{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T00:47:57Z","timestamp":1771030077038,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,31]],"date-time":"2025-08-31T00:00:00Z","timestamp":1756598400000},"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":[[2025,8,31]]},"DOI":"10.1109\/mlsp62443.2025.11204254","type":"proceedings-article","created":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T17:15:52Z","timestamp":1761326152000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["From Aesthetics to Human Preferences: Comparative Perspectives of Evaluating Text-to-Music Systems"],"prefix":"10.1109","author":[{"given":"Huan","family":"Zhang","sequence":"first","affiliation":[{"name":"Queen Mary University of London,Centre for Digial Music,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhua","family":"Liang","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digial Music,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huy","family":"Phan","sequence":"additional","affiliation":[{"name":"Reality Labs,Meta,France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"Speech and Signal Processing (CVSSP), University of Surrey,Centre for Vision,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emmanouil","family":"Benetos","sequence":"additional","affiliation":[{"name":"Queen Mary University of London,Centre for Digial Music,United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683727"},{"key":"ref2","article-title":"AudioGen: Textually guided audio generation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kreuk","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app14156543"},{"key":"ref4","author":"DeepSeek-AI","year":"2025","journal-title":"DeepSeek-R1: Incentivizing reasoning capability in llms via reinforcement learning"},{"key":"ref5","volume-title":"Qwen2.5 technical report","year":"2025"},{"key":"ref6","article-title":"DSPO: Direct score preference optimization for diffusion model alignment","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhu","year":"2025"},{"key":"ref7","volume-title":"Seed-TTS: A family of high-quality versatile speech generation models","year":"2024"},{"key":"ref8","volume-title":"Musicrl: Aligning music generation to human preferences","author":"Cideron","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref10","first-page":"4542","article-title":"BATON: Aligning text-to-audio model using human preference feedback","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, IJCAI-24","volume":"8","author":"Liao","year":"2024"},{"key":"ref11","volume-title":"DRAGON: Distributional rewards optimize diffusion generative models","author":"Bai","year":"2025"},{"key":"ref12","volume-title":"SMART: Tuning a symbolic music generation system with an audio domain aesthetic reward","author":"Jonason","year":"2025"},{"key":"ref13","article-title":"Benchmarking music generation models and metrics via human preference studies","volume-title":"Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation","author":"Solak","year":"2024"},{"key":"ref14","volume-title":"Aligning text-to-music evaluation with human preferences","author":"Huang","year":"2025"},{"key":"ref15","volume-title":"KAD: No more FAD! An effective and efficient evaluation metric for audio generation","author":"Chung","year":"2025"},{"key":"ref16","article-title":"WavCraft: Audio editing and generation with large language models","volume-title":"ICLR 2024 Workshop on Large Language Model (LLM) Agents","author":"Liang","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3574867"},{"key":"ref18","volume-title":"Bridging paintings and music \u2013 exploring emotion based music generation through paintings","author":"Hisariya","year":"2024"},{"key":"ref19","volume-title":"Hierarchical symbolic pop music generation with graph neural networks","author":"Qing Lim","year":"2024"},{"key":"ref20","volume-title":"Renderbox: Expressive performance rendering with text control","author":"Zhang","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289975"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446663"},{"key":"ref24","article-title":"Zero-shot unsupervised and text-based audio editing using DDPM inversion","volume-title":"ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling","author":"Manor","year":"2024"},{"key":"ref25","article-title":"AudioMorphix: Training-free audio editing with diffusion probabilistic models","author":"Liang","year":"2024","journal-title":"arxiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ISSC59246.2023.10162088"},{"key":"ref27","volume-title":"Meta audiobox aesthetics: Unified automatic quality assessment for speech, music, and sound","author":"Tjandra","year":"2025"},{"key":"ref28","article-title":"From Audio Encoders to Piano Judges: Benchmarking Performance Understanding for Solo Piano","author":"Zhang","year":"2024","journal-title":"Proceeding of the 25 t International Society on Music Information Retrieval (ISMIR)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP53017.2021.9733638"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890522"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890307"},{"key":"ref32","article-title":"How does the teacher rate? Observations from the NeuroPiano dataset","author":"Zhang","year":"2024","journal-title":"Late-Breaking and Demo Session of the International Society on Music Information Retrieval (ISMIR)"},{"key":"ref33","article-title":"Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation","author":"Tal","year":"2024","journal-title":"Proceeding of the 25t International Society on Music Information Retrieval (ISMIR)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888461"},{"key":"ref35","article-title":"Simple and controllable music generation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Copet","year":"2023"},{"key":"ref36","volume-title":"Yue: Scaling open foundation models for long-form music generation","year":"2025"},{"key":"ref37","article-title":"DiffRhythm: Blazingly fast and embarrassingly simple end-to-end fulllength song generation with latent diffusion","author":"Ziqian","year":"2025","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"LP-MusicCaps: LLM-based pseudo music captioning","author":"Doh","year":"2023","journal-title":"Proceeding of the 24th International Society on Music Information Retrieval (ISMIR)"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"}],"event":{"name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","location":"Istanbul, Turkiye","start":{"date-parts":[[2025,8,31]]},"end":{"date-parts":[[2025,9,3]]}},"container-title":["2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11204201\/11204202\/11204254.pdf?arnumber=11204254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T18:37:14Z","timestamp":1762367834000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11204254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,31]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/mlsp62443.2025.11204254","relation":{},"subject":[],"published":{"date-parts":[[2025,8,31]]}}}