{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T07:07:02Z","timestamp":1775200022763,"version":"3.50.1"},"reference-count":27,"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\/asru65441.2025.11434719","type":"proceedings-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T19:48:04Z","timestamp":1775159284000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation"],"prefix":"10.1109","author":[{"given":"Hongming","family":"Guo","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Ruibo","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Yizhong","family":"Geng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Shuchen","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Chunyu","family":"Qiang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Ya","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,Beijing,China"}]},{"given":"Zhengqi","family":"Wen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Beijing National Research Center for Information Science and Technology,Beijing,China"}]},{"given":"Yukun","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Xuefei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Chenxing","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"28","article-title":"Hmmbased text-to-audio-visual speech synthesis","volume-title":"INTERSPEECH","volume":"25","author":"Sako","year":"2000"},{"key":"ref2","article-title":"Echoaudio: Efficient and high-quality text-to-audio generation with minimal inference steps","author":"Liu","year":"2024","journal-title":"ACM Multimedia 2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3485485"},{"key":"ref4","first-page":"13 916","article-title":"Make-an-audio: Text-to-audio generation with promptenhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref5","article-title":"Make-an-audio 2: Temporal-enhanced text-toaudio generation","author":"Huang","year":"2023","journal-title":"arXiv preprint arXiv:2305.18474"},{"key":"ref6","article-title":"Diffava: Personalized text-to-audio generation with visual alignment","author":"Mo","year":"2023","journal-title":"arXiv preprint arXiv:2305.12903"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref9","article-title":"Audiopalm: A large language model that can speak and listen","author":"Rubenstein","year":"2023","journal-title":"arXiv preprint arXiv:2306.12925"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0795"},{"key":"ref11","article-title":"Uniaudio 1.5: Large language model-driven audio codec is a few-shot audio task learner","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv:2406.10056"},{"key":"ref12","article-title":"Audiogen: Textually guided audio generation","volume-title":"The Eleventh International Conference on Learning Representations","author":"Kreuk"},{"key":"ref13","article-title":"Simple and controllable music generation","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Copet"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/TASLP.2024.3399607","article-title":"Audioldm 2: Learning holistic audio generation with self-supervised pretraining","author":"Liu","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref20","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/2024.naacl-long.459","article-title":"Mustango: Toward controllable text-to-music generation","author":"Melechovsky","year":"2024"},{"key":"ref21","article-title":"Tango 2: Aligning diffusion-based text-to-audio generative models through direct preference optimization","author":"Majumder","year":"2024","journal-title":"ACM Multimedia 2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref26","article-title":"Fr\u2019echet audio distance: A metric for evaluating music enhancement algorithms","author":"Kilgour","year":"2018","journal-title":"arXiv preprint arXiv:1812.08466"},{"key":"ref27","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11434719.pdf?arnumber=11434719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T04:58:44Z","timestamp":1775192324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11434719\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/asru65441.2025.11434719","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]}}}