{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:31:25Z","timestamp":1775068285289,"version":"3.50.1"},"reference-count":25,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007937","name":"Peking University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007937","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\/icassp49660.2025.10890178","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["Cross-attention Inspired Selective State Space Models for Target Sound Extraction"],"prefix":"10.1109","author":[{"given":"Donghang","family":"Wu","sequence":"first","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"}]},{"given":"Yiwen","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"}]},{"given":"Xihong","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"}]},{"given":"Tianshu","family":"Qu","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094573"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-197"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2987429"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2922820"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414003"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094306"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST59754.2023.10367130"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/709"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref14","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref16","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"ref17","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"ref18","article-title":"U-mamba: Enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3418714"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-994"},{"key":"ref21","article-title":"The hidden attention of mamba models","author":"Ali","year":"2024"},{"key":"ref22","article-title":"Wavenet: A generative model for raw audio","volume":"12","author":"Van Den Oord","year":"2016"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref24","article-title":"General-purpose tagging of freesound audio with audioset labels: Task description, dataset, and baseline","author":"Fonseca","year":"2018"},{"key":"ref25","article-title":"A multi-device dataset for urban acoustic scene classification","author":"Mesaros","year":"2018"}],"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\/10890178.pdf?arnumber=10890178","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:42Z","timestamp":1774416342000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890178\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890178","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}