{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:52:27Z","timestamp":1781193147379,"version":"3.54.1"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Delta Research Computing Project"},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OCI 2005572"],"award-info":[{"award-number":["OCI 2005572"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"State of Illinois, Delta is a joint effort of the University of Illinois at Urbana-Champaign and its National Center for Supercomputing Applications"},{"name":"NVIDIA Corporation with the donation of the RTX 8000 GPUs"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3304482","type":"journal-article","created":{"date-parts":[[2023,8,11]],"date-time":"2023-08-11T17:28:59Z","timestamp":1691774939000},"page":"3221-3236","source":"Crossref","is-referenced-by-count":183,"title":["TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4204-9430","authenticated-orcid":false,"given":"Zhong-Qiu","family":"Wang","sequence":"first","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samuele","family":"Cornell","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Universitá Politecnica delle Marche, Ancona, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shukjae","family":"Choi","sequence":"additional","affiliation":[{"name":"Hyundai Motor Group and 42dot Inc., Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Younglo","family":"Lee","sequence":"additional","affiliation":[{"name":"Hyundai Motor Group and 42dot Inc., Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Byeong-Yeol","family":"Kim","sequence":"additional","affiliation":[{"name":"Hyundai Motor Group and 42dot Inc., Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5970-8631","authenticated-orcid":false,"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37731-1_53"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414177"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054719"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462471"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747888"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2911179"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/9781119279860.ch15"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref55","article-title":"Single-channel speech dereverberation using subband network with a reverberation time shortening target","author":"zhou","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2290"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462275"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2205"},{"key":"ref16","first-page":"7121","article-title":"Voice separation with an unknown number of multiple speakers","author":"nachmani","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413901"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIS53528.2021.9645957"},{"key":"ref51","author":"courville","year":"2016","journal-title":"Deep Learning"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3018668"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095961"},{"key":"ref46","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10727"},{"key":"ref89","first-page":"1","article-title":"Multi-channel target speaker extraction with refinement: The WAVLAB submission to the second clarity enhancement challenge","author":"cornell","year":"0","journal-title":"Proc Clarity"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2647702"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2881912"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053327"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746610"},{"key":"ref41","article-title":"SMS-WSJ: Database, performance measures, and baseline recipe for multi-channel source separation and recognition","author":"drude","year":"2019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746902"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746872"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP52302.2021.9596418"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747146"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746055"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2052251"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2941148"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683231"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462116"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1176"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2726762"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1629"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462507"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3202129"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054177"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683855"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414092"},{"key":"ref83","article-title":"On using transformers for speech-separation","author":"subakan","year":"2022"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053833"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3083405"},{"key":"ref79","first-page":"1","article-title":"Neural speech enhancement with very low algorithmic latency and complexity via integrated full- and sub-band modeling","author":"wang","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053610"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129363"},{"key":"ref36","article-title":"Leveraging low-distortion target estimates for improved speech enhancement","author":"wang","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2955276"},{"key":"ref75","first-page":"1","article-title":"NARA-WPE: A Python package for weighted prediction error dereverberation in numpy and tensorflow for online and offline processing","author":"drude","year":"0","journal-title":"Proc IEEE 13th Speech Commun ITG-Symp"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2017.8168119"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2998279"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404829"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2975902"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404828"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2842159"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632667"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145319"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746694"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-733"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1186\/s13634-016-0306-6"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-700"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383522"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21372"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2114881"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-296"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747554"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3224285"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413837"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2018.2795749"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3116502"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746882"},{"key":"ref66","first-page":"1","article-title":"BUT system for the first clarity enhancement challenge","author":"zmolikova","year":"0","journal-title":"Proc Clarity"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3099291"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682783"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094992"},{"key":"ref27","first-page":"6857","article-title":"DPT-FSNet:Dual-Path transformer based full-band and sub-band fusion network for speech enhancement","author":"dang","year":"0","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2512042"},{"key":"ref60","article-title":"Voice and accompaniment separation in music using self-attention convolutional neural network","author":"liu","year":"2020"},{"key":"ref62","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3064421"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6570655\/9970249\/10214650-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10214650.pdf?arnumber=10214650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,18]],"date-time":"2023-09-18T18:07:40Z","timestamp":1695060460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10214650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3304482","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}