{"id":"https://openalex.org/W4388821370","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317320","title":"CASA-Net: Cross-attention and Self-attention for End-to-End Audio-visual Speaker Diarization","display_name":"CASA-Net: Cross-attention and Self-attention for End-to-End Audio-visual Speaker Diarization","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821370","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317320"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317320","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5010106071","display_name":"Haodong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Zhou","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048348409","display_name":"Tao Li","orcid":"https://orcid.org/0000-0002-9146-5975"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Li","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440189","display_name":"Jie Wang","orcid":"https://orcid.org/0000-0003-3520-7565"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wang","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412926","display_name":"Lin Li","orcid":"https://orcid.org/0000-0003-0426-6546"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]},{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Li","raw_affiliation_strings":["Xiamen University,School of Electronic Science and Engineering,China","School of Electronic Science and Engineering, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Electronic Science and Engineering,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Electronic Science and Engineering, Xiamen University, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University,School of Informatics,China","School of Informatics, Xiamen University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"106"},"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":0.9994000196456909,"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":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.8006079792976379},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7391785383224487},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.72509765625},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4632408022880554},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.45216619968414307},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4499706029891968},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44924116134643555},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.448818564414978},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4130338728427887},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41104093194007874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3781248927116394},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.29571986198425293},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.17904964089393616},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14914622902870178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8006079792976379},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7391785383224487},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.72509765625},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4632408022880554},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.45216619968414307},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4499706029891968},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44924116134643555},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.448818564414978},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4130338728427887},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41104093194007874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3781248927116394},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.29571986198425293},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.17904964089393616},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14914622902870178},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317320","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2015394094","https://openalex.org/W2116873850","https://openalex.org/W2122364000","https://openalex.org/W2219249508","https://openalex.org/W2915347754","https://openalex.org/W3008357631","https://openalex.org/W3015598461","https://openalex.org/W3025260599","https://openalex.org/W3038871978","https://openalex.org/W3039972129","https://openalex.org/W3119418740","https://openalex.org/W3140898556","https://openalex.org/W3206008172","https://openalex.org/W4212948839","https://openalex.org/W4221153068","https://openalex.org/W4225299282","https://openalex.org/W4226407477","https://openalex.org/W4286378963","https://openalex.org/W4296069335","https://openalex.org/W4297788887","https://openalex.org/W4297841387","https://openalex.org/W4297841834","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6766380642","https://openalex.org/W6779429391","https://openalex.org/W6810168380"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4221148444","https://openalex.org/W1556857061","https://openalex.org/W2177420620","https://openalex.org/W4296594783","https://openalex.org/W4387225169","https://openalex.org/W4380994539","https://openalex.org/W4308671730","https://openalex.org/W2915347927","https://openalex.org/W3151768066"],"abstract_inverted_index":{"Audio-visual":[0],"speaker":[1],"diarization":[2,94],"(AVSD)":[3],"is":[4,32,101],"a":[5,93,135],"critical":[6],"technique":[7],"that":[8],"segments":[9],"audio-visual":[10,30,60,73],"signals":[11,31],"and":[12,62],"assigns":[13],"them":[14],"to":[15,23,55,67,105,117],"multiple":[16,130],"speakers":[17],"in":[18,59],"practical":[19],"scenarios.":[20],"Thus,":[21],"how":[22],"efficiently":[24],"extract":[25],"the":[26,69,76,80,89,106,119,140],"cross-modal":[27,57],"information":[28,58,71],"from":[29],"essential":[33],"for":[34,46],"AVSD.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,114,132],"present":[40],"CASA-Net,":[41],"an":[42],"embedding":[43],"fusion":[44],"method":[45],"end-to-end":[47],"AVSD":[48],"system.":[49],"CASA-Net":[50,91],"incorporates":[51],"cross-attention":[52],"(CA)":[53],"module":[54,66],"capture":[56],"signals,":[61],"utilizes":[63],"self-attention":[64],"(SA)":[65],"learn":[68],"context":[70],"among":[72],"frames.":[74],"On":[75],"development":[77,141],"set":[78],"of":[79,98,137],"Multimodal":[81],"Information":[82],"Based":[83],"Speech":[84],"Processing":[85],"(MISP)":[86],"Challenge":[87],"2022,":[88],"proposed":[90],"achieved":[92,134],"error":[95],"rate":[96],"(DER)":[97],"13.18%,":[99],"which":[100],"1.56%":[102],"lower":[103],"compared":[104],"concatenation":[107],"(Concat)":[108],"method.":[109],"To":[110],"further":[111],"enhance":[112],"performance,":[113],"utilized":[115],"beamforming":[116],"integrate":[118],"available":[120],"multi-channel":[121],"audio":[122],"information,":[123],"along":[124],"with":[125],"data":[126],"augmentation.":[127],"By":[128],"fusing":[129],"systems,":[131],"ultimately":[133],"DER":[136],"12.60%":[138],"on":[139],"set.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
