{"id":"https://openalex.org/W4392903720","doi":"https://doi.org/10.1109/icassp48485.2024.10446297","title":"Audiovisual Speaker Separation with Full- and Sub-Band Modeling in the Time-Frequency Domain","display_name":"Audiovisual Speaker Separation with Full- and Sub-Band Modeling in the Time-Frequency Domain","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903720","doi":"https://doi.org/10.1109/icassp48485.2024.10446297"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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":["Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080751032","display_name":"Anurag Kumar","orcid":"https://orcid.org/0000-0002-1164-144X"},"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,USA","Meta Reality Labs, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs, USA","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075227645","display_name":"Ke Tan","orcid":null},"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,USA","Meta Reality Labs, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs, 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,USA","Meta Reality Labs, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta Reality Labs,USA","institution_ids":["https://openalex.org/I4210128585"]},{"raw_affiliation_string":"Meta Reality Labs, 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":["Ohio State University,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, Ohio State University, USA","Center for Cognitive and Brain Sciences, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ohio State University,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Center for Cognitive and Brain Sciences, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8343,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84964757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12001","last_page":"12005"},"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":0.9980999827384949,"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":0.9970999956130981,"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":0.82503342628479},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6606206893920898},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.5152933597564697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5037505030632019},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4576389789581299},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45668235421180725},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4496680498123169},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37404799461364746},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.26233625411987305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.82503342628479},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6606206893920898},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.5152933597564697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5037505030632019},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4576389789581299},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45668235421180725},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4496680498123169},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37404799461364746},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26233625411987305},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"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":35,"referenced_works":["https://openalex.org/W2014621385","https://openalex.org/W2015143272","https://openalex.org/W2104887782","https://openalex.org/W2136808440","https://openalex.org/W2137400100","https://openalex.org/W2593116425","https://openalex.org/W2771039075","https://openalex.org/W2808631503","https://openalex.org/W2844030168","https://openalex.org/W2886232760","https://openalex.org/W2890952074","https://openalex.org/W2891205112","https://openalex.org/W2952218014","https://openalex.org/W2964171275","https://openalex.org/W2973010927","https://openalex.org/W3008400075","https://openalex.org/W3024147341","https://openalex.org/W3096028031","https://openalex.org/W3096214032","https://openalex.org/W3099330747","https://openalex.org/W3136499730","https://openalex.org/W3163652268","https://openalex.org/W3173382920","https://openalex.org/W3182657421","https://openalex.org/W4221143458","https://openalex.org/W4239396298","https://openalex.org/W4289665794","https://openalex.org/W4312710798","https://openalex.org/W4312711418","https://openalex.org/W4380373744","https://openalex.org/W4385756463","https://openalex.org/W4385823088","https://openalex.org/W6746717610","https://openalex.org/W6754420807","https://openalex.org/W6781364056"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W1947057263","https://openalex.org/W2355447608","https://openalex.org/W1980067354","https://openalex.org/W2033324903","https://openalex.org/W1978333447","https://openalex.org/W2136112003"],"abstract_inverted_index":{"We":[0],"introduce":[1],"a":[2,60,87,97,118],"new":[3],"deep":[4],"learning":[5],"model":[6,23,129],"for":[7],"talker-independent":[8],"audiovisual":[9,38,105,139],"speaker":[10,134],"separation":[11,135],"in":[12,15,137],"noisy":[13,25],"conditions":[14],"the":[16,22,29,65,77,109,127,131],"time-frequency":[17],"domain.":[18],"The":[19,71],"inputs":[20],"to":[21,101],"include":[24],"multi-talker":[26],"mixtures":[27],"and":[28,43,46,53,96],"corresponding":[30],"cropped":[31],"face":[32],"images.":[33],"Our":[34],"approach":[35],"incorporates":[36],"cross-attention":[37,98],"fusion,":[39],"effectively":[40],"merging":[41],"audio":[42],"visual":[44,54,112],"features":[45,58,67],"enabling":[47],"seamless":[48],"information":[49],"interchange":[50],"between":[51],"auditory":[52],"modalities.":[55],"These":[56],"fused":[57,104],"drive":[59],"separator":[61,72],"module,":[62],"which":[63,81],"separates":[64],"acoustic":[66],"of":[68,111],"individual":[69],"speakers.":[70],"module":[73,90,99],"is":[74],"based":[75],"on":[76],"recently":[78],"proposed":[79,128],"TF-Gridnet,":[80],"comprises":[82],"an":[83],"intra-frame":[84],"full-band":[85],"component,":[86],"sub-band":[88],"temporal":[89,94],"that":[91,126],"captures":[92],"frequency-specific":[93],"dependencies,":[95],"dedicated":[100],"extracting":[102],"long-term":[103],"features.":[106],"To":[107],"encourage":[108],"utilization":[110],"streams":[113],"during":[114],"training,":[115],"we":[116],"employ":[117],"Signal-to-Noise":[119],"Ratio":[120],"(SNR)":[121],"scheduler.":[122],"Experimental":[123],"results":[124],"demonstrate":[125],"advances":[130],"state-of-":[132],"the-art":[133],"performance":[136],"several":[138],"benchmark":[140],"datasets.":[141]},"counts_by_year":[{"year":2025,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}