{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:50Z","timestamp":1774419410774,"version":"3.50.1"},"reference-count":28,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890645","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:56:59Z","timestamp":1741787819000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["SoundCollage: Automated Discovery of New Classes in Audio Datasets"],"prefix":"10.1109","author":[{"given":"Ryuhaerang","family":"Choi","sequence":"first","affiliation":[{"name":"KAIST,South Korea"}]},{"given":"Soumyajit","family":"Chatterjee","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs,Cambridge,UK"}]},{"given":"Dimitris","family":"Spathis","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs,Cambridge,UK"}]},{"given":"Sung-Ju","family":"Lee","sequence":"additional","affiliation":[{"name":"KAIST,South Korea"}]},{"given":"Fahim","family":"Kawsar","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs,Cambridge,UK"}]},{"given":"Mohammad","family":"Malekzadeh","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs,Cambridge,UK"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Covid-19 sounds: a large-scale audio dataset for digital respiratory screening","volume-title":"Thirty-fifth Conference on neural information processing systems datasets and benchmarks track","author":"Xia"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1515\/9781399507769-021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00849"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5040\/9781350249127.ch-i"},{"key":"ref5","article-title":"Unseen class discovery in open-world classification","author":"Shu","year":"2018"},{"key":"ref6","article-title":"Meta discovery: Learning to discover novel classes given very limited data","volume-title":"International Conference on Learning Representations","author":"Chi"},{"key":"ref7","article-title":"Unsupervised musical object discovery from audio","volume-title":"NeurIPS Workshop on Machine Learning for Audio","author":"Gha"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447561"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376875"},{"key":"ref10","article-title":"Task discovery: Finding the tasks that neural networks generalize on","volume-title":"Advances in Neural Information Processing Systems","author":"Atanov"},{"key":"ref11","article-title":"Learning to cluster in order to transfer across domains and tasks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Hsu"},{"key":"ref12","article-title":"Deep audio priors emerge from harmonic convolutional networks","volume-title":"International Conference on Learning Representations","author":"Zhang"},{"key":"ref13","article-title":"Sound classification with YAMNet","author":"Plakal"},{"key":"ref14","article-title":"Audioset"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746096"},{"key":"ref17","article-title":"Music\/voice separation using the similarity matrix","volume-title":"ISMIR","author":"Rafii"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177993"},{"key":"ref19","article-title":"A kernel multiple change-point algorithm via model selection","author":"Arlot","year":"2019","journal-title":"Journal of machine learning research"},{"key":"ref20","article-title":"Let\u2019s agree to agree: Neural networks share classification order on real datasets","volume-title":"International Conference on Machine Learning","author":"Hacohen"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_23"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1903070116"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/DCOSS-IoT58021.2023.00013"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447868"},{"key":"ref26","article-title":"Task discovery framework open source","author":"Atanov"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref28","article-title":"Uniaudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023"}],"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\/10890645.pdf?arnumber=10890645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:44Z","timestamp":1774416164000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890645","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}