{"id":"https://openalex.org/W4405056317","doi":"https://doi.org/10.1109/icspcc62635.2024.10770551","title":"Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verification","display_name":"Progressive Sub-Graph Clustering Algorithm for Semi-Supervised Domain Adaptation Speaker Verification","publication_year":2024,"publication_date":"2024-08-19","ids":{"openalex":"https://openalex.org/W4405056317","doi":"https://doi.org/10.1109/icspcc62635.2024.10770551"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc62635.2024.10770551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc62635.2024.10770551","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 Signal Processing, Communications and Computing (ICSPCC)","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/A5100448036","display_name":"Zhuo Li","orcid":"https://orcid.org/0000-0002-9937-2669"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhuo Li","raw_affiliation_strings":["OPPO,Beijing,China"],"affiliations":[{"raw_affiliation_string":"OPPO,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023894764","display_name":"Jingze Lu","orcid":"https://orcid.org/0000-0002-2815-3784"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingze Lu","raw_affiliation_strings":["Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059099172","display_name":"Zhenduo Zhao","orcid":"https://orcid.org/0009-0002-7376-0441"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenduo Zhao","raw_affiliation_strings":["Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115594424","display_name":"Wenchao Wang","orcid":"https://orcid.org/0009-0001-9630-3537"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenchao Wang","raw_affiliation_strings":["Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Acoustics,Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210099069","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175728","display_name":"Mou Wang","orcid":"https://orcid.org/0000-0002-6476-2501"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mou Wang","raw_affiliation_strings":["OPPO,Beijing,China"],"affiliations":[{"raw_affiliation_string":"OPPO,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101673728","display_name":"Ziteng Wang","orcid":"https://orcid.org/0009-0001-8487-8093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziteng Wang","raw_affiliation_strings":["OPPO,Beijing,China"],"affiliations":[{"raw_affiliation_string":"OPPO,Beijing,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100352180","display_name":"Xin Liu","orcid":"https://orcid.org/0000-0002-0011-6260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["OPPO,Beijing,China"],"affiliations":[{"raw_affiliation_string":"OPPO,Beijing,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100448036"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3626,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69593047,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9790999889373779,"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":0.9790999889373779,"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":0.9081000089645386,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7791354656219482},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.7240385413169861},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6630622148513794},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5840789079666138},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.47434747219085693},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42029380798339844},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41183188557624817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40153494477272034},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3875807821750641},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.31457775831222534},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2821919322013855},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12253394722938538}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791354656219482},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.7240385413169861},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6630622148513794},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5840789079666138},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.47434747219085693},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42029380798339844},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41183188557624817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40153494477272034},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3875807821750641},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31457775831222534},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2821919322013855},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12253394722938538},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc62635.2024.10770551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icspcc62635.2024.10770551","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 Signal Processing, Communications and Computing (ICSPCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W2886606195","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489"],"abstract_inverted_index":{"Utilizing":[0],"the":[1,6,50,55,82,85,93],"large-scale":[2],"unlabeled":[3],"data":[4],"from":[5],"target":[7],"domain":[8,19],"via":[9],"pseudo-label":[10],"clustering":[11,35,100],"algorithms":[12],"is":[13,89],"an":[14,104],"important":[15],"approach":[16,106],"for":[17],"addressing":[18],"adaptation":[20],"problems":[21],"in":[22],"speaker":[23],"verification":[24],"tasks.":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,102],"propose":[30],"a":[31,76,113],"novel":[32],"progressive":[33],"subgraph":[34],"algorithm":[36,117],"based":[37,43,67,115],"on":[38,68],"multi-model":[39],"voting":[40,77],"and":[41,54,71,111],"double-Gaussian":[42,114],"assessment":[44,116],"(MVGPG":[45],"clustering).":[46],"To":[47],"fully":[48],"exploit":[49],"relationships":[51],"among":[52,57],"utterances":[53],"complementarity":[56],"multiple":[58,63],"models,":[59],"our":[60],"method":[61],"constructs":[62],"k-nearest":[64],"neighbors":[65],"graphs":[66],"diverse":[69],"models":[70],"generates":[72],"high-confidence":[73],"edges":[74],"using":[75],"mechanism.":[78],"Further,":[79],"to":[80,91,97,118],"maximize":[81],"intra-class":[83],"diversity,":[84],"connected":[86],"sub":[87],"graph":[88],"utilized":[90],"obtain":[92],"initial":[94],"pseudo-labels.":[95],"Finally,":[96],"prevent":[98],"disastrous":[99],"results,":[101],"adopt":[103],"iterative":[105],"that":[107],"progressively":[108],"increases":[109],"k":[110],"employs":[112],"decide":[119],"whether":[120],"merging":[121],"sub-classes.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
