{"id":"https://openalex.org/W4385756463","doi":"https://doi.org/10.1109/taslp.2023.3304482","title":"TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation","display_name":"TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385756463","doi":"https://doi.org/10.1109/taslp.2023.3304482"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3304482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3304482","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Department of Information Engineering, Universitá Politecnica delle Marche, Ancona, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universitá Politecnica delle Marche, Ancona, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046390548","display_name":"Shukjae Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shukjae Choi","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc., Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, South Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024990167","display_name":"Younglo Lee","orcid":"https://orcid.org/0000-0002-0725-3444"},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younglo Lee","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc., Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, South Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc., Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, South Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":29.6871,"has_fulltext":false,"cited_by_count":152,"citation_normalized_percentile":{"value":0.99870162,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"3221","last_page":"3236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7198323607444763},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6525560617446899},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.589677095413208},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5641418695449829},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5366001129150391},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5067251324653625},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.48059865832328796},{"id":"https://openalex.org/keywords/monaural","display_name":"Monaural","score":0.4495111107826233},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4451243579387665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3167235255241394},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.252108097076416},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22277477383613586},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11002856492996216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7198323607444763},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6525560617446899},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.589677095413208},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5641418695449829},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5366001129150391},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5067251324653625},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.48059865832328796},{"id":"https://openalex.org/C102894143","wikidata":"https://www.wikidata.org/wiki/Q1323979","display_name":"Monaural","level":2,"score":0.4495111107826233},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4451243579387665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3167235255241394},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.252108097076416},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22277477383613586},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11002856492996216},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3304482","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3304482","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7599999904632568}],"awards":[{"id":"https://openalex.org/G2642208862","display_name":null,"funder_award_id":"OCI 2005572","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":99,"referenced_works":["https://openalex.org/W2127851351","https://openalex.org/W2141998673","https://openalex.org/W2164502538","https://openalex.org/W2221409856","https://openalex.org/W2242685705","https://openalex.org/W2288645994","https://openalex.org/W2289480995","https://openalex.org/W2291877678","https://openalex.org/W2568308529","https://openalex.org/W2734774145","https://openalex.org/W2735663686","https://openalex.org/W2747732471","https://openalex.org/W2763188033","https://openalex.org/W2774389566","https://openalex.org/W2800022361","https://openalex.org/W2889540509","https://openalex.org/W2890401420","https://openalex.org/W2891405874","https://openalex.org/W2900893004","https://openalex.org/W2905402910","https://openalex.org/W2952218014","https://openalex.org/W2962715207","https://openalex.org/W2962866211","https://openalex.org/W2962905190","https://openalex.org/W2962935966","https://openalex.org/W2963189033","https://openalex.org/W2963197115","https://openalex.org/W2963317762","https://openalex.org/W2964058413","https://openalex.org/W2972460025","https://openalex.org/W2982456909","https://openalex.org/W2991361823","https://openalex.org/W2996969697","https://openalex.org/W3007256793","https://openalex.org/W3012897083","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3015679215","https://openalex.org/W3015794161","https://openalex.org/W3016094953","https://openalex.org/W3032514799","https://openalex.org/W3035268204","https://openalex.org/W3042857426","https://openalex.org/W3086154751","https://openalex.org/W3094607766","https://openalex.org/W3096893582","https://openalex.org/W3099330747","https://openalex.org/W3124972797","https://openalex.org/W3126427729","https://openalex.org/W3134695619","https://openalex.org/W3151596526","https://openalex.org/W3158779859","https://openalex.org/W3160085755","https://openalex.org/W3160903688","https://openalex.org/W3163652268","https://openalex.org/W3171278394","https://openalex.org/W3185109982","https://openalex.org/W3195155284","https://openalex.org/W3197627016","https://openalex.org/W3201698955","https://openalex.org/W3203119473","https://openalex.org/W3211779545","https://openalex.org/W3213747130","https://openalex.org/W3215005424","https://openalex.org/W4200598930","https://openalex.org/W4205689591","https://openalex.org/W4210402803","https://openalex.org/W4211261061","https://openalex.org/W4221149546","https://openalex.org/W4221165117","https://openalex.org/W4223583411","https://openalex.org/W4224931234","https://openalex.org/W4224931672","https://openalex.org/W4224932531","https://openalex.org/W4224936432","https://openalex.org/W4225270933","https://openalex.org/W4225310539","https://openalex.org/W4283794752","https://openalex.org/W4294891356","https://openalex.org/W4295312788","https://openalex.org/W4296068774","https://openalex.org/W4297841651","https://openalex.org/W4311187069","https://openalex.org/W4321276703","https://openalex.org/W4366458450","https://openalex.org/W4372271367","https://openalex.org/W4375868849","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6766380642","https://openalex.org/W6766978945","https://openalex.org/W6769802879","https://openalex.org/W6774995033","https://openalex.org/W6775369996","https://openalex.org/W6794544138","https://openalex.org/W6802205285","https://openalex.org/W6850377926","https://openalex.org/W6852238222"],"related_works":["https://openalex.org/W2621851636","https://openalex.org/W2103031592","https://openalex.org/W4389082013","https://openalex.org/W1967226023","https://openalex.org/W2538939196","https://openalex.org/W2380771148","https://openalex.org/W2955471771","https://openalex.org/W2348931051","https://openalex.org/W2538903081","https://openalex.org/W2389562147"],"abstract_inverted_index":{"We":[0,72,142],"propose":[1],"TF-GridNet":[2,145],"for":[3,105],"speech":[4,215,219,238],"separation.":[5,80,107],"The":[6],"model":[7],"is":[8,46,179,196,223],"a":[9,36,41,90,102,158,162,180,226],"novel":[10,181],"deep":[11],"neural":[12],"network":[13],"(DNN)":[14],"integrating":[15],"full-":[16],"and":[17,40,56,85,114,128,135,154,204,217,229],"sub-band":[18,37],"modeling":[19],"in":[20,95,164,169,176],"the":[21,54,125,173,188,191,199,211,231,234],"time-frequency":[22],"(T-F)":[23],"domain.":[24],"It":[25,45],"stacks":[26],"several":[27],"blocks,":[28],"each":[29],"consisting":[30],"of":[31,60,190,202,233],"an":[32],"intra-frame":[33],"full-band":[34],"module,":[35,39],"temporal":[38],"cross-frame":[42],"self-attention":[43],"module.":[44],"trained":[47],"to":[48,67,112,146,214],"perform":[49],"complex":[50,151],"spectral":[51,152],"mapping,":[52,153],"where":[53,172],"real":[55],"imaginary":[57],"(RI)":[58],"components":[59],"input":[61],"signals":[62],"are":[63],"stacked":[64],"as":[65,167],"features":[66],"predict":[68],"target":[69],"RI":[70],"components.":[71],"first":[73,192],"evaluate":[74,117],"it":[75,88,118,156],"on":[76,100,119,129,139,187,198,225,230],"monaural":[77,120],"anechoic":[78],"speaker":[79,122,131,207],"Without":[81],"using":[82,124,133],"data":[83],"augmentation":[84],"dynamic":[86],"mixing,":[87],"obtains":[89],"state-of-the-art":[91,137],"23.5":[92],"dB":[93],"improvement":[94],"scale-invariant":[96],"signal-to-distortion":[97],"ratio":[98],"(SI-SDR)":[99],"WSJ0-2mix,":[101],"standard":[103],"dataset":[104,127,228,232],"two-speaker":[106],"To":[108],"show":[109],"its":[110],"robustness":[111],"noise":[113],"reverberation,":[115],"we":[116,209],"reverberant":[121],"separation":[123,132],"SMS-WSJ":[126,203],"noisy-reverberant":[130,218],"WHAMR!,":[134],"obtain":[136],"performance":[138,195,222],"both":[140],"datasets.":[141],"then":[143],"extend":[144],"multi-microphone":[147,150],"conditions":[148],"through":[149],"integrate":[155],"into":[157],"two-DNN":[159],"system":[160],"with":[161],"beamformer":[163,174],"between":[165],"(named":[166],"MISO-BF-MISO":[168],"earlier":[170],"studies),":[171],"proposed":[175,212],"this":[177],"paper":[178],"multi-frame":[182],"Wiener":[183],"filter":[184],"computed":[185],"based":[186],"outputs":[189],"DNN.":[193],"State-of-the-art":[194,221],"obtained":[197,224],"multi-channel":[200,237],"tasks":[201],"WHAMR!.":[205],"Besides":[206],"separation,":[208],"apply":[210],"algorithms":[213],"dereverberation":[216,227],"enhancement.":[220],"recent":[235],"L3DAS22":[236],"enhancement":[239],"challenge.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":79},{"year":2024,"cited_by_count":44},{"year":2023,"cited_by_count":13}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}