{"id":"https://openalex.org/W4415428940","doi":"https://doi.org/10.3233/faia250845","title":"A Fast and Lightweight Model for Causal Audio-Visual Speech Separation","display_name":"A Fast and Lightweight Model for Causal Audio-Visual Speech Separation","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428940","doi":"https://doi.org/10.3233/faia250845"},"language":null,"primary_location":{"id":"doi:10.3233/faia250845","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250845","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia250845","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wendi Sang","orcid":null},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]},{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Wendi Sang","raw_affiliation_strings":["Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China","Intelligent Computing and Application Laboratory of Qinghai Province, Qinghai University, Xining 810016, China","School of Computer Technology and Application, Qinghai University, Xining 810016, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I144112489"]},{"raw_affiliation_string":"Intelligent Computing and Application Laboratory of Qinghai Province, Qinghai University, Xining 810016, China","institution_ids":["https://openalex.org/I116265982"]},{"raw_affiliation_string":"School of Computer Technology and Application, Qinghai University, Xining 810016, China","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399944","display_name":"Kai Li","orcid":"https://orcid.org/0000-0002-8336-9684"},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Li","raw_affiliation_strings":["Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006425914","display_name":"Runxuan Yang","orcid":"https://orcid.org/0009-0004-2526-1909"},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runxuan Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I144112489"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101945412","display_name":"Jianqiang Huang","orcid":"https://orcid.org/0000-0003-2234-2696"},"institutions":[{"id":"https://openalex.org/I116265982","display_name":"Qinghai University","ror":"https://ror.org/05h33bt13","country_code":"CN","type":"education","lineage":["https://openalex.org/I116265982"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqiang Huang","raw_affiliation_strings":["Intelligent Computing and Application Laboratory of Qinghai Province, Qinghai University, Xining 810016, China","School of Computer Technology and Application, Qinghai University, Xining 810016, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Computing and Application Laboratory of Qinghai Province, Qinghai University, Xining 810016, China","institution_ids":["https://openalex.org/I116265982"]},{"raw_affiliation_string":"School of Computer Technology and Application, Qinghai University, Xining 810016, China","institution_ids":["https://openalex.org/I116265982"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xiaolin Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I144112489","display_name":"McGovern Institute for Brain Research","ror":"https://ror.org/05ymca674","country_code":"US","type":"facility","lineage":["https://openalex.org/I144112489","https://openalex.org/I63966007"]},{"id":"https://openalex.org/I4210115644","display_name":"Chinese Institute for Brain Research","ror":"https://ror.org/029819q61","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210115644"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiaolin Hu","raw_affiliation_strings":["Chinese Institute for Brain Research (CIBR), Beijing 100010, China","Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Institute for Brain Research (CIBR), Beijing 100010, China","institution_ids":["https://openalex.org/I4210115644"]},{"raw_affiliation_string":"Department of Computer Science and Technology, Institute for AI, BNRist, Tsinghua Laboratory of Brain and Intelligence (THBI), IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I144112489"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.3298,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94023265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.9973000288009644,"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":0.9478999972343445,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.656000018119812},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5791000127792358},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5756999850273132},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5372999906539917},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.5325000286102295},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5242000222206116},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.49799999594688416},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.460099995136261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7603999972343445},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.656000018119812},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5791000127792358},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5756999850273132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5540000200271606},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5372999906539917},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.5325000286102295},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5242000222206116},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5232999920845032},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.49799999594688416},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.460099995136261},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.365200012922287},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32440000772476196},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.314300000667572},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25929999351501465},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia250845","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250845","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia250845","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia250845","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,9,155],"separation":[2],"(AVSS)":[3],"aims":[4],"to":[5,92,115],"extract":[6],"a":[7,12,54,73,111],"target":[8],"signal":[10,14],"from":[11],"mixed":[13],"by":[15,47],"leveraging":[16],"both":[17],"auditory":[18],"and":[19,32,79,134],"visual":[20,75],"(lip":[21],"movement)":[22],"cues.":[23],"However,":[24],"most":[25],"existing":[26],"AVSS":[27,57,121],"methods":[28],"exhibit":[29],"complex":[30,157],"architectures":[31],"rely":[33],"on":[34,127],"future":[35],"context,":[36],"operating":[37],"offline,":[38],"which":[39,61],"renders":[40],"them":[41],"unsuitable":[42],"for":[43,68,84,153],"real-time":[44,69],"applications.":[45,70],"Inspired":[46],"the":[48,63,102,117,148],"pipeline":[49],"of":[50,105,119,150],"RTFSNet,":[51],"we":[52],"propose":[53,110],"novel":[55],"streaming":[56],"model,":[58],"named":[59],"Swift-Net,":[60],"enhances":[62],"causal":[64,112,124,139],"processing":[65,154],"capabilities":[66],"required":[67],"Swift-Net":[71,88,143],"adopts":[72],"lightweight":[74],"feature":[76,98],"extraction":[77],"module":[78,83],"an":[80],"efficient":[81],"fusion":[82],"audio-visual":[85],"integration.":[86],"Additionally,":[87],"employs":[89],"Grouped":[90],"SRUs":[91],"integrate":[93],"historical":[94,106],"information":[95],"across":[96],"different":[97],"spaces,":[99],"thereby":[100],"improving":[101],"utilization":[103],"efficiency":[104],"information.":[107],"We":[108],"further":[109],"transformation":[113],"template":[114],"facilitate":[116],"conversion":[118],"non-causal":[120],"models":[122],"into":[123],"counterparts.":[125],"Experiments":[126],"three":[128],"standard":[129],"benchmark":[130],"datasets":[131],"(LRS2,":[132],"LRS3,":[133],"VoxCeleb2)":[135],"demonstrated":[136],"that":[137],"under":[138],"conditions,":[140],"our":[141],"proposed":[142],"exhibited":[144],"outstanding":[145],"performance,":[146],"highlighting":[147],"potential":[149],"this":[151],"method":[152],"in":[156],"environments.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-24T00:00:00"}
