{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:21:04Z","timestamp":1775229664175,"version":"3.50.1"},"reference-count":49,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T00:00:00Z","timestamp":1764979200000},"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":[[2025,12,6]]},"DOI":"10.1109\/asru65441.2025.11433848","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["A correlation-permutation approach for speech-music encoders model merging"],"prefix":"10.1109","author":[{"given":"Fabian","family":"Ritter-Gutierrez","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Yi-Cheng","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Jeremy H.M","family":"Wong","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research,Singapore"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University,Taiwan"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}]},{"given":"Nancy F.","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research,Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref2","article-title":"MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training","volume-title":"International Conference on Learning Representations (ICLR)","author":"Li"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2025-747"},{"key":"ref4","article-title":"Dynamic-superb phase-2: A collaboratively expanding benchmark for measuring the capabilities of spoken language models with 180 tasks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Huang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832361"},{"key":"ref6","article-title":"Editing models with task arithmetic","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Ilharco"},{"key":"ref7","article-title":"Tiesmerging: Resolving interference when merging models","volume":"36","author":"Yadav","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Language models are super mario: Absorbing abilities from homologous models as a free lunch","volume-title":"International Conference on Machine Learning (ICML)","author":"Yu"},{"key":"ref9","article-title":"Task arithmetic for language expansion in speech translation","author":"Cheng","year":"2024","journal-title":"arXiv preprint arXiv:2409.11274"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.503"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-208"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887889"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taslpro.2025.3635827"},{"key":"ref14","article-title":"The role of permutation invariance in linear mode connectivity of neural networks","volume-title":"International Conference on Learning Representations (ICLR)","author":"Entezari"},{"key":"ref15","article-title":"Git re-basin: Merging models modulo permutation symmetries","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ainsworth"},{"key":"ref16","article-title":"Zipit! merging models from different tasks without training","volume-title":"International Conference on Learning Representations (ICLR)","author":"Stoica"},{"key":"ref17","article-title":"Merging text transformer models from different initializations","author":"Verma","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref18","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"ICML"},{"key":"ref20","article-title":"Best-first model merging for hidden markov model induction","author":"Stolcke","year":"1994","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2008.04.006"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659110"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367310"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2141"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.63317\/23tgpmzarvkw"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-419"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"ref28","article-title":"Checkpoint ensembles: Ensemble methods from a single training process","author":"Chen","year":"2017","journal-title":"arXiv preprint arXiv:1710.03282"},{"key":"ref29","first-page":"512","article-title":"What is being transferred in transfer learning?","volume":"33","author":"Neyshabur","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2016.140952"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref32","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IWSSIP48289.2020.9145170"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1722"},{"key":"ref39","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref43","first-page":"468","article-title":"Vocalset: A singing voice dataset","author":"Wilkins","year":"2018","journal-title":"ISMIR"},{"key":"ref44","first-page":"1068","article-title":"Neural audio synthesis of musical notes with wavenet autoencoders","volume-title":"International conference on machine learning. PMLR","author":"Engel"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1316"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"}],"event":{"name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,12,6]]},"end":{"date-parts":[[2025,12,10]]}},"container-title":["2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11434577\/11433836\/11433848.pdf?arnumber=11433848","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:56:02Z","timestamp":1775192162000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11433848\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11433848","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}