{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:45:44Z","timestamp":1776887144840,"version":"3.51.2"},"reference-count":40,"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\/icassp49660.2025.10890307","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":12,"title":["MusicEval: A Generative Music Dataset with Expert Ratings for Automatic Text-to-Music Evaluation"],"prefix":"10.1109","author":[{"given":"Cheng","family":"Liu","sequence":"first","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinghua","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiwan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Bu","sequence":"additional","affiliation":[{"name":"Beijing AISHELL Technology Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing AISHELL Technology Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoqin","family":"Sun","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Qin","sequence":"additional","affiliation":[{"name":"Nankai University,TMCC, College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Musiclm: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref2","first-page":"47704","article-title":"Simple and controllable music generation","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Copet","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref4","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Ho","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref7","article-title":"A note on the inception score","author":"Barratt","year":"2018"},{"key":"ref8","article-title":"A comprehensive survey for evaluation methodologies of ai-generated music","author":"Xiong","year":"2023"},{"key":"ref9","article-title":"Evaluating generative audio systems and their metrics","author":"Vinay","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414878"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-299"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11295"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746395"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-851"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-937"},{"key":"ref16","article-title":"Singmos: An extensive open-source singing voice dataset for mos prediction","author":"Tang","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref18","article-title":"Noise2music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref19","article-title":"Ernie-music: Text-to-waveform music generation with diffusion models","author":"Zhu","year":"2023"},{"key":"ref20","article-title":"Musecoco: Generating symbolic music from text","author":"Lu","year":"2023"},{"key":"ref21","article-title":"Masked audio generation using a single non-autoregressive transformer","author":"Ziv","year":"2024"},{"key":"ref22","article-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref23","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref27","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref28","article-title":"Uniaudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023"},{"key":"ref29","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022"},{"key":"ref30","article-title":"Suno official website","year":"2024"},{"key":"ref31","article-title":"Udio official website","year":"2024"},{"key":"ref32","article-title":"Skymusic official website","year":"2024"},{"key":"ref33","article-title":"qqmusic official website","year":"2024"},{"key":"ref34","article-title":"mubert official website","year":"2024"},{"key":"ref35","article-title":"riffusion official website","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3597493"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447667"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2525"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"}],"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\/10890307.pdf?arnumber=10890307","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:23:09Z","timestamp":1774416189000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890307\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890307","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}