{"id":"https://openalex.org/W4404102497","doi":"https://doi.org/10.1109/taslp.2024.3492803","title":"TF-CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation","display_name":"TF-CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404102497","doi":"https://doi.org/10.1109/taslp.2024.3492803"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3492803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3492803","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/A5009379093","display_name":"Vahid Ahmadi Kalkhorani","orcid":"https://orcid.org/0000-0002-4166-1935"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahid Ahmadi Kalkhorani","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0002-4166-1935","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051837453","display_name":"DeLiang Wang","orcid":"https://orcid.org/0000-0001-8195-6319"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeLiang Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering, and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-8195-6319","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, and the Center for Cognitive and Brain Sciences, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":5.9894,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97182203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"4999","last_page":"5009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.973800003528595,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6347284317016602},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.535244345664978},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.49974489212036133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47504472732543945},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.36427828669548035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13550612330436707}],"concepts":[{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6347284317016602},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.535244345664978},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.49974489212036133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47504472732543945},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.36427828669548035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13550612330436707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3492803","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3492803","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":[],"awards":[{"id":"https://openalex.org/G3119090121","display_name":null,"funder_award_id":"ECCS-2125074","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320317189","display_name":"Ohio Supercomputer Center","ror":"https://ror.org/01apna436"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2117678320","https://openalex.org/W2127851351","https://openalex.org/W2130722890","https://openalex.org/W2147166770","https://openalex.org/W2164502538","https://openalex.org/W2221409856","https://openalex.org/W2242685705","https://openalex.org/W2291877678","https://openalex.org/W2516001803","https://openalex.org/W2734774145","https://openalex.org/W2763188033","https://openalex.org/W2774389566","https://openalex.org/W2905402910","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2964058413","https://openalex.org/W2972460025","https://openalex.org/W2991361823","https://openalex.org/W2996969697","https://openalex.org/W3007256793","https://openalex.org/W3015191643","https://openalex.org/W3015199127","https://openalex.org/W3015372568","https://openalex.org/W3016094953","https://openalex.org/W3042857426","https://openalex.org/W3096073522","https://openalex.org/W3096893582","https://openalex.org/W3097777922","https://openalex.org/W3151851237","https://openalex.org/W3160903688","https://openalex.org/W3171278394","https://openalex.org/W3185109982","https://openalex.org/W3195155284","https://openalex.org/W4200598930","https://openalex.org/W4210402803","https://openalex.org/W4210984894","https://openalex.org/W4224936432","https://openalex.org/W4226062543","https://openalex.org/W4226153164","https://openalex.org/W4283794752","https://openalex.org/W4294891356","https://openalex.org/W4296068774","https://openalex.org/W4372259962","https://openalex.org/W4375869348","https://openalex.org/W4379797396","https://openalex.org/W4385245566","https://openalex.org/W4385571459","https://openalex.org/W4385756463","https://openalex.org/W4391621214","https://openalex.org/W4395471098","https://openalex.org/W6631362777","https://openalex.org/W6766380642","https://openalex.org/W6769802879","https://openalex.org/W6803996941"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2071676784","https://openalex.org/W2376932109","https://openalex.org/W2791440692"],"abstract_inverted_index":{"We":[0],"introduce":[1,59],"TF-CrossNet,":[2,76],"a":[3,25,30,33,60],"complex":[4],"spectral":[5],"mapping":[6],"approach":[7],"to":[8,98,106],"speaker":[9,86],"separation":[10],"and":[11,15,36,44,73,84,92],"enhancement":[12],"in":[13,47,55,80,96,112],"reverberant":[14,83],"noisy":[16],"conditions.":[17],"The":[18],"proposed":[19],"architecture":[20],"comprises":[21],"an":[22,37],"encoder":[23],"layer,":[24],"global":[26],"multi-head":[27],"self-attention":[28],"module,":[29,32,35],"cross-band":[31],"narrow-band":[34,45],"output":[38],"layer.":[39],"TF-CrossNet":[40,89],"captures":[41],"global,":[42],"cross-band,":[43],"correlations":[46],"the":[48,71],"time-frequency":[49],"domain.":[50],"To":[51],"address":[52],"performance":[53,79,104],"degradation":[54],"long":[56],"utterances,":[57],"we":[58],"random":[61],"chunk":[62],"positional":[63],"encoding.":[64],"Experimental":[65],"results":[66],"on":[67],"multiple":[68],"datasets":[69],"demonstrate":[70],"effectiveness":[72],"robustness":[74],"of":[75],"achieving":[77],"state-of-the-art":[78],"tasks":[81],"including":[82],"noisy-reverberant":[85],"separation.":[87],"Furthermore,":[88],"exhibits":[90],"faster":[91],"more":[93],"stable":[94],"training":[95],"comparison":[97],"recent":[99],"baselines.":[100],"Additionally,":[101],"TF-CrossNet's":[102],"high":[103],"extends":[105],"multi-microphone":[107],"conditions,":[108],"demonstrating":[109],"its":[110],"versatility":[111],"various":[113],"acoustic":[114],"scenarios.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}