{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:32:10Z","timestamp":1778603530735,"version":"3.51.4"},"reference-count":40,"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\/icassp48485.2024.10448429","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"12951-12955","source":"Crossref","is-referenced-by-count":19,"title":["Diffusion-Based Speech Enhancement with Joint Generative and Predictive Decoders"],"prefix":"10.1109","author":[{"given":"Hao","family":"Shi","sequence":"first","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kazuki","family":"Shimada","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masato","family":"Hirano","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Shibuya","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuichiro","family":"Koyama","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Zhong","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shusuke","family":"Takahashi","sequence":"additional","affiliation":[{"name":"Sony Group Corporation,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsuya","family":"Kawahara","sequence":"additional","affiliation":[{"name":"Kyoto University,Graduate School of Informatics,Kyoto,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuki","family":"Mitsufuji","sequence":"additional","affiliation":[{"name":"Sony AI,Tokyo,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2304637"},{"key":"ref2","article-title":"Training speech enhancement systems with noisy speech datasets","author":"Saito","year":"2021","journal-title":"arXiv"},{"key":"ref3","article-title":"Open-unmix for speech enhancement (umx se)","author":"Uhlich","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2012-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639038"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/HSCMA.2014.6843279"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.101.2100269"},{"key":"ref9","article-title":"Generative semantic communication: Diffusion models beyond bit recovery","author":"Grassucci","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/mwc.001.2300346"},{"key":"ref11","article-title":"Enhancing Semantic Communication with Deep Generative Models \u2013 An ICASSP Special Session Overview","author":"Grassucci","year":"2023","journal-title":"arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2364452"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745591"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/89.397090"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6489"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2968738"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054661"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2021.108499"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1428"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746901"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3294692"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2018.8516711"},{"key":"ref27","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. NIPS","volume":"32","author":"Song"},{"key":"ref28","first-page":"21 696","article-title":"Variational diffusion models","volume-title":"Proc. NIPS","volume":"34","author":"Kingma"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095046"},{"key":"ref30","article-title":"Noise-aware speech enhancement using diffusion probabilistic model","author":"Hu","year":"2023","journal-title":"arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1547"},{"key":"ref32","article-title":"Universal Speech Enhancement with Score-based Diffusion","author":"Serr\u00e0","year":"2022","journal-title":"arXiv"},{"key":"ref33","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref35","first-page":"22 863","article-title":"A variational perspective on diffusion-based generative models and score matching","volume-title":"Proc. NIPS","volume":"34","author":"Huang"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14394-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/ssw.2016-24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"}],"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\/10448429.pdf?arnumber=10448429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:53:45Z","timestamp":1722660825000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448429","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}