{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:11:53Z","timestamp":1775200313412,"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\/asru65441.2025.11434795","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":["ASTAR-NTU solution to AudioMOS Challenge 2025 Track1"],"prefix":"10.1109","author":[{"given":"Fabian","family":"Ritter-Gutierrez","sequence":"first","affiliation":[{"name":"Institute for Infocomm Research (A* STAR)"}]},{"given":"Yi-Cheng","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Jui-Chiang","family":"Wei","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]},{"given":"Jeremy H.M.","family":"Wong","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (A* STAR)"}]},{"given":"Nancy F.","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research (A* STAR)"}]},{"given":"Hung-Yi","family":"Lee","sequence":"additional","affiliation":[{"name":"National Taiwan University"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning (ICML)","author":"Liu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref3","article-title":"Audiox: Diffusion transformer for anything-to-audio generation","author":"Tian","year":"2025","journal-title":"ArXiv Preprint"},{"key":"ref4","article-title":"Musiceval: A generative music corpus with expert ratings for automatic text-to-music evaluation","author":"Liu","year":"2025","journal-title":"ICASSP"},{"key":"ref5","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv preprint arXiv:2301.11325"},{"key":"ref6","first-page":"47704","article-title":"Simple and controllable music generation","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Copet"},{"key":"ref7","article-title":"Audiogen: Textually guided audio generation","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kreuk"},{"key":"ref8","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with promptenhanced diffusion models","volume-title":"International Conference on Machine Learning. PMLR","author":"Huang"},{"key":"ref9","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2302.03917"},{"key":"ref10","article-title":"Musecoco: Generating symbolic music from text","author":"Lu","year":"2023","journal-title":"arXiv preprint arXiv:2306.00110"},{"key":"ref11","article-title":"Ernie-music: Text-to-waveform music generation with diffusion models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv:2302.04456"},{"key":"ref12","article-title":"Mo\u00e4sai: Text-tomusic generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3602320"},{"key":"ref15","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.11.008"},{"key":"ref17","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani"},{"key":"ref18","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","volume-title":"First Conference on Language Modeling","author":"Gu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2307\/1267351"},{"key":"ref21","article-title":"Lightgbm: A highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"Metaperser: Few-shot listener personalized speech emotion recognition via meta-learning","author":"Shen","year":"2025"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3297958"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715351"},{"key":"ref25","article-title":"800.2: Mean opinion score interpretation and reporting","volume-title":"Tech. rep, Tech. Rep.","year":"2016"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-74"}],"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\/11434795.pdf?arnumber=11434795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:59:52Z","timestamp":1775192392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434795\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434795","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}