{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:29:36Z","timestamp":1778171376840,"version":"3.51.4"},"reference-count":27,"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\/icassp49660.2025.10890477","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Conditional Latent Diffusion-Based Speech Enhancement via Dual Context Learning"],"prefix":"10.1109","author":[{"given":"Shengkui","family":"Zhao","sequence":"first","affiliation":[{"name":"Alibaba Group,Tongyi Lab,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zexu","family":"Pan","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yukun","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Ma","sequence":"additional","affiliation":[{"name":"Alibaba Group,Tongyi Lab,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-599"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3294692"},{"key":"ref6","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. of ICML","author":"Sohl-Dickstein"},{"key":"ref7","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"ref8","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC58517.2023.10317412"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref12","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref13","article-title":"Audit: Audio editing by following instructions with latent diffusion models","author":"Wang","year":"2023"},{"key":"ref14","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2022"},{"key":"ref16","article-title":"Bigvgan: A universal neural vocoder with large-scale training","author":"Lee","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2016-24"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097255"},{"key":"ref25","article-title":"DNSMOS p.835: A non-intrusive perceptual objective speech quality metric to evaluate noise suppressors","author":"Chandan","year":"2022"},{"key":"ref26","article-title":"Beats: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022"},{"key":"ref27","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"}],"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\/10890477.pdf?arnumber=10890477","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:07Z","timestamp":1774416307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890477\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890477","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}