{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T15:24:16Z","timestamp":1787671456017,"version":"build-2736575974"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100013243","name":"British Broadcasting Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013243","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447246","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"1076-1080","source":"Crossref","is-referenced-by-count":41,"title":["Audiosr: Versatile Audio Super-Resolution at Scale"],"prefix":"10.1109","author":[{"given":"Haohe","family":"Liu","sequence":"first","affiliation":[{"name":"University of Surrey,Centre for Vision Speech and Signal Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Chen","sequence":"additional","affiliation":[{"name":"University of California San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Tian","sequence":"additional","affiliation":[{"name":"ByteDance,Speech, Audio & Music Intelligence (SAMI)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenwu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision Speech and Signal Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark D.","family":"Plumbley","sequence":"additional","affiliation":[{"name":"University of Surrey,Centre for Vision Speech and Signal Processing"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"VoiceFixer: Toward general speech restoration with neural vocoder","author":"Liu","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.885934"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3054302"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-36"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2605"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596082"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-45"},{"key":"ref9","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"International Conference on Machine Learning","author":"Liu"},{"key":"ref10","article-title":"Simple and controllable music generation","author":"Copet","year":"2023"},{"key":"ref11","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","volume-title":"International Conference on Learning Representations","author":"Ren"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00532"},{"key":"ref14","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"International Conference on Learning Representations","author":"Salimans"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3399607"},{"key":"ref16","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref17","first-page":"17 022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Advances in neural information processing systems","volume":"33","author":"Kong"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-41"},{"key":"ref19","author":"Rafii","year":"2019","journal-title":"MUSDB18-HQ - an uncompressed version of MUSDB18"},{"key":"ref20","article-title":"MoisesDB: A dataset for source separation beyond 4-stems","author":"Pereira","year":"2023"},{"key":"ref21","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive mir research","volume-title":"ISMIR","volume":"14","author":"Bittner"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref23","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023"},{"key":"ref24","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"NAACL-HLT","author":"Kim"},{"key":"ref25","volume-title":"The LJSpeech dataset","author":"Ito","year":"2017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447246.pdf?arnumber=10447246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:43:52Z","timestamp":1722573832000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447246","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}