{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:10:48Z","timestamp":1775200248191,"version":"3.50.1"},"reference-count":26,"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\/asru65441.2025.11434767","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-4","source":"Crossref","is-referenced-by-count":0,"title":["DyMEvalNet: Dynamic Text-Audio-Personalization Fusion for Multimodal Music Quality Assessment"],"prefix":"10.1109","author":[{"given":"Xiaoxun","family":"Wu","sequence":"first","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China"}]},{"given":"Kailai","family":"Shen","sequence":"additional","affiliation":[{"name":"Juphoon System Software Co., Ltd,Ningbo,China"}]},{"given":"Yuheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China"}]},{"given":"Naiyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China"}]},{"given":"Diqun","family":"Yan","sequence":"additional","affiliation":[{"name":"Ningbo University,Faculty of Electrical Engineering and Computer Science,Ningbo,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447869"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1508"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095710"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445996"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2574"},{"key":"ref7","article-title":"SingMOS: An extensive Open-Source Singing Voice Dataset for MOS Prediction","author":"Tang","year":"2024","journal-title":"arXiv e-prints, p. arXiv:2406.10911"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3525969"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"key":"ref10","article-title":"Songeval: A benchmark dataset for song aesthetics evaluation","author":"Yao","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-325"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890307"},{"key":"ref13","article-title":"Inspiremusic: Integrating super resolution and large language model for high-fidelity long-form music generation","volume":"abs\/2503.00084","author":"Zhang","year":"2025","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747222"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2525"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref19","article-title":"Automos: Learning a non-intrusive assessor of naturalness-of-speech","volume":"abs\/1611.09207","author":"Patton","year":"2016","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1802"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2003"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683770"},{"key":"ref23","first-page":"482","article-title":"Stoinet: A deep learning based non-intrusive speech intelligibility assessment model","volume-title":"2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","author":"Zezario"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413877"},{"key":"ref25","article-title":"Seed-music: A unified framework for high quality and controlled music generation","volume":"abs\/2409.09214","author":"Bai","year":"2024","journal-title":"CoRR"},{"key":"ref26","article-title":"Long-form music generation with latent diffusion","volume":"abs\/2404.10301","author":"Evans","year":"2024","journal-title":"CoRR"}],"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\/11434767.pdf?arnumber=11434767","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:30Z","timestamp":1775192370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434767\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434767","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}