{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T06:38:51Z","timestamp":1775716731702,"version":"3.50.1"},"reference-count":29,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447679","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12632-12636","source":"Crossref","is-referenced-by-count":9,"title":["Seeing Through The Conversation: Audio-Visual Speech Separation Based on Diffusion Model"],"prefix":"10.1109","author":[{"given":"Suyeon","family":"Lee","sequence":"first","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaeyoung","family":"Jung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngjoon","family":"Jang","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaehun","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joon Son","family":"Chung","sequence":"additional","affiliation":[{"name":"Korea Advanced Institute of Science and Technology,South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987209"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP55362.2022.9948860"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00805"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596406"},{"key":"ref9","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. ICML","author":"Sohl-Dickstein"},{"key":"ref10","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref11","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"NeurIPS","author":"Song"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref14","article-title":"Grad-tts: A diffusion probabilistic model for text-to-speech","volume-title":"Proc. ICML","author":"Popov"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095310"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095979"},{"key":"ref18","article-title":"Is someone speaking? exploring long-term temporal features for audio-visual active speaker detection","volume-title":"Proc. ACM MM","author":"Tao"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref20","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.2307\/2288814"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref27","article-title":"LRS3-TED: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018"},{"key":"ref28","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"},{"key":"ref29","article-title":"Improved techniques for training score-based generative models","volume-title":"NeurIPS","author":"Song"}],"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\/10447679.pdf?arnumber=10447679","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:57:24Z","timestamp":1722578244000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447679\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447679","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}