{"id":"https://openalex.org/W4408345599","doi":"https://doi.org/10.1109/icassp49660.2025.10889699","title":"Egocentric Speaker Diarization with Vision-Guided Clustering and Adaptive Speech Re-detection","display_name":"Egocentric Speaker Diarization with Vision-Guided Clustering and Adaptive Speech Re-detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345599","doi":"https://doi.org/10.1109/icassp49660.2025.10889699"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100411301","display_name":"He Huang","orcid":"https://orcid.org/0000-0002-9217-4977"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"He Huang","raw_affiliation_strings":["Hunan University,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591870","display_name":"Haoyuan Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyuan Yu","raw_affiliation_strings":["Hunan University,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037449474","display_name":"Daibo Liu","orcid":"https://orcid.org/0000-0002-8268-2951"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daibo Liu","raw_affiliation_strings":["Hunan University,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101527359","display_name":"Haowen Chen","orcid":"https://orcid.org/0000-0002-4777-7525"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haowen Chen","raw_affiliation_strings":["Hunan University,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108940025","display_name":"Minjie Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minjie Cai","raw_affiliation_strings":["Hunan University,China"],"affiliations":[{"raw_affiliation_string":"Hunan University,China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100411301"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01964926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9847999811172485,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9847999811172485,"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/T10860","display_name":"Speech and Audio Processing","score":0.9761000275611877,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9168999791145325,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8549513816833496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7394130229949951},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6653568148612976},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6403516530990601},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4826284348964691},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4814128875732422},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4485000967979431},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32674098014831543}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8549513816833496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7394130229949951},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6653568148612976},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6403516530990601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4826284348964691},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4814128875732422},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4485000967979431},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32674098014831543}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889699","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W2081074144","https://openalex.org/W2962788625","https://openalex.org/W2963307811","https://openalex.org/W2972449503","https://openalex.org/W2997419692","https://openalex.org/W3008283340","https://openalex.org/W3015443711","https://openalex.org/W3024869864","https://openalex.org/W3095851463","https://openalex.org/W3120041065","https://openalex.org/W3162347631","https://openalex.org/W3163903701","https://openalex.org/W3178462146","https://openalex.org/W3182657421","https://openalex.org/W3205786327","https://openalex.org/W3206008172","https://openalex.org/W4224291204","https://openalex.org/W4224917453","https://openalex.org/W4251366631","https://openalex.org/W4286378963","https://openalex.org/W4297841834","https://openalex.org/W4312466984","https://openalex.org/W4385822353","https://openalex.org/W4385822356","https://openalex.org/W4385823321","https://openalex.org/W4386075783","https://openalex.org/W4386076373","https://openalex.org/W4392903223","https://openalex.org/W4392909798","https://openalex.org/W4408352172","https://openalex.org/W6846145006","https://openalex.org/W6853717450","https://openalex.org/W6853723667"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W4406496871","https://openalex.org/W1521049138","https://openalex.org/W2023466863"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,14,32,34,106,115,150],"aims":[2],"to":[3,83,127,133],"identify":[4],"\"who":[5],"spoke":[6],"when\"":[7],"in":[8,35,59,90,152],"multi-person":[9],"conversational":[10,42],"scenarios.":[11,155],"State-of-the-art":[12],"audio-only":[13,114],"methods":[15],"divide":[16],"the":[17,61,71,96,113,134,141],"task":[18],"into":[19,112],"multi-stages":[20],"of":[21,47,63,73],"speech":[22,124],"segmentation,":[23],"neural":[24],"speaker":[25,31,85,131],"embedding":[26],"and":[27,53,68,129,158],"unsupervised":[28],"clustering.":[29,75],"Egocentric":[30],"(i.e.,":[33],"egocentric":[36,91,154],"videos)":[37],"is":[38],"characterized":[39],"by":[40,108],"natural":[41],"scenarios":[43],"involving":[44],"a":[45,103],"variety":[46],"noisy":[48],"backgrounds,":[49],"changing":[50],"sound":[51],"levels":[52],"overlapping":[54],"speech.":[55],"These":[56],"cause":[57],"difficulty":[58],"predicting":[60],"number":[62],"speakers":[64],"from":[65],"audio":[66,137],"input,":[67],"heavily":[69],"influence":[70],"performance":[72,151],"audio-based":[74],"Although":[76],"audio-visual":[77,105],"modeling":[78],"has":[79],"been":[80],"studied":[81],"recently":[82],"enhance":[84],"diarization,":[86],"unreliable":[87],"visual":[88,110],"information":[89],"videos":[92],"may":[93],"even":[94],"degrade":[95],"performance.":[97],"In":[98,117],"this":[99],"work,":[100],"we":[101,119],"propose":[102,121],"unified":[104],"framework":[107],"incorporating":[109],"guidance":[111],"pipeline.":[116],"addition,":[118],"also":[120],"an":[122],"adaptive":[123],"re-detection":[125],"strategy":[126],"detect":[128],"assign":[130],"identity":[132],"mistakenly":[135],"undetected":[136],"segments.":[138],"Experiments":[139],"on":[140],"Ego4D":[142],"dataset":[143],"show":[144],"that":[145],"our":[146],"method":[147],"achieves":[148],"state-of-the-art":[149],"challenging":[153],"The":[156],"code":[157],"model":[159],"weights":[160],"are":[161],"available":[162],"at":[163],"https://github.com/YellowRiver2001/EgoDiarization.":[164]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}