{"id":"https://openalex.org/W3015841457","doi":"https://doi.org/10.1109/icassp40776.2020.9054376","title":"Self-Supervised Learning for Audio-Visual Speaker Diarization","display_name":"Self-Supervised Learning for Audio-Visual Speaker Diarization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015841457","doi":"https://doi.org/10.1109/icassp40776.2020.9054376","mag":"3015841457"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101822673","display_name":"Yifan Ding","orcid":"https://orcid.org/0000-0003-1973-8374"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Ding","raw_affiliation_strings":["University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467338","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-4944-6890"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["Tencent AI Lab, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785327","display_name":"Shi-Xiong Zhang","orcid":"https://orcid.org/0009-0007-7803-2407"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi-Xiong Zhang","raw_affiliation_strings":["Tencent AI Lab, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006210168","display_name":"Yahuan Cong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yahuan Cong","raw_affiliation_strings":["BUPT, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BUPT, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100427863","display_name":"Liqiang Wang","orcid":"https://orcid.org/0000-0002-1265-4656"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liqiang Wang","raw_affiliation_strings":["University of Central Florida, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Central Florida, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6291,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91255842,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4367","last_page":"4371"},"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":0.9998999834060669,"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":0.9993000030517578,"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":0.7971430420875549},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.716899037361145},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.693903923034668},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4664352238178253},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.45542922616004944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43462228775024414},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.412199467420578},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.36930906772613525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7971430420875549},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.716899037361145},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.693903923034668},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4664352238178253},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45542922616004944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43462228775024414},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.412199467420578},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.36930906772613525},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1964448421","https://openalex.org/W1965819578","https://openalex.org/W2038101708","https://openalex.org/W2093499222","https://openalex.org/W2168996682","https://openalex.org/W2194775991","https://openalex.org/W2316138215","https://openalex.org/W2400006663","https://openalex.org/W2403757143","https://openalex.org/W2512973121","https://openalex.org/W2551572271","https://openalex.org/W2604379605","https://openalex.org/W2612445135","https://openalex.org/W2621109248","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2809716557","https://openalex.org/W2896538040","https://openalex.org/W2952746495","https://openalex.org/W2953092061","https://openalex.org/W2963470929","https://openalex.org/W3016098309","https://openalex.org/W3105099157","https://openalex.org/W4297775537","https://openalex.org/W6712999683","https://openalex.org/W6735927292","https://openalex.org/W6737664043","https://openalex.org/W6738390143","https://openalex.org/W6740167877","https://openalex.org/W6753054903","https://openalex.org/W6757716108"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2150890698","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W1992908141","https://openalex.org/W2175373321","https://openalex.org/W4245698648","https://openalex.org/W2125642021"],"abstract_inverted_index":{"Speaker":[0],"diarization,":[1],"which":[2],"is":[3],"to":[4,38,108],"find":[5],"the":[6,40,51,60,65,78,110],"speech":[7],"segments":[8],"of":[9,42,88,112],"specific":[10],"speakers,":[11],"has":[12],"been":[13],"widely":[14],"used":[15],"in":[16,115],"human-centered":[17],"applications":[18],"such":[19],"as":[20,91,93],"video":[21],"conferences":[22],"or":[23],"human-computer":[24,74],"interaction":[25,75],"systems.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30,99],"propose":[31],"a":[32,72,85,101],"self-supervised":[33],"audio-video":[34,105,113],"synchronization":[35],"learning":[36],"method":[37],"address":[39],"problem":[41],"speaker":[43],"diarization":[44,94],"without":[45],"massive":[46],"labeling":[47],"effort.":[48],"We":[49,68],"improve":[50],"previous":[52],"approaches":[53],"by":[54],"introducing":[55],"two":[56],"new":[57,102],"loss":[58,63],"functions:":[59],"dynamic":[61],"triplet":[62],"and":[64,77],"multinomial":[66],"loss.":[67],"test":[69],"them":[70],"on":[71],"real-world":[73],"system":[76],"results":[79],"show":[80],"our":[81],"best":[82],"model":[83],"yields":[84],"remarkable":[86],"gain":[87],"+8%":[89],"F1-scores":[90],"well":[92],"error":[95],"rate":[96],"reduction.":[97],"Finally,":[98],"introduce":[100],"large":[103],"scale":[104],"corpus":[106],"designed":[107],"fill":[109],"vacancy":[111],"dataset":[114],"Chinese.":[116]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}