawaiian Islands Cetacean and Ecosystem Assessment Survey (HICEAS) towed array data","year":"2022","journal-title":"DCLDE"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2020.101113"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/rse2.201"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447250.pdf?arnumber=10447250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:41:33Z","timestamp":1722573693000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447250\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447250","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}