{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:17:20Z","timestamp":1774419440026,"version":"3.50.1"},"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890304","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":2,"title":["Exploring Acoustic Similarity in Emotional Speech and Music via Self-Supervised Representations"],"prefix":"10.1109","author":[{"given":"Yujia","family":"Sun","sequence":"first","affiliation":[{"name":"University of Edinburgh,UK"}]},{"given":"Zeyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Edinburgh,UK"}]},{"given":"Korin","family":"Richmond","sequence":"additional","affiliation":[{"name":"University of Edinburgh,UK"}]},{"given":"Yuanchao","family":"Li","sequence":"additional","affiliation":[{"name":"University of Edinburgh,UK"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/79.911197"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.2000-287"},{"key":"ref3","first-page":"937","article-title":"Music emotion recognition: A state of the art review","volume-title":"Proc. ISMIR","volume":"86","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2168752.2168754"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0179289"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACII.2015.7344563"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472790"},{"key":"ref8","first-page":"1298","article-title":"data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Baevski"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475576"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023428"},{"key":"ref11","article-title":"Mert: Acoustic music understanding model with large-scale self-supervised training","author":"Li","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9334"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287548"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW62465.2024.10627629"},{"key":"ref18","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref19","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"International conference on machine learning","author":"Houlsby"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446272"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10889008"},{"key":"ref22","first-page":"2350","article-title":"Fr\u00e9chet audio distance: A reference-free metric for evaluating music enhancement algorithms","volume-title":"Proc. Interspeech","author":"Roblek"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"key":"ref24","article-title":"Rethinking emotion bias in music via frechet audio distance","author":"Li","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023234"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1097\/WNR.0b013e3282f0b787"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/1029864914542842"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367152"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367261"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688093"}],"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\/10890304.pdf?arnumber=10890304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:54Z","timestamp":1774416174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890304\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890304","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}