{"id":"https://openalex.org/W4401597516","doi":"https://doi.org/10.1109/icasspw62465.2024.10626914","title":"Late Audio-Visual Fusion for in-the-Wild Speaker Diarization","display_name":"Late Audio-Visual Fusion for in-the-Wild Speaker Diarization","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401597516","doi":"https://doi.org/10.1109/icasspw62465.2024.10626914"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10626914","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5060530570","display_name":"Zexu Pan","orcid":"https://orcid.org/0000-0002-8106-1176"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zexu Pan","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102812631","display_name":"Fran\u00e7ois G. Germain","orcid":"https://orcid.org/0000-0002-8973-5315"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois G. Germain","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048730867","display_name":"Aswin Shanmugam Subramanian","orcid":"https://orcid.org/0000-0003-4446-001X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aswin Subramanian","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064097430","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-0158-2837"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6114,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64624516,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9901999831199646,"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":0.9901999831199646,"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":0.9800999760627747,"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":0.6505693793296814},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6252133250236511},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5782846808433533},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5330475568771362},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4333666265010834},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2041706144809723},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.14914721250534058},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10267043113708496}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6505693793296814},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6252133250236511},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5782846808433533},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5330475568771362},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4333666265010834},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2041706144809723},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.14914721250534058},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10267043113708496},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10626914","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10626914","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1800068500","https://openalex.org/W2035890032","https://openalex.org/W2096733369","https://openalex.org/W2219249508","https://openalex.org/W2460742184","https://openalex.org/W2787692317","https://openalex.org/W2808631503","https://openalex.org/W2962715207","https://openalex.org/W2972729214","https://openalex.org/W2972949456","https://openalex.org/W3016098309","https://openalex.org/W3094380169","https://openalex.org/W3095212884","https://openalex.org/W3095379519","https://openalex.org/W3109496323","https://openalex.org/W3162475350","https://openalex.org/W3163287738","https://openalex.org/W3178462146","https://openalex.org/W3205879560","https://openalex.org/W3212886388","https://openalex.org/W4205689591","https://openalex.org/W4214698081","https://openalex.org/W4220731890","https://openalex.org/W4226062543","https://openalex.org/W4226338831","https://openalex.org/W4281651811","https://openalex.org/W4286378963","https://openalex.org/W4295308317","https://openalex.org/W4297788887","https://openalex.org/W4297841773","https://openalex.org/W4297841834","https://openalex.org/W4313048484","https://openalex.org/W6688816777","https://openalex.org/W6779429391","https://openalex.org/W6798523648"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W2111874347","https://openalex.org/W3120512183","https://openalex.org/W2118860825","https://openalex.org/W1509309911","https://openalex.org/W2096510939","https://openalex.org/W2041797852","https://openalex.org/W1940231550"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,33],"has":[2],"been":[3],"well":[4],"studied":[5],"for":[6,12,84],"constrained":[7],"scenarios":[8],"but":[9],"little":[10],"explored":[11],"in-the-wild":[13],"videos,":[14],"which":[15,35],"have":[16],"more":[17],"speakers,":[18],"shorter":[19],"utterances,":[20],"and":[21,38,57,68,81,86],"inconsistent":[22],"on-screen":[23,91],"speakers.":[24,92],"We":[25],"address":[26],"this":[27],"gap":[28],"by":[29,102],"proposing":[30],"an":[31,54],"audio-visual":[32],"model":[34],"combines":[36],"audio-only":[37],"visual-centric":[39,76],"sub-systems":[40,94],"via":[41],"late":[42],"fusion.":[43],"For":[44],"audio,":[45],"we":[46],"improve":[47],"the":[48,64,70,96,99,107,116],"attractor-based":[49],"end-to-end":[50],"system":[51,110],"EEND-EDA":[52],"with":[53,106],"attention":[55],"mechanism":[56],"a":[58,103,112],"speaker":[59,66,71],"recognition":[60],"loss":[61],"to":[62],"handle":[63],"larger":[65],"number":[67],"retain":[69],"identity":[72,85],"across":[73],"recordings.":[74],"The":[75],"sub-system":[77],"leverages":[78],"facial":[79],"attributes":[80],"lip-audio":[82],"synchrony":[83],"speech":[87],"activity":[88],"estimation":[89],"of":[90,98],"Both":[93],"surpass":[95],"state":[97],"art":[100],"(SOTA)":[101],"wide":[104],"margin,":[105],"fused":[108],"audiovisual":[109],"achieving":[111],"new":[113],"SOTA":[114],"on":[115],"AVA-AVD":[117],"benchmark.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
