{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:22:24Z","timestamp":1774419744333,"version":"3.50.1"},"reference-count":42,"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"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889472","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":0,"title":["FlashSR: One-step Versatile Audio Super-resolution via Diffusion Distillation"],"prefix":"10.1109","author":[{"given":"Jaekwon","family":"Im","sequence":"first","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea"}]},{"given":"Juhan","family":"Nam","sequence":"additional","affiliation":[{"name":"KAIST,Graduate School of Culture Technology,Daejeon,South Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447246"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-555"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1994"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-36"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413575"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2605"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref8","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref9","first-page":"17022","article-title":"Hifi-gan: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"NeurIPS","author":"Kong"},{"key":"ref10","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song"},{"key":"ref11","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref13","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"ICLR","author":"Salimans"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33722"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-1333"},{"key":"ref16","article-title":"Music consistency models","author":"Fei","year":"2024"},{"key":"ref17","article-title":"Audiolcm: Text-to-audio generation with latent consistency models","author":"Liu","year":"2024"},{"key":"ref18","article-title":"Soundctm: Uniting score-based and consistency models for text-to-sound generation","author":"Saito","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547855"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612061"},{"key":"ref21","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref24","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song"},{"key":"ref25","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","volume-title":"ICLR","author":"Xiao"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00783"},{"key":"ref27","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref29","article-title":"BigVGAN: A universal neural vocoder with large-scale training","volume-title":"ICLR","author":"gil Lee"},{"key":"ref30","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"ICML","author":"Maas"},{"key":"ref31","article-title":"Highfidelity audio compression with improved rvqgan","volume-title":"NeurIPS","volume":"36","author":"Kumar"},{"key":"ref32","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","volume-title":"ICML","author":"Larsen"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10448436"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-11017"},{"key":"ref36","article-title":"Voicefixer: Toward general speech restoration with neural vocoder","author":"Liu","year":"2021"},{"key":"ref37","first-page":"155","article-title":"Medleydb: A multitrack dataset for annotation-intensive MIR research","volume-title":"ISMIR","author":"Bittner"},{"key":"ref38","article-title":"The musdb18 corpus for music separation","author":"Rafii","year":"2017"},{"key":"ref39","first-page":"619","article-title":"Moisesdb: A dataset for source separation beyond 4-stems","volume-title":"ISMIR","author":"Pereira"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref41","first-page":"316","article-title":"FMA: A dataset for music analysis","volume-title":"ISMIR","author":"Defferrard"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"}],"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\/10889472.pdf?arnumber=10889472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:24Z","timestamp":1774416264000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889472","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}