{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:32:53Z","timestamp":1763202773386,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10095979","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["SEPDIFF: Speech Separation Based on Denoising Diffusion Model"],"prefix":"10.1109","author":[{"given":"Bo","family":"Chen","sequence":"first","affiliation":[{"name":"Huawei Technologies,Hangzhou,China"}]},{"given":"Chao","family":"Wu","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Hangzhou,China"}]},{"given":"Wenbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Huawei Technologies,Hangzhou,China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383612"},{"journal-title":"Nu-gan High resolution neural upsampling with gan","year":"2020","author":"kumar","key":"ref24"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3039944"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414901"},{"key":"ref15","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3019495"},{"journal-title":"Bigvgan A universal neural vocoder with large-scale training","year":"2022","author":"lee","key":"ref20"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461671"},{"journal-title":"Int Telecommunication Union","article-title":"Perceptual objective listening quality prediction","year":"2018","key":"ref22"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462505"},{"journal-title":"LibriMix An open-source dataset for generalizable speech separation","year":"2020","author":"cosentino","key":"ref21"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1109\/TASLP.2017.2726762","article-title":"Multi-talker speech separation with utterance-level permutation invariant training of deep recurrent neural networks","volume":"25","author":"tan","year":"2017","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref16","first-page":"659","article-title":"A study on speech enhancement based on diffusion probabilistic model","author":"lu","year":"2021","journal-title":"Proc APSIPA ASC"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"journal-title":"Speech enhancement with score-based generative models in the complex stft domain","year":"2022","author":"welker","key":"ref18"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21372"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"journal-title":"Tf-gridnet Making time-frequency domain models great again for monaural speaker separation","year":"2022","author":"wang","key":"ref9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref3","first-page":"697","article-title":"Tasnet: Time-domain audio separation network for real-time, single-channel speech separation","author":"luo","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref5","article-title":"Sudo rm -rf: Efficient networks for universal audio source separation","author":"wang e tzinis","year":"2020","journal-title":"Proc MLSP"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10095979.pdf?arnumber=10095979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T18:57:05Z","timestamp":1699901825000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095979\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095979","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}