{"id":"https://openalex.org/W4410153306","doi":"https://doi.org/10.1109/jstsp.2025.3567838","title":"AV-CrossNet: An Audiovisual Complex Spectral Mapping Network for Speech Separation by Leveraging Narrow- and Cross-Band Modeling","display_name":"AV-CrossNet: An Audiovisual Complex Spectral Mapping Network for Speech Separation by Leveraging Narrow- and Cross-Band Modeling","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W4410153306","doi":"https://doi.org/10.1109/jstsp.2025.3567838"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2025.3567838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3567838","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal 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, 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, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108743403","display_name":"Cheng Yu","orcid":"https://orcid.org/0000-0001-5544-7449"},"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":"Cheng Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA"],"raw_orcid":"https://orcid.org/0000-0001-5544-7449","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103006888","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0003-2217-5891"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Kumar","raw_affiliation_strings":["Meta Reality Labs, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2217-5891","affiliations":[{"raw_affiliation_string":"Meta Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058209019","display_name":"Ke Tan","orcid":"https://orcid.org/0000-0001-5073-8060"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Tan","raw_affiliation_strings":["Meta Reality Labs, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5073-8060","affiliations":[{"raw_affiliation_string":"Meta Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Meta Reality Labs, Redmond, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3027-7567","affiliations":[{"raw_affiliation_string":"Meta Reality Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"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, Center for Cognitive and Brain Sciences, Ohio State University, Columbus, OH, USA","Department of Computer Science and Engineering and the Center for Cognitive and Brain Sciences, 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, Center for Cognitive and Brain Sciences, 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, Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.2561,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.94038296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"19","issue":"4","first_page":"685","last_page":"694"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9757000207901001,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6941981911659241},{"id":"https://openalex.org/keywords/separation","display_name":"Separation (statistics)","score":0.575839102268219},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5015804767608643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36071860790252686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11426165699958801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941981911659241},{"id":"https://openalex.org/C2776061190","wikidata":"https://www.wikidata.org/wiki/Q7451805","display_name":"Separation (statistics)","level":2,"score":0.575839102268219},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5015804767608643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36071860790252686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11426165699958801}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jstsp.2025.3567838","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2025.3567838","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"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 Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309374","display_name":"Ohio State University","ror":"https://ror.org/00rs6vg23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2014621385","https://openalex.org/W2029199293","https://openalex.org/W2044893557","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2289925289","https://openalex.org/W2291877678","https://openalex.org/W2510642588","https://openalex.org/W2516001803","https://openalex.org/W2521686623","https://openalex.org/W2734774145","https://openalex.org/W2747876639","https://openalex.org/W2774389566","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2940275453","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963082324","https://openalex.org/W2964058413","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W2972460025","https://openalex.org/W2972513594","https://openalex.org/W2972541922","https://openalex.org/W2972568703","https://openalex.org/W2973062255","https://openalex.org/W2973231102","https://openalex.org/W3007256793","https://openalex.org/W3008400075","https://openalex.org/W3015199127","https://openalex.org/W3015529133","https://openalex.org/W3024147341","https://openalex.org/W3042857426","https://openalex.org/W3096028031","https://openalex.org/W3116298410","https://openalex.org/W3136499730","https://openalex.org/W3137758952","https://openalex.org/W3163287738","https://openalex.org/W3173382920","https://openalex.org/W3182657421","https://openalex.org/W3197823486","https://openalex.org/W3197832224","https://openalex.org/W4210984894","https://openalex.org/W4226062543","https://openalex.org/W4232282348","https://openalex.org/W4233392025","https://openalex.org/W4253928870","https://openalex.org/W4289665794","https://openalex.org/W4313417891","https://openalex.org/W4319862437","https://openalex.org/W4364323053","https://openalex.org/W4372259900","https://openalex.org/W4372346152","https://openalex.org/W4385245566","https://openalex.org/W4385756463","https://openalex.org/W4385823088","https://openalex.org/W4385823228","https://openalex.org/W4391021590","https://openalex.org/W4391621214","https://openalex.org/W4392903720","https://openalex.org/W4392908343","https://openalex.org/W4393405428","https://openalex.org/W4395471098","https://openalex.org/W4401023616","https://openalex.org/W4404102497","https://openalex.org/W6754420807","https://openalex.org/W6803594737"],"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/W2001405890"],"abstract_inverted_index":{"Adding":[0],"visual":[1,60,67,72,80],"cues":[2],"to":[3,91],"audio-based":[4],"speech":[5,20,48],"separation":[6,9,49],"can":[7],"improve":[8],"performance.":[10],"This":[11],"paper":[12],"introduces":[13],"AV-CrossNet,":[14],"an":[15,85],"audiovisual":[16,130],"(AV)":[17],"system":[18,64],"for":[19,47],"enhancement,":[21],"target":[22],"speaker":[23,27],"extraction,":[24],"and":[25,54,69,79,104,117,135],"multi-talker":[26],"separation.":[28],"AV-CrossNet":[29,92,96,123],"is":[30,37],"extended":[31],"from":[32],"the":[33,62,110,125],"TF-CrossNet":[34],"architecture,":[35],"which":[36],"a":[38,71],"recently":[39],"proposed":[40,63],"network":[41],"that":[42,122],"performs":[43],"complex":[44],"spectral":[45],"mapping":[46],"by":[50],"leveraging":[51],"global":[52],"attention":[53],"positional":[55],"encoding.":[56],"To":[57],"effectively":[58],"utilize":[59],"cues,":[61],"incorporates":[65],"pre-extracted":[66],"embeddings":[68],"employs":[70],"encoder":[73],"comprising":[74],"temporal":[75],"convolutional":[76],"layers.":[77],"Audio":[78],"features":[81],"are":[82],"fused":[83],"in":[84,107,128],"early":[86],"fusion":[87],"layer":[88],"before":[89],"feeding":[90],"blocks.":[93],"We":[94],"evaluate":[95],"on":[97,133],"multiple":[98],"datasets,":[99],"including":[100],"LRS,":[101],"VoxCeleb,":[102],"TCD-TIMIT,":[103],"COG-MHEAR":[105],"challenge,":[106],"terms":[108],"of":[109,113],"performance":[111,127],"metrics":[112],"PESQ,":[114],"STOI,":[115],"SNR":[116],"SDR.":[118],"Evaluation":[119],"results":[120],"demonstrate":[121],"advances":[124],"state-of-the-art":[126],"all":[129],"tasks,":[131],"even":[132],"untrained":[134],"mismatched":[136],"datasets.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}