{"id":"https://openalex.org/W3043471679","doi":"https://doi.org/10.1109/taslp.2021.3061885","title":"Meta-Learning With Latent Space Clustering in Generative Adversarial Network for Speaker Diarization","display_name":"Meta-Learning With Latent Space Clustering in Generative Adversarial Network for Speaker Diarization","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3043471679","doi":"https://doi.org/10.1109/taslp.2021.3061885","mag":"3043471679","pmid":"https://pubmed.ncbi.nlm.nih.gov/33997106"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3061885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3061885","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.09635","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027587001","display_name":"Monisankha Pal","orcid":"https://orcid.org/0000-0002-0788-4158"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Monisankha Pal","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","University  of Southern California"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101849944","display_name":"Manoj Kumar","orcid":"https://orcid.org/0000-0003-2100-461X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manoj Kumar","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","University  of Southern California"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086205666","display_name":"Raghuveer Peri","orcid":"https://orcid.org/0000-0002-1010-065X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghuveer Peri","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","University  of Southern California"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101397880","display_name":"Tae Jin Park","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tae Jin Park","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","University  of Southern California"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100689634","display_name":"So Hyun Kim","orcid":"https://orcid.org/0000-0003-4269-0866"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]},{"id":"https://openalex.org/I2800817003","display_name":"California Southern University","ror":"https://ror.org/058zz0t50","country_code":"US","type":"education","lineage":["https://openalex.org/I2800817003"]},{"id":"https://openalex.org/I94690351","display_name":"Center for Autism and Related Disorders","ror":"https://ror.org/00t7r5h51","country_code":"US","type":"other","lineage":["https://openalex.org/I94690351"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"So Hyun Kim","raw_affiliation_strings":["Center for Autism and the Developing Brain, Weill Cornell Medicine, USA","University  of Southern California"],"affiliations":[{"raw_affiliation_string":"Center for Autism and the Developing Brain, Weill Cornell Medicine, USA","institution_ids":["https://openalex.org/I94690351","https://openalex.org/I205783295"]},{"raw_affiliation_string":"University  of Southern California","institution_ids":["https://openalex.org/I2800817003","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082294410","display_name":"Catherine Lord","orcid":"https://orcid.org/0000-0001-5633-1253"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Catherine Lord","raw_affiliation_strings":["Semel Institute of Neuroscience and Human Behavior, University of California Los Angeles, USA","cornell University"],"affiliations":[{"raw_affiliation_string":"Semel Institute of Neuroscience and Human Behavior, University of California Los Angeles, USA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"cornell University","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067226360","display_name":"Somer Bishop","orcid":"https://orcid.org/0000-0002-2592-4715"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]},{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Somer Bishop","raw_affiliation_strings":["Department of Psychiatry, University of California, San Francisco, USA","University of California-Los Angeles"],"affiliations":[{"raw_affiliation_string":"Department of Psychiatry, University of California, San Francisco, USA","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"University of California-Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]},{"id":"https://openalex.org/I76766440","display_name":"University of San Francisco","ror":"https://ror.org/029m7xn54","country_code":"US","type":"education","lineage":["https://openalex.org/I76766440"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","\u00a7University of California, San Francisco"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"\u00a7University of California, San Francisco","institution_ids":["https://openalex.org/I180670191","https://openalex.org/I76766440"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5027587001"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I2800817003"],"apc_list":null,"apc_paid":null,"fwci":0.8398,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77608454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"1204","last_page":"1219"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9986000061035156,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8690208196640015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7180517911911011},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6210678815841675},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5552927255630493},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5006091594696045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48739224672317505},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4631480872631073},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4365652799606323},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3859992027282715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33375000953674316},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.2998460531234741}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8690208196640015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7180517911911011},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6210678815841675},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5552927255630493},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5006091594696045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48739224672317505},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4631480872631073},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4365652799606323},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3859992027282715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33375000953674316},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2998460531234741},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1109/taslp.2021.3061885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3061885","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:33997106","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33997106","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:arXiv.org:2007.09635","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.09635","pdf_url":"https://arxiv.org/pdf/2007.09635","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"mag:3043471679","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2007.09635.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:escholarship.org:ark:/13030/qt5bz7d4qg","is_oa":false,"landing_page_url":"https://escholarship.org/uc/item/5bz7d4qg","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8118028","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8118028","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2007.09635","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.09635","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.09635","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.09635","pdf_url":"https://arxiv.org/pdf/2007.09635","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6655150508","display_name":null,"funder_award_id":"1R01 MH114925-01","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"}],"funders":[{"id":"https://openalex.org/F4320306164","display_name":"Simons Foundation","ror":"https://ror.org/01cmst727"},{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W48568691","https://openalex.org/W1591607137","https://openalex.org/W2038101708","https://openalex.org/W2081074144","https://openalex.org/W2093499222","https://openalex.org/W2096733369","https://openalex.org/W2098726438","https://openalex.org/W2099471712","https://openalex.org/W2109761419","https://openalex.org/W2114925438","https://openalex.org/W2138730338","https://openalex.org/W2144446993","https://openalex.org/W2150769028","https://openalex.org/W2157364932","https://openalex.org/W2330594182","https://openalex.org/W2472819217","https://openalex.org/W2533545350","https://openalex.org/W2587150483","https://openalex.org/W2590916118","https://openalex.org/W2601450892","https://openalex.org/W2638067502","https://openalex.org/W2730106296","https://openalex.org/W2749214709","https://openalex.org/W2753160622","https://openalex.org/W2781711557","https://openalex.org/W2784962210","https://openalex.org/W2786458517","https://openalex.org/W2804107505","https://openalex.org/W2808516958","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2892055372","https://openalex.org/W2896538040","https://openalex.org/W2915347754","https://openalex.org/W2948398419","https://openalex.org/W2952006246","https://openalex.org/W2962788625","https://openalex.org/W2962852342","https://openalex.org/W2962879692","https://openalex.org/W2963105487","https://openalex.org/W2963226019","https://openalex.org/W2963341924","https://openalex.org/W2963386851","https://openalex.org/W2963470929","https://openalex.org/W2963702081","https://openalex.org/W2963745998","https://openalex.org/W2963761396","https://openalex.org/W2963962398","https://openalex.org/W2964074409","https://openalex.org/W2964316912","https://openalex.org/W2971668813","https://openalex.org/W2972446354","https://openalex.org/W2972533226","https://openalex.org/W2972756562","https://openalex.org/W2972949456","https://openalex.org/W2981103786","https://openalex.org/W2981608174","https://openalex.org/W2989790778","https://openalex.org/W2997419692","https://openalex.org/W3007483572","https://openalex.org/W3008357631","https://openalex.org/W3013020904","https://openalex.org/W3015308613","https://openalex.org/W3015337773","https://openalex.org/W3015778863","https://openalex.org/W3025757635","https://openalex.org/W3091905774","https://openalex.org/W3099206234","https://openalex.org/W3105031100","https://openalex.org/W6601517211","https://openalex.org/W6601947329","https://openalex.org/W6685380521","https://openalex.org/W6717697761","https://openalex.org/W6718140377","https://openalex.org/W6718379498","https://openalex.org/W6720057410","https://openalex.org/W6728550200","https://openalex.org/W6734007871","https://openalex.org/W6734641875","https://openalex.org/W6735236233","https://openalex.org/W6735913928","https://openalex.org/W6743661861","https://openalex.org/W6748447238","https://openalex.org/W6748483046","https://openalex.org/W6767939354","https://openalex.org/W6769302490","https://openalex.org/W6769530546","https://openalex.org/W6769628059","https://openalex.org/W6775982067","https://openalex.org/W6783596713","https://openalex.org/W6840066292"],"related_works":["https://openalex.org/W3015778863","https://openalex.org/W3158287709","https://openalex.org/W3015621653","https://openalex.org/W2972949456","https://openalex.org/W2981473019","https://openalex.org/W2748026385","https://openalex.org/W3144086690","https://openalex.org/W3093864324","https://openalex.org/W3121485920","https://openalex.org/W3016021376","https://openalex.org/W180663858","https://openalex.org/W2989378323","https://openalex.org/W3008849579","https://openalex.org/W2405970501","https://openalex.org/W3015463733","https://openalex.org/W3160204360","https://openalex.org/W2340557458","https://openalex.org/W2110783210","https://openalex.org/W2396559392","https://openalex.org/W2400584454"],"abstract_inverted_index":{"The":[0,149],"performance":[1,46,216],"of":[2,130,140,195,220],"most":[3],"speaker":[4,23],"diarization":[5,24,60,170,184,190,227],"systems":[6],"with":[7,30,156,177],"x-vector":[8,169],"embeddings":[9,146,155,207,213],"is":[10],"both":[11],"vulnerable":[12],"to":[13,35,58,122,136,179,197,229],"noisy":[14],"environments":[15],"and":[16,62,81,114,144,223,231],"lacks":[17],"domain":[18],"robustness.":[19],"Earlier":[20],"work":[21],"on":[22,47,99,199,233],"using":[25,86,203],"generative":[26],"adversarial":[27],"network":[28,33,57],"(GAN)":[29],"an":[31],"encoder":[32,77],"(ClusterGAN)":[34],"project":[36],"input":[37],"x-vectors":[38,178,230],"into":[39],"a":[40,188],"latent":[41],"space":[42],"has":[43],"shown":[44],"promising":[45],"meeting":[48,104],"data.":[49],"In":[50],"this":[51,71],"paper,":[52],"we":[53,73,173],"extend":[54],"the":[55,75,79,93,123,131,138,141,153,166,200,204,211,218],"ClusterGAN":[56,80,143,232],"improve":[59],"robustness":[61],"enable":[63],"rapid":[64],"generalization":[65],"across":[66],"various":[67],"challenging":[68,111],"domains.":[69],"To":[70],"end,":[72],"fetch":[74],"pre-trained":[76],"from":[78],"fine":[82],"tune":[83],"it":[84],"by":[85],"prototypical":[87],"loss":[88],"(meta-ClusterGAN":[89],"or":[90],"MCGAN)":[91],"under":[92],"meta-learning":[94],"paradigm.":[95],"Experiments":[96],"are":[97,134],"conducted":[98],"CALLHOME":[100],"telephonic":[101,234],"conversations,":[102],"AMI":[103],"data,":[105],"DIHARD-II":[106],"(dev":[107],"set)":[108],"which":[109],"includes":[110],"multi-domain":[112],"corpus,":[113],"two":[115],"child-clinician":[116],"interaction":[117],"corpora":[118],"(ADOS,":[119],"BOSCC)":[120],"related":[121],"autism":[124],"spectrum":[125],"disorder":[126],"domain.":[127],"Extensive":[128],"analyses":[129],"experimental":[132],"data":[133],"done":[135],"investigate":[137],"effectiveness":[139],"proposed":[142,154,205],"MCGAN":[145,212],"over":[147,208],"x-vectors.":[148,209],"results":[150],"show":[151],"that":[152],"normalized":[157],"maximum":[158],"eigengap":[159],"spectral":[160],"clustering":[161],"(NME-SC)":[162],"back-end":[163],"consistently":[164],"outperform":[165],"Kaldi":[167],"state-of-the-art":[168],"system.":[171],"Finally,":[172],"employ":[174],"embedding":[175],"fusion":[176],"provide":[180,214],"further":[181],"improvement":[182,194],"in":[183,217],"performance.":[185],"We":[186],"achieve":[187],"relative":[189],"error":[191],"rate":[192],"(DER)":[193],"6.67%":[196],"53.93%":[198],"aforementioned":[201],"datasets":[202],"fused":[206],"Besides,":[210],"better":[215],"number":[219],"speakers":[221],"estimation":[222],"short":[224],"speech":[225],"segment":[226],"compared":[228],"conversations.":[235]},"counts_by_year":[{"year":2021,"cited_by_count":6}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}