{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:00:57Z","timestamp":1776445257320,"version":"3.51.2"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFC2004003"],"award-info":[{"award-number":["2020YFC2004003"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3545065","type":"journal-article","created":{"date-parts":[[2025,2,24]],"date-time":"2025-02-24T18:41:32Z","timestamp":1740422492000},"page":"36701-36713","source":"Crossref","is-referenced-by-count":4,"title":["Hybrid Convolutional Neural Network-Transformer Model for End-to-End Binaural Sound Source Localization in Reverberant Environments"],"prefix":"10.1109","volume":"13","author":[{"given":"Xinyi","family":"Chen","sequence":"first","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8188-7519","authenticated-orcid":false,"given":"Lijia","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9391-6744","authenticated-orcid":false,"given":"Jie","family":"Cui","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7470-2924","authenticated-orcid":false,"given":"Hua","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6525-2362","authenticated-orcid":false,"given":"Xiaodong","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-022-09747-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2183869"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDSP.2011.6004954"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2011.2180376"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-020-0171-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1828\/1\/012017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909764"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2750760"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/5819624"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1049\/joe.2019.1207"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905617"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12009"},{"key":"ref13","first-page":"432","article-title":"Full-sphere binaural sound source localization using multi-task neural network","volume-title":"Proc. Asia\u2013Pacific Signal Inf. Process. Assoc. Annu. Summit Conf. (APSIPA ASC)","author":"Yang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2855960"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446210"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120641"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413923"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683732"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268734"},{"key":"ref21","first-page":"275","article-title":"An end-to-end binaural sound localization model based on the equalization and cancellation theory","volume-title":"Proc. Audio Eng. Soc. Conv.","author":"Song"},{"key":"ref22","first-page":"58","article-title":"The pre-response stimulus ensemble of neurons in the cochlear nucleus","volume-title":"Proc. Symp. Hear. Theory","author":"Johannesma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref24","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref25","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref26","volume-title":"HRFT measurements of a KEMAR dummy-head microphone","author":"Gardner","year":"1994"},{"issue":"3","key":"ref27","first-page":"48","article-title":"A MATLAB simulation of \u2019shoebox\u2019 room acoustics for use in research and teaching","volume":"9","author":"Campbell","year":"2005","journal-title":"Comput. Inf. Syst."},{"key":"ref28","volume-title":"DARPA TIMIT acoustic phonetic continuous speech corpus CDROM","author":"Garofolo","year":"4930"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6393(93)90095-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1121\/1.2987429"},{"key":"ref31","first-page":"6072","article-title":"Direction of arrival estimation in noisy and reverberant acoustic environments using convolutional recurrent neural networks","volume-title":"Proc. ICASSP","author":"May"},{"issue":"5","key":"ref32","first-page":"2832","article-title":"Binaural modeling of speech intelligibility based on a signal-to-noise ratio in the envelope domain","volume":"129","author":"May","year":"2011","journal-title":"J. Acoust. Soc. Amer."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10902008.pdf?arnumber=10902008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T05:59:55Z","timestamp":1741067995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10902008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3545065","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}