{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T20:48:10Z","timestamp":1763412490730,"version":"3.45.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2025,10,12]]},"DOI":"10.1109\/waspaa66052.2025.11230991","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:47Z","timestamp":1763146007000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Conditioned Wave-U-Net for Acoustic Matching of Speech in Shared XR Environments"],"prefix":"10.1109","author":[{"given":"Joanna","family":"Luberadzka","sequence":"first","affiliation":[{"name":"Centre Tecnòlogic de Catalunya, Tecnologies Multimèdia,Eurecat,Barcelona"}]},{"given":"Enric","family":"Gus\u00f3","sequence":"additional","affiliation":[{"name":"Centre Tecnòlogic de Catalunya, Tecnologies Multimèdia,Eurecat,Barcelona"}]},{"given":"Umut","family":"Sayin","sequence":"additional","affiliation":[{"name":"Centre Tecnòlogic de Catalunya, Tecnologies Multimèdia,Eurecat,Barcelona"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/23312165221092919"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10612-2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF01211654"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3385270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP55844.2023.10285887"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10890782"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2577502"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052970"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3193298"},{"key":"ref11","first-page":"244","article-title":"Differentiable feedback delay network for colorless reverberation","volume-title":"International Conference on Digital Audio Effects","author":"Dal Santo"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414038"},{"key":"ref13","article-title":"Blind arbitrary reverb matching","volume-title":"Proceedings of the 23rd International Conference on Digital Audio Effects (DAFx-2020)","volume":"2","author":"Sarroff"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447818"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054701"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3302506.3310398"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2045183"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747055"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1167\/16.12.326"},{"article-title":"Wave-u-net: A multi-scale neural network for end-to-end audio source separation","year":"2018","author":"Stoller","key":"ref21"},{"article-title":"Hybrid spectrogram and waveform source separation","year":"2021","author":"D\u00e9fossez","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0028"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414280"},{"article-title":"Real-time streaming wave-u-net with temporal convolutions for multichannel speech enhancement","year":"2021","author":"Kuzmin","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"article-title":"Modulated variational auto-encoders for many-to-many musical timbre transfer","year":"2018","author":"Bitton","key":"ref27"},{"article-title":"Diff-ssl-g-comp: Towards a large-scale and diverse dataset for virtual analog modeling","year":"2025","author":"Gu","key":"ref28"},{"key":"ref29","first-page":"271","article-title":"Cstr vctk corpus: English multi-speaker corpus for cstr voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019","journal-title":"University of Edinburgh. The Centre for Speech Technology Research (CSTR)"},{"article-title":"A python library for multichannel acoustic signal processing","volume-title":"Audio Engineering Society Convention 148","author":"Perez-Lopez","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053795"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096509"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.7.1493"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1121\/1.3097493"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096680"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052247"},{"key":"ref40","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","volume":"2","author":"Series","year":"2014","journal-title":"International Telecommunication Union Radiocommunication Assembly"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1002\/0470011815.b2a15177"}],"event":{"name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","start":{"date-parts":[[2025,10,12]]},"location":"Tahoe City, CA, USA","end":{"date-parts":[[2025,10,15]]}},"container-title":["2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11230875\/11230917\/11230991.pdf?arnumber=11230991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T18:38:38Z","timestamp":1763404718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11230991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/waspaa66052.2025.11230991","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]}}}