{"id":"https://openalex.org/W2972729214","doi":"https://doi.org/10.21437/interspeech.2019-3116","title":"Who Said That?: Audio-Visual Speaker Diarisation of Real-World Meetings","display_name":"Who Said That?: Audio-Visual Speaker Diarisation of Real-World Meetings","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972729214","doi":"https://doi.org/10.21437/interspeech.2019-3116","mag":"2972729214"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3116","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086369397","display_name":"Bong\u2010Jin Lee","orcid":"https://orcid.org/0000-0001-7896-2961"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Bong-Jin Lee","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028211638","display_name":"Icksang Han","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Icksang Han","raw_affiliation_strings":["Naver Corporation, South Korea"],"affiliations":[{"raw_affiliation_string":"Naver Corporation, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038723822"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":3.1722,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.92823665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"371","last_page":"375"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9905999898910522,"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/T11309","display_name":"Music and Audio Processing","score":0.9905999898910522,"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":0.9832000136375427,"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/T12031","display_name":"Speech and dialogue systems","score":0.9829000234603882,"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/audio-visual","display_name":"Audio visual","score":0.8016054034233093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7236871719360352},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5733019113540649},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3955944776535034}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.8016054034233093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7236871719360352},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5733019113540649},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3955944776535034}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-3116","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W126779258","https://openalex.org/W1494198834","https://openalex.org/W1587845029","https://openalex.org/W1771384906","https://openalex.org/W1800068500","https://openalex.org/W1996950552","https://openalex.org/W2046056978","https://openalex.org/W2049893888","https://openalex.org/W2084827375","https://openalex.org/W2101261946","https://openalex.org/W2115175902","https://openalex.org/W2125336414","https://openalex.org/W2148613904","https://openalex.org/W2150769028","https://openalex.org/W2153842971","https://openalex.org/W2194775991","https://openalex.org/W2271840356","https://openalex.org/W2292259253","https://openalex.org/W2394699868","https://openalex.org/W2470966581","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2796898951","https://openalex.org/W2808631503","https://openalex.org/W2884797218","https://openalex.org/W2889031312","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2899771611","https://openalex.org/W2950864153","https://openalex.org/W2953066166","https://openalex.org/W2963839617","https://openalex.org/W3106250896","https://openalex.org/W4234330420"],"related_works":["https://openalex.org/W2355862304","https://openalex.org/W2356108042","https://openalex.org/W2030250808","https://openalex.org/W2376796979","https://openalex.org/W2379418341","https://openalex.org/W2380054981","https://openalex.org/W2393110101","https://openalex.org/W2379285345","https://openalex.org/W2372054075","https://openalex.org/W2045326262"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,70],"this":[3],"work":[4],"is":[5,74,112],"to":[6,56,104],"determine":[7,57],"who":[8],"spoke":[9],"when'":[10],"in":[11],"real-world":[12,71],"meetings.The":[13,72],"method":[14,73],"takes":[15],"surround-view":[16],"video":[17,103],"and":[18,25,64],"single":[19],"or":[20],"multi-channel":[21,110],"audio":[22,111],"as":[23],"inputs,":[24],"generates":[26],"robust":[27],"diarisation":[28],"outputs.To":[29],"achieve":[30],"this,":[31],"we":[32,85],"propose":[33],"a":[34,68],"novel":[35],"iterative":[36],"approach":[37],"that":[38,88,95],"first":[39],"enrolls":[40],"speaker":[41],"models":[42,50],"using":[43],"audio-visual":[44],"correspondence,":[45],"then":[46],"uses":[47],"the":[48,53,58,78,102,107],"enrolled":[49],"together":[51,100],"with":[52,101],"visual":[54],"information":[55],"active":[59],"speaker.We":[60],"show":[61,94],"strong":[62],"quantitative":[63],"qualitative":[65],"performance":[66,108],"on":[67,77,83],"dataset":[69],"also":[75,93],"evaluated":[76],"public":[79],"AMI":[80],"meeting":[81],"corpus,":[82],"which":[84],"demonstrate":[86],"results":[87],"exceed":[89],"all":[90],"comparable":[91],"methods.We":[92],"beamforming":[96],"can":[97],"be":[98],"used":[99],"further":[105],"improve":[106],"when":[109],"available.":[113]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
