{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:54:28Z","timestamp":1778604868991,"version":"3.51.4"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007085","name":"National University of Defense Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007085","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890750","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["Scaling Bioacoustic Signal Pre-training with Million Samples Via Mask-Modeling"],"prefix":"10.1109","author":[{"given":"Xuyao","family":"Deng","sequence":"first","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianjiao","family":"Wan","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kele","family":"Xu","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tian","family":"Gao","sequence":"additional","affiliation":[{"name":"iFLYTEK Research Institute,Hefei,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Qiao","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dawei","family":"Feng","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Dou","sequence":"additional","affiliation":[{"name":"National University of Defense Technology,College of Computer Science and Technology,Changsha,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-27980-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-49989-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095642"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","article-title":"The xeno-canto collection and its relation to sound recognition and classification","author":"Vellinga","year":"2015","journal-title":"CLEF (Working Notes)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1121\/2.0000358"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10714948"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.143"},{"key":"ref13","article-title":"Cornell birdcall identification","year":"2020"},{"key":"ref14","article-title":"Humbugdb: a large-scale acoustic mosquito dataset","author":"Kiskin","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.anbehav.2003.07.016"},{"key":"ref16","first-page":"145","article-title":"Few-shot bioacoustic event detection: A new task at the dcase 2021 challenge","author":"Morfi","year":"2021","journal-title":"DCASE"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1002\/ecy.3329"},{"key":"ref18","article-title":"Hawaiian islands cetacean and ecosystem assessment survey (hiceas) towed array data","volume-title":"9th international workshop on detection, classification, localization, and density estimation of marine mammals using passive acoustics (dclde 2022)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoinf.2020.101113"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/rse2.201"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref22","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096686"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3402049"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"issue":"11","key":"ref31","article-title":"Visualizing data using t-sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890750.pdf?arnumber=10890750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:46Z","timestamp":1774416286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890750","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}