{"id":"https://openalex.org/W4391538086","doi":"https://doi.org/10.1007/s11042-024-18457-9","title":"AS-Net: active speaker detection using deep audio-visual attention","display_name":"AS-Net: active speaker detection using deep audio-visual attention","publication_year":2024,"publication_date":"2024-02-05","ids":{"openalex":"https://openalex.org/W4391538086","doi":"https://doi.org/10.1007/s11042-024-18457-9"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-024-18457-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-024-18457-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-024-18457-9.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-024-18457-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049343215","display_name":"Abduljalil Radman","orcid":"https://orcid.org/0000-0002-6317-9752"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Abduljalil Radman","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-6317-9752","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036133390","display_name":"Jorma Laaksonen","orcid":"https://orcid.org/0000-0001-7218-3131"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jorma Laaksonen","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5049343215"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.5702,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58219861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"83","issue":"28","first_page":"72027","last_page":"72042"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9296474456787109},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6614922881126404},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5993310213088989},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.4976361095905304},{"id":"https://openalex.org/keywords/visual-attention","display_name":"Visual attention","score":0.4153466820716858},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38814911246299744},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.18718433380126953},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.05962413549423218}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9296474456787109},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6614922881126404},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5993310213088989},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.4976361095905304},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.4153466820716858},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38814911246299744},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.18718433380126953},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.05962413549423218},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11042-024-18457-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-024-18457-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-024-18457-9.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/130322","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/1b6f1a89-56b5-4a69-8ff5-d5d034baef62","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s11042-024-18457-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-024-18457-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-024-18457-9.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7599999904632568}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321394","display_name":"Aalto-Yliopisto","ror":"https://ror.org/020hwjq30"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391538086.pdf"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W123007118","https://openalex.org/W2064675550","https://openalex.org/W2131774270","https://openalex.org/W2157331557","https://openalex.org/W2161226030","https://openalex.org/W2194775991","https://openalex.org/W2287407690","https://openalex.org/W2316138215","https://openalex.org/W2604379605","https://openalex.org/W2768817490","https://openalex.org/W2793493229","https://openalex.org/W2796898951","https://openalex.org/W2950864153","https://openalex.org/W2962918445","https://openalex.org/W2963173190","https://openalex.org/W2963470929","https://openalex.org/W2972949456","https://openalex.org/W2990152177","https://openalex.org/W3016098309","https://openalex.org/W3023351797","https://openalex.org/W3034702511","https://openalex.org/W3035875334","https://openalex.org/W3104119587","https://openalex.org/W3135222947","https://openalex.org/W3172472082","https://openalex.org/W3189964604","https://openalex.org/W3197584784","https://openalex.org/W3198690170","https://openalex.org/W3204030204","https://openalex.org/W3206008172","https://openalex.org/W3207207922","https://openalex.org/W4214701094","https://openalex.org/W4225302874","https://openalex.org/W4280538209","https://openalex.org/W4289874551","https://openalex.org/W4291920479","https://openalex.org/W4297491374","https://openalex.org/W4312268709","https://openalex.org/W4312466984","https://openalex.org/W4312638101","https://openalex.org/W4382241160","https://openalex.org/W4386441189","https://openalex.org/W4387847789","https://openalex.org/W4387968000","https://openalex.org/W6600577311"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101","https://openalex.org/W1984634519","https://openalex.org/W2801048620"],"abstract_inverted_index":{"Abstract":[0],"Active":[1],"Speaker":[2],"Detection":[3],"(ASD)":[4],"aims":[5],"at":[6,54],"identifying":[7],"the":[8,55,76,109,118,126,159,166],"active":[9,67,94],"speaker":[10],"among":[11],"multiple":[12],"speakers":[13,68,95],"in":[14,65,69,96],"a":[15,32,85],"video":[16,29,71,99],"scene.":[17],"Previous":[18],"ASD":[19,89,146],"models":[20,41],"often":[21],"seek":[22],"audio":[23],"and":[24,60,133,162],"visual":[25,123],"features":[26,124],"from":[27],"long":[28],"clips":[30,100],"with":[31,165],"complex":[33,170],"3D":[34,44,104],"Convolutional":[35],"Neural":[36],"Network":[37],"(CNN)":[38],"architecture.":[39],"However,":[40],"based":[42],"on":[43,103,158],"CNNs":[45],"can":[46],"generate":[47],"discriminative":[48],"spatial-temporal":[49],"features,":[50],"but":[51],"this":[52],"comes":[53],"expense":[56],"of":[57,120],"computational":[58],"complexity,":[59],"they":[61],"frequently":[62],"face":[63],"challenges":[64],"detecting":[66,93],"short":[70,98],"clips.":[72],"This":[73],"work":[74,82],"proposes":[75],"A":[77],"ctive":[78],"S":[79],"peaker":[80],"Net":[81],"(AS-Net)":[83],"model,":[84],"simple":[86],"yet":[87],"effective":[88],"method":[90],"tailored":[91],"for":[92,128],"relatively":[97],"without":[101,125],"relying":[102],"CNNs.":[105],"Instead,":[106],"it":[107],"incorporates":[108],"Temporal":[110],"Shift":[111],"Module":[112],"(TSM)":[113],"into":[114],"2D":[115,155],"CNNs,":[116],"facilitating":[117],"extraction":[119],"dense":[121],"temporal":[122,141],"need":[127],"additional":[129],"computations.":[130],"Moreover,":[131],"self-attention":[132],"cross-attention":[134],"schemes":[135],"are":[136],"introduced":[137],"to":[138],"enhance":[139],"long-term":[140],"audio-visual":[142],"synchronization,":[143],"thereby":[144],"improving":[145],"performance.":[147],"Experimental":[148],"results":[149],"demonstrate":[150],"that":[151],"AS-Net":[152],"outperforms":[153],"state-of-the-art":[154],"CNN-based":[156],"methods":[157,167],"AVA-ActiveSpeaker":[160],"dataset":[161],"remains":[163],"competitive":[164],"utilizing":[168],"more":[169],"architectures.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}