{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:21:56Z","timestamp":1774419716076,"version":"3.50.1"},"reference-count":34,"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\/icassp49660.2025.10890104","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":1,"title":["Bridge-SR: Schr\u00f6dinger Bridge for Efficient SR"],"prefix":"10.1109","author":[{"given":"Chang","family":"Li","sequence":"first","affiliation":[{"name":"Shengshu AI,Beijing,China"}]},{"given":"Zehua","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of CST,Beijing,China"}]},{"given":"Fan","family":"Bao","sequence":"additional","affiliation":[{"name":"Shengshu AI,Beijing,China"}]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of CST,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref2","first-page":"21450","article-title":"Audioldm: text-to-audio generation with latent diffusion models","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Liu"},{"key":"ref3","article-title":"Quality-aware masked diffusion transformer for enhanced music generation","author":"Li","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-892"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-36"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-45"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2024.3432393"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA58266.2023.10248089"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888830"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-113"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095382"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095637"},{"key":"ref14","article-title":"Voicefixer: Toward general speech restoration with neural vocoder","author":"Liu","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447246"},{"key":"ref16","first-page":"71340","article-title":"Audit: Audio editing by following instructions with latent diffusion models","volume":"36","author":"Wang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3349053"},{"key":"ref18","article-title":"Specmaskgit: Masked generative modelling of audio spectrogram for efficient audio synthesis and beyond","author":"Comunita"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11017"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"Kong","year":"2020"},{"key":"ref22","article-title":"Schrodinger bridges beat diffusion models on text-to-speech synthesis","author":"Chen","year":"2023"},{"key":"ref23","article-title":"I2sb: Image-to-image schr\u00f6dinger bridge","author":"Liu","year":"2023"},{"key":"ref24","article-title":"Framebridge: Improving image-to-video generation with bridge models","author":"Wang","year":"2024"},{"key":"ref25","first-page":"271","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"key":"ref26","article-title":"Wavenet: A generative model for raw audio","volume":"12","author":"Van Den Oord","year":"2016"},{"key":"ref27","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"issue":"4","key":"ref28","first-page":"269","article-title":"Sur la th\u00e9orie relativiste de l\u2019\u00e9lectron et l\u2019interpr\u00e9tation de la m\u00e9canique quantique","volume-title":"Annales de l\u2019institut Henri Poincar\u00e9","volume":"2","author":"Schr\u00f6dinger"},{"key":"ref29","first-page":"10794","article-title":"Deep generative learning via schr\u00f6dinger bridge","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref30","article-title":"Likelihood training of schr\u00f6dinger bridge using forward-backward sdes theory","author":"Chen","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-579"},{"key":"ref32","article-title":"Diffusion-based speech enhancement with schr\u00f6dinger bridge and symmetric noise schedule","author":"Wang","year":"2024"},{"key":"ref33","article-title":"Long-form music generation with latent diffusion","author":"Evans","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096553"}],"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\/10890104.pdf?arnumber=10890104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:16Z","timestamp":1774416256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890104","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}