{"id":"https://openalex.org/W3135815897","doi":"https://doi.org/10.1109/iscslp49672.2021.9362084","title":"Age-Invariant Speaker Embedding for Diarization of Cognitive Assessments","display_name":"Age-Invariant Speaker Embedding for Diarization of Cognitive Assessments","publication_year":2021,"publication_date":"2021-01-24","ids":{"openalex":"https://openalex.org/W3135815897","doi":"https://doi.org/10.1109/iscslp49672.2021.9362084","mag":"3135815897"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp49672.2021.9362084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107106/1/Xu_Age-Invariant_Speaker_Embedding.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059023760","display_name":"Sean Shensheng Xu","orcid":"https://orcid.org/0000-0001-8846-5061"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sean Shensheng Xu","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891041","display_name":"Ka Ho Wong","orcid":"https://orcid.org/0000-0002-4818-1467"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ka Ho Wong","raw_affiliation_strings":["Dept. of Systems Engineering and Engineering Management, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Systems Engineering and Engineering Management, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Dept. of Systems Engineering and Engineering Management, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Systems Engineering and Engineering Management, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083203170","display_name":"Timothy Kwok","orcid":"https://orcid.org/0000-0001-9253-3549"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I4210100650","display_name":"Hong Kong Jockey Club","ror":"https://ror.org/015ygrv52","country_code":"HK","type":"nonprofit","lineage":["https://openalex.org/I4210100650"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Timothy C. Y. Kwok","raw_affiliation_strings":["Dept. of Medicine and Therapeutics, The Chinese University of Hong Kong","Jockey Club Centre for Osteoporosis Care and Control, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Medicine and Therapeutics, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Jockey Club Centre for Osteoporosis Care and Control, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633","https://openalex.org/I4210100650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"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":0.9998999834060669,"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":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9991999864578247,"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":0.9979000091552734,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9077206254005432},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6868411898612976},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6655975580215454},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6637532114982605},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5308657288551331},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.45729339122772217},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4328341782093048},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.42895743250846863},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4193931818008423},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4057618975639343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3711642622947693},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23488637804985046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12417402863502502}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9077206254005432},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6868411898612976},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6655975580215454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6637532114982605},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5308657288551331},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.45729339122772217},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4328341782093048},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.42895743250846863},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4193931818008423},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4057618975639343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3711642622947693},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23488637804985046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12417402863502502},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iscslp49672.2021.9362084","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp49672.2021.9362084","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/107106","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107106","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107106/1/Xu_Age-Invariant_Speaker_Embedding.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/107106","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107106","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107106/1/Xu_Age-Invariant_Speaker_Embedding.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135815897.pdf","grobid_xml":"https://content.openalex.org/works/W3135815897.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1731081199","https://openalex.org/W2002830978","https://openalex.org/W2043224889","https://openalex.org/W2081074144","https://openalex.org/W2109140840","https://openalex.org/W2121812409","https://openalex.org/W2121947440","https://openalex.org/W2138730338","https://openalex.org/W2165758561","https://openalex.org/W2187089797","https://openalex.org/W2219249508","https://openalex.org/W2638067502","https://openalex.org/W2696967604","https://openalex.org/W2748488820","https://openalex.org/W2752744672","https://openalex.org/W2766958920","https://openalex.org/W2889519245","https://openalex.org/W2891833136","https://openalex.org/W2915280872","https://openalex.org/W2915347754","https://openalex.org/W2946244506","https://openalex.org/W2972680151","https://openalex.org/W3015648588","https://openalex.org/W3038083940","https://openalex.org/W3039832962","https://openalex.org/W4205930639","https://openalex.org/W6629903641","https://openalex.org/W6631362777","https://openalex.org/W6637618735","https://openalex.org/W6688816777","https://openalex.org/W6754734105","https://openalex.org/W6776196743"],"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/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"an":[3,13,79,96],"age-invariant":[4,113],"speaker":[5,9,28,36,47,52,92],"embedding":[6],"approach":[7,124],"to":[8,51,85],"diarization,":[10],"which":[11],"is":[12,49,56,83],"essential":[14],"step":[15],"towards":[16],"the":[17,46,61,65,73,90,107,127],"automatic":[18],"cognitive":[19,102],"assessments":[20,103],"from":[21,89],"speech.":[22],"Studies":[23],"have":[24],"shown":[25],"that":[26,42,106],"incorporating":[27],"traits":[29],"(e.g.,":[30],"age,":[31],"gender,":[32],"etc.)":[33],"can":[34,111],"improve":[35],"diarization":[37,53,117],"performance.":[38],"However,":[39],"we":[40],"found":[41],"age":[43,62,77,87],"information":[44],"in":[45,64],"embeddings":[48,114],"detrimental":[50,74],"if":[54],"there":[55],"a":[57],"severe":[58],"mismatch":[59],"between":[60],"distributions":[63],"training":[66,81,109,133],"data":[67],"and":[68,115],"test":[69],"data.":[70,134],"To":[71],"minimize":[72],"effect":[75],"of":[76],"mismatch,":[78],"adversarial":[80,108],"strategy":[82,110],"introduced":[84],"remove":[86],"variability":[88],"utterance-level":[91],"embeddings.":[93],"Evaluations":[94],"on":[95],"interactive":[97],"dialog":[98],"dataset":[99],"for":[100],"Montreal":[101],"(MoCA)":[104],"show":[105],"produce":[112],"reduce":[116],"error":[118],"rate":[119],"(DER)":[120],"by":[121],"4.33%.":[122],"The":[123],"also":[125],"outperforms":[126],"conventional":[128],"method":[129],"even":[130],"with":[131],"less":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}