{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:48:11Z","timestamp":1783529291724,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS-2125074"],"award-info":[{"award-number":["ECCS-2125074"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017186","name":"Ohio Supercomputer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017186","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NCSA Delta Supercomputer Center","award":["OCI 2005572"],"award-info":[{"award-number":["OCI 2005572"]}]},{"name":"Pittsburgh Supercomputer Center","award":["NSF ACI-1928147"],"award-info":[{"award-number":["NSF ACI-1928147"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3492803","type":"journal-article","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T18:44:42Z","timestamp":1730918682000},"page":"4999-5009","source":"Crossref","is-referenced-by-count":23,"title":["TF-CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4166-1935","authenticated-orcid":false,"given":"Vahid Ahmadi","family":"Kalkhorani","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8195-6319","authenticated-orcid":false,"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3282097"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3202129"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3304482"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2975902"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3357036"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3393726"},{"key":"ref16","article-title":"Analysis of positional encodings for neural machine translation","volume-title":"Proc. Spoken Lang. Transl.","author":"Rosendahl","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3163856"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3083405"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145319"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.161"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.2019.8683855"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-157"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref28","article-title":"SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition","author":"Drude","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref30","article-title":"The kaldi speech recognition toolkit","volume-title":"Proc. Workshop Autom. Speech Recognit. Understanding","author":"Povey","year":"2011"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icassp.1995.479278"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2005.1566470"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2585878"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21105\/joss.04101"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383615"},{"key":"ref40","article-title":"ESPnet2 pretrained model","author":"Wang","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_53"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIS53528.2021.9645957"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413837"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747554"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21372"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-700"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096646"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095037"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632667"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054177"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053833"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref54","first-page":"1","article-title":"NARA-WPE: A python package for weighted prediction error dereverberation in numpy and tensorflow for online and offline processing","volume-title":"Proc. IEEE 13th Speech Commun.; ITG- Symp.","author":"Drude","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2911179"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2432"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/10304349\/10745728-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10745728.pdf?arnumber=10745728","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:42:24Z","timestamp":1732736544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10745728\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3492803","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}