{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:51:22Z","timestamp":1764399082036,"version":"3.46.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/apsipaasc65261.2025.11249072","type":"proceedings-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:40:26Z","timestamp":1764355226000},"page":"950-955","source":"Crossref","is-referenced-by-count":0,"title":["End-To-End Multi-Channel Speaker Extraction and Binaural Speech Synthesis"],"prefix":"10.1109","author":[{"given":"Cheng","family":"Chi","sequence":"first","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxuan","family":"Ke","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qunping","family":"Ni","sequence":"additional","affiliation":[{"name":"Tianjin 712 Communication & Broadcasting Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Yao","sequence":"additional","affiliation":[{"name":"Tianjin Tianan Borui Technology Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengshi","family":"Zheng","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences,Laboratory of Noise and Audio Research,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Natural and augmented listening for VR, and AR\/MR","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018 tutorial","author":"Gan","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3555170"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2372062"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.urology.2021.02.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.1639908"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-444-62630-1.00006-8"},{"key":"ref7","article-title":"DopplerBAS: Binaural Audio Synthesis Addressing Doppler Effect","volume-title":"arXiv preprint","author":"Liu","year":"2022"},{"key":"ref8","article-title":"BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models","volume-title":"arXiv preprint","author":"Liang","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00221"},{"key":"ref10","article-title":"Neural synthesis of binaural speech from mono audio","volume-title":"International Conference on Learning Representations","author":"Richard","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"ref12","article-title":"Self-supervised generation of spatial audio for 360 video","volume":"31","author":"Morgado","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10055-021-00594-3"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448000"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3234034"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5120\/9970-4758"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-159"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746432"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00242-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1051\/aacus\/2022040"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747583"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521348"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0003-682X(90)90070-B"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref27","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3038"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092529"},{"issue":"2.4","key":"ref30","first-page":"1","article-title":"Room impulse response generator","volume":"2","author":"Habets","year":"2006","journal-title":"Technische Universiteit Eindhoven"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1121\/1.2936367"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1121\/1.423749"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/23312165231209913"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095300"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/29.1509"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.1955.0005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.907330"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"}],"event":{"name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2025,10,22]]},"location":"Singapore, Singapore","end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11248853\/11248968\/11249072.pdf?arnumber=11249072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:50:07Z","timestamp":1764399007000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11249072\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc65261.2025.11249072","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}