{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T18:14:58Z","timestamp":1771611298846,"version":"3.50.1"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11231018","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source Separation"],"prefix":"10.1109","author":[{"given":"Kohei","family":"Saijo","sequence":"first","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),Tokyo,Japan"}]},{"given":"Yoshiaki","family":"Bando","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology (AIST),Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01667"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref3","article-title":"Demucs: Deep extractor for music sources with extra unlabeled data remixed","author":"D\u00e9fossez","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446843"},{"key":"ref6","article-title":"MUSDB18-HQ - an uncompressed version of MUSDB18","author":"Rafii","year":"2019"},{"key":"ref7","first-page":"1","article-title":"Pac-hubert: Self-supervised music source separation via primitive auditory clustering and hidden-unit bert","volume-title":"Proc. ICASSP SASB","author":"Chen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2213249"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2188515"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746655"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200911"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095596"},{"key":"ref14","first-page":"3846","article-title":"Unsupervised sound separation using mixture invariant training","volume-title":"Proc. NeurIPS","volume":"33","author":"Wisdom"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747909"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3252272"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413723"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616154"},{"key":"ref19","article-title":"Bootstrapping deep music separation from primitive auditory grouping principles","author":"Seetharaman","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632714"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1243"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1389"},{"key":"ref23","article-title":"FMA: A dataset for music analysis","author":"Defferrard","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-1363"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887819"},{"key":"ref26","article-title":"A comparative study on positional encoding for time-frequency domain dual-path transformer-based source separation models","author":"Saijo","year":"2025"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC61483.2024.10694313"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447771"},{"key":"ref29","article-title":"A two-stage band-split mamba-2 network for music separation","author":"Bai","year":"2024"},{"key":"ref30","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref31","first-page":"16 344","article-title":"Flashattention: Fast and memory-efficient exact attention with io-awareness","volume-title":"Proc. NeurIPS","volume":"35","author":"Dao"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414774"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2021.808395"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_28"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","location":"Tahoe City, CA, USA","start":{"date-parts":[[2025,10,12]]},"end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11231018.pdf?arnumber=11231018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:48:36Z","timestamp":1763192916000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11231018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11231018","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}