{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:08:48Z","timestamp":1776884928214,"version":"3.51.2"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890826","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Dual Position Attention Time-Frequency Network for Binaural Audio Synthesis"],"prefix":"10.1109","author":[{"given":"Changjun","family":"He","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiping","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingjiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen),Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9780080498195"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2666081"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1051\/aacus\/2022040"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/pres.1996.5.3.290"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1121\/1.1639908"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4236\/nm.2010.11004"},{"issue":"9","key":"ref7","first-page":"675","article-title":"Creating interactive virtual acoustic environments","volume":"47","author":"Savioja","year":"1999","journal-title":"Journal of the Audio Engineering Society"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2372062"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.827516"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096144"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app7050532"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.5005606"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3066303"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref15","article-title":"Review of end-to-end speech synthesis technology based on deep learning","author":"Mu","year":"2021"},{"key":"ref16","article-title":"Neural synthesis of binaural speech from mono audio","volume-title":"International Conference on Learning Representations (ICLR)","author":"Richard"},{"key":"ref17","first-page":"23 689","article-title":"Binauralgrad: A two-stage conditional diffusion probabilistic model for binaural audio synthesis","volume":"35","author":"Leng","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10603"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095685"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414750"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746135"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00221"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00041"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00995"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3460426.3463624"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803494"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00194"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16302"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480560"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111814"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/89.709673"},{"key":"ref33","volume-title":"The Doppler effect : an introduction to the theory of the effect.","author":"Gill","year":"1965"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2006.12.003"},{"key":"ref35","article-title":"Melgan: Generative adversarial networks for conditional waveform synthesis","volume":"32","author":"Kumar","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref36","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref37","article-title":"Wavenet: A generative model for raw audio","volume":"12","author":"Van Den Oord","year":"2016"},{"key":"ref38","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref39","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/app14083385"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890826.pdf?arnumber=10890826","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:07Z","timestamp":1774416307000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890826\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890826","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}