{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T14:44:06Z","timestamp":1775227446790,"version":"3.50.1"},"reference-count":25,"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\/icassp48485.2024.10447612","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"13136-13140","source":"Crossref","is-referenced-by-count":38,"title":["Diffusion Models for Audio Semantic Communication"],"prefix":"10.1109","author":[{"given":"Eleonora","family":"Grassucci","sequence":"first","affiliation":[{"name":"Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy"}]},{"given":"Christian","family":"Marinoni","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy"}]},{"given":"Andrea","family":"Rodriguez","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy"}]},{"given":"Danilo","family":"Comminiello","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome,Dept. of Information Eng., Electronics and Telecom.,Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/mwc.017.2100705"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.005.2200829"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICC42927.2021.9500590"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094680"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221952"},{"key":"ref6","article-title":"Enhancing semantic communication with deep generative models \u2013 An ICASSP special session overview","volume-title":"IEEE Int. Conf. on Acoustics, Speech and Signal Process. (ICASSP)","author":"Grassucci"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps58843.2023.10464910"},{"key":"ref8","article-title":"Generative semantic communication: Diffusion models beyond bit recovery","author":"Grassucci","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095637"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095396"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285241"},{"key":"ref12","article-title":"Zero-shot image restoration using denoising diffusion null-space model","volume-title":"Int. Conf. on Learning Representations (ICLR)","author":"Wang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref14","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023"},{"key":"ref15","article-title":"Scaling instruction-finetuned language models","author":"Chung","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aaf14a"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25372"},{"key":"ref19","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"NAACL-HLT","author":"Kim"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1130"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2219"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref25","article-title":"A whisper transformer for audio captioning trained with synthetic captions and transfer learning","author":"Kadl\u010d\u00edk","year":"2023"}],"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\/10447612.pdf?arnumber=10447612","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:52:44Z","timestamp":1722577964000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447612\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447612","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}