{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T05:04:30Z","timestamp":1784351070159,"version":"3.55.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2026.3702515","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T20:06:07Z","timestamp":1781121967000},"page":"2740-2744","source":"Crossref","is-referenced-by-count":0,"title":["DeRA-MOS: Optimizing Text-to-Music Evaluation via Decoupled Listwise Ranking and Modality Alignment"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1392-0058","authenticated-orcid":false,"given":"Chien-Chun","family":"Wang","sequence":"first","affiliation":[{"name":"E.SUN Financial Holding Company, Ltd., Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7044-9434","authenticated-orcid":false,"given":"Hung-Shin","family":"Lee","sequence":"additional","affiliation":[{"name":"United Link Company, Ltd., Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3599-5071","authenticated-orcid":false,"given":"Hsin-Min","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Academia Sinica, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0693-8932","authenticated-orcid":false,"given":"Berlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan Normal University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2023"},{"key":"ref2","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2066"},{"key":"ref4","first-page":"13916","article-title":"Make-an-Audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890307"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3297958"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715351"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.11.008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU65441.2025.11434795"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3602320"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2016.2545658"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00487"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390306"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0029"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU65441.2025.11434625"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC65261.2025.11249325"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU65441.2025.11434660"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.2307\/2332226"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref31","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref32","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1002\/9780471462422.eoct979"},{"key":"ref34","first-page":"5824","article-title":"Gradient surgery for multi-task learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2020"},{"key":"ref35","first-page":"5530","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref36","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kong","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2307\/2346806"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11557172.pdf?arnumber=11557172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T05:02:12Z","timestamp":1784350932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11557172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/lsp.2026.3702515","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}