{"id":"https://openalex.org/W3206008172","doi":"https://doi.org/10.1145/3474085.3475587","title":"Is Someone Speaking?","display_name":"Is Someone Speaking?","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206008172","doi":"https://doi.org/10.1145/3474085.3475587","mag":"3206008172"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475587","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475587","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475587","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029637694","display_name":"Rohan Kumar Das","orcid":"https://orcid.org/0000-0002-1332-3357"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rohan Kumar Das","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056495776","display_name":"Xinyuan Qian","orcid":"https://orcid.org/0000-0002-9511-6713"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xinyuan Qian","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068937750","display_name":"Mike Zheng Shou","orcid":"https://orcid.org/0000-0002-7681-2166"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mike Zheng Shou","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":129,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3927","last_page":"3935"},"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":0.9983999729156494,"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":0.8047759532928467},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7608320713043213},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6875060200691223},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.608343243598938},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5882907509803772},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5705996155738831},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5668312311172485},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5177585482597351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49380621314048767},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4756585955619812},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47421884536743164},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35097992420196533},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.12819916009902954},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06676343083381653}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8047759532928467},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7608320713043213},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6875060200691223},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.608343243598938},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5882907509803772},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5705996155738831},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5668312311172485},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5177585482597351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49380621314048767},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4756585955619812},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47421884536743164},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35097992420196533},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.12819916009902954},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06676343083381653},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475587","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475587","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3474085.3475587","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3474085.3475587","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3474085.3475587","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3206008172.pdf","grobid_xml":"https://content.openalex.org/works/W3206008172.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1547319264","https://openalex.org/W1578985305","https://openalex.org/W1583773829","https://openalex.org/W1867429401","https://openalex.org/W2132347018","https://openalex.org/W2219249508","https://openalex.org/W2287407690","https://openalex.org/W2323437298","https://openalex.org/W2330149154","https://openalex.org/W2551437525","https://openalex.org/W2604379605","https://openalex.org/W2696967604","https://openalex.org/W2730845691","https://openalex.org/W2749694333","https://openalex.org/W2752782242","https://openalex.org/W2792351646","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2890964092","https://openalex.org/W2891205112","https://openalex.org/W2917987043","https://openalex.org/W2950864153","https://openalex.org/W2954458766","https://openalex.org/W2962960500","https://openalex.org/W2963232038","https://openalex.org/W2963307811","https://openalex.org/W2964171275","https://openalex.org/W2965002127","https://openalex.org/W2971784756","https://openalex.org/W2972729214","https://openalex.org/W2994810768","https://openalex.org/W3010457696","https://openalex.org/W3010594275","https://openalex.org/W3011519842","https://openalex.org/W3013020904","https://openalex.org/W3016098309","https://openalex.org/W3024085360","https://openalex.org/W3034702511","https://openalex.org/W3035875334","https://openalex.org/W3038871978","https://openalex.org/W3041847644","https://openalex.org/W3048939150","https://openalex.org/W3055892316","https://openalex.org/W3099638501","https://openalex.org/W3116298410","https://openalex.org/W3119269912","https://openalex.org/W3123318516","https://openalex.org/W3135222947","https://openalex.org/W3162475350","https://openalex.org/W3163287738","https://openalex.org/W4214701094","https://openalex.org/W4234389704","https://openalex.org/W4289665794","https://openalex.org/W4309845474","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2385859805","https://openalex.org/W3137890128","https://openalex.org/W1984634519","https://openalex.org/W4245955731"],"abstract_inverted_index":{"Active":[0],"speaker":[1],"detection":[2],"(ASD)":[3],"seeks":[4],"to":[5,91],"detect":[6],"who":[7],"is":[8],"speaking":[9,94],"in":[10],"a":[11,53,88],"visual":[12,32,75],"scene":[13],"of":[14,26,72],"one":[15],"or":[16],"more":[17],"speakers.":[18],"The":[19,96],"successful":[20],"ASD":[21,116],"depends":[22],"on":[23,110],"accurate":[24],"interpretation":[25],"short-term":[27,49,64],"and":[28,31,65,74,87,103,114],"long-term":[29,66,93],"audio":[30,73],"information,":[33],"as":[34,36],"well":[35],"audio-visual":[37,81],"interaction.":[38],"Unlike":[39],"the":[40,107,111],"prior":[41],"work":[42],"where":[43],"systems":[44,109],"make":[45],"decision":[46,60],"instantaneously":[47],"using":[48],"features,":[50],"we":[51],"propose":[52],"novel":[54],"framework,":[55],"named":[56],"TalkNet,":[57],"that":[58,99],"makes":[59],"by":[61],"taking":[62],"both":[63],"features":[67],"into":[68],"consideration.":[69],"TalkNet":[70,100],"consists":[71],"temporal":[76],"encoders":[77],"for":[78,84],"feature":[79],"representation,":[80],"cross-attention":[82],"mechanism":[83,90],"inter-modality":[85],"interaction,":[86],"self-attention":[89],"capture":[92],"evidence.":[95],"experiments":[97],"demonstrate":[98],"achieves":[101],"3.5%":[102],"2.2%":[104],"improvement":[105],"over":[106],"state-of-the-art":[108],"AVA-ActiveSpeaker":[112],"dataset":[113],"Columbia":[115],"dataset,":[117],"respectively.":[118],"Code":[119],"has":[120],"been":[121],"made":[122],"available":[123],"at:":[124],"https://github.com/TaoRuijie/TalkNet_ASD.":[125]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":34},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2021-10-25T00:00:00"}
