{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T20:48:56Z","timestamp":1773262136065,"version":"3.50.1"},"reference-count":30,"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\/icassp49357.2023.10095818","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":21,"title":["Learning Audio-Visual Dereverberation"],"prefix":"10.1109","author":[{"given":"Changan","family":"Chen","sequence":"first","affiliation":[{"name":"UT Austin"}]},{"given":"Wei","family":"Sun","sequence":"additional","affiliation":[{"name":"UT Austin"}]},{"given":"David","family":"Harwath","sequence":"additional","affiliation":[{"name":"UT Austin"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[{"name":"UT Austin"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Acoustic room modelling using 360 stereo cameras","author":"kim","year":"2020","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref12","article-title":"Learning neural acoustic fields","author":"luo","year":"2022","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref14","article-title":"SoundSpaces: Audiovisual navigation in 3d environments","author":"chen","year":"2020","journal-title":"ECCV"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"ref10","article-title":"Few-shot audio-visual learning of environment acoustics","author":"majumder","year":"2022","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1109\/JSTSP.2019.2917582","article-title":"Building and evaluation of a real room? impulse response dataset","author":"sz\u00f6ke","year":"2019","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref17","article-title":"Digging into self-supervised monocular depth prediction","author":"godard","year":"2019","journal-title":"ICCV"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1121\/1.383069"},{"key":"ref19","first-page":"129","article-title":"Openair: An interactive auralization web resource and database","author":"murphy","year":"2010","journal-title":"Audio Engineering Society Convention"},{"key":"ref18","article-title":"A binaural room impulse response database for the evaluation of dereverberation algorithms","author":"marco jeub","year":"2009","journal-title":"Proceedings of International Conference on Digital Signal Processing"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2143"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-599"},{"key":"ref20","article-title":"The replica dataset: A digital replica of indoor spaces","author":"straub","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref28","article-title":"Speechbrain","author":"ravanelli","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1454"},{"key":"ref8","article-title":"MetricGAN: Generative adversarial networks based black-box metric scores optimization for speech enhancement","author":"fu","year":"2019","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-84996-056-4"},{"key":"ref9","article-title":"Learning audio-visual dereverberation","author":"chen","year":"2021"},{"key":"ref4","article-title":"A reverberation-time-aware approach to speech dereverberation based on deep neural networks","author":"wu","year":"2016","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref3","article-title":"Learning spectral mapping for speech dereverberation and denoising","author":"han","year":"2015","journal-title":"IEEE Trans Audio Speech Lang Process"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2870725"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"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\/10095818.pdf?arnumber=10095818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:08:25Z","timestamp":1700507305000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095818","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}