{"id":"https://openalex.org/W2981615245","doi":"https://doi.org/10.1109/icassp40776.2020.9053952","title":"Speaker Diarization Using Latent Space Clustering in Generative Adversarial Network","display_name":"Speaker Diarization Using Latent Space Clustering in Generative Adversarial Network","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981615245","doi":"https://doi.org/10.1109/icassp40776.2020.9053952","mag":"2981615245"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.11398","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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Monisankha Pal","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California","University of Southern California,Signal Analysis and Interpretation Laboratory"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manoj Kumar","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California","University of Southern California,Signal Analysis and Interpretation Laboratory"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghuveer Peri","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California","University of Southern California,Signal Analysis and Interpretation Laboratory"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tae Jin Park","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California","University of Southern California,Signal Analysis and Interpretation Laboratory"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["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/I94690351","display_name":"Center for Autism and Related Disorders","ror":"https://ror.org/00t7r5h51","country_code":"US","type":"other","lineage":["https://openalex.org/I94690351"]},{"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/I4387153466","display_name":"Weill Cornell Medicine","ror":"https://ror.org/02r109517","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4387153466"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"So Hyun Kim","raw_affiliation_strings":["Center for Autism and the Developing Brain, Weill Cornell Medicine","Weill Cornell Medicine,Center for Autism and the Developing Brain"],"affiliations":[{"raw_affiliation_string":"Center for Autism and the Developing Brain, Weill Cornell Medicine","institution_ids":["https://openalex.org/I94690351","https://openalex.org/I205783295","https://openalex.org/I4387153466"]},{"raw_affiliation_string":"Weill Cornell Medicine,Center for Autism and the Developing Brain","institution_ids":["https://openalex.org/I94690351","https://openalex.org/I205783295","https://openalex.org/I4387153466"]}]},{"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"]}],"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","University of California Los Angeles,Semel Institute of Neuroscience and Human Behavior"],"affiliations":[{"raw_affiliation_string":"Semel Institute of Neuroscience and Human Behavior, University of California Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California Los Angeles,Semel Institute of Neuroscience and Human Behavior","institution_ids":["https://openalex.org/I161318765"]}]},{"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/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","University of California Department of Psychiatry San Francisco"],"affiliations":[{"raw_affiliation_string":"Department of Psychiatry, University of California, San Francisco","institution_ids":["https://openalex.org/I180670191"]},{"raw_affiliation_string":"University of California Department of Psychiatry San Francisco","institution_ids":["https://openalex.org/I180670191"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California","University of Southern California,Signal Analysis and Interpretation Laboratory"],"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5027587001"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.5485,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.72193126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6504","last_page":"6508"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.8039789795875549},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6728646755218506},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6628704071044922},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.6012288928031921},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48477524518966675},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.48341190814971924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46854910254478455},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.45022672414779663},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.43245309591293335},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3597796559333801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3302651047706604},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.226730614900589}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8039789795875549},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6728646755218506},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6628704071044922},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.6012288928031921},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48477524518966675},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.48341190814971924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46854910254478455},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.45022672414779663},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.43245309591293335},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3597796559333801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3302651047706604},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.226730614900589},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.11398","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11398","pdf_url":"https://arxiv.org/pdf/1910.11398","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:2981615245","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1910.11398","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":"doi:10.48550/arxiv.1910.11398","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.11398","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"},{"id":"doi:10.17023/dwy2-xr52","is_oa":true,"landing_page_url":"https://doi.org/10.17023/dwy2-xr52","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:1910.11398","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.11398","pdf_url":"https://arxiv.org/pdf/1910.11398","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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981615245.pdf","grobid_xml":"https://content.openalex.org/works/W2981615245.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1591607137","https://openalex.org/W2038101708","https://openalex.org/W2081074144","https://openalex.org/W2093499222","https://openalex.org/W2099471712","https://openalex.org/W2144446993","https://openalex.org/W2330594182","https://openalex.org/W2405970501","https://openalex.org/W2407637315","https://openalex.org/W2533545350","https://openalex.org/W2590916118","https://openalex.org/W2638067502","https://openalex.org/W2746574320","https://openalex.org/W2781711557","https://openalex.org/W2784962210","https://openalex.org/W2786458517","https://openalex.org/W2889203268","https://openalex.org/W2889418727","https://openalex.org/W2889546047","https://openalex.org/W2896538040","https://openalex.org/W2915347754","https://openalex.org/W2952006246","https://openalex.org/W2962852342","https://openalex.org/W2962879692","https://openalex.org/W2963105487","https://openalex.org/W2963226019","https://openalex.org/W2963470929","https://openalex.org/W2963761396","https://openalex.org/W2963962398","https://openalex.org/W2964074409","https://openalex.org/W2971668813","https://openalex.org/W2972446354","https://openalex.org/W6631190155","https://openalex.org/W6685380521","https://openalex.org/W6713679436","https://openalex.org/W6718140377","https://openalex.org/W6728550200","https://openalex.org/W6734007871","https://openalex.org/W6735913928","https://openalex.org/W6740364378","https://openalex.org/W6747544821","https://openalex.org/W6748447238","https://openalex.org/W6748483046","https://openalex.org/W6765872269","https://openalex.org/W6767939354"],"related_works":["https://openalex.org/W3015778863","https://openalex.org/W3043471679","https://openalex.org/W2981473019","https://openalex.org/W2989378323","https://openalex.org/W2538493831","https://openalex.org/W2405970501","https://openalex.org/W3158287709","https://openalex.org/W3095129427","https://openalex.org/W3093864324","https://openalex.org/W71947379","https://openalex.org/W2340557458","https://openalex.org/W3016021376","https://openalex.org/W2961166387","https://openalex.org/W2038101708","https://openalex.org/W2153342002","https://openalex.org/W3144086690","https://openalex.org/W2018419535","https://openalex.org/W2400584454","https://openalex.org/W3015463733","https://openalex.org/W2346457055"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,137],"propose":[4],"deep":[5],"latent":[6,35,53],"space":[7],"clustering":[8],"for":[9,111],"speaker":[10,46,72],"diarization":[11,27,131,147],"using":[12,69,171],"generative":[13],"adversarial":[14],"network":[15],"(GAN)":[16],"back-projection":[17],"with":[18,32,116,141],"the":[19,49,52,70,80,93,127,168],"help":[20],"of":[21,60,152],"an":[22],"encoder":[23],"network.":[24],"The":[25],"proposed":[26,77,123],"system":[28,78,124,132],"is":[29],"trained":[30],"jointly":[31],"GAN":[33],"loss,":[34,38],"variable":[36],"recovery":[37],"and":[39,64,84,90,98,102,114,155,161],"a":[40,58,145],"clustering-specific":[41],"loss.":[42],"It":[43],"uses":[44],"x-vector":[45,129,169],"embeddings":[47],"at":[48],"input,":[50],"while":[51],"variables":[54,63,68],"are":[55],"sampled":[56],"from":[57,92],"combination":[59],"continuous":[61],"random":[62],"discrete":[65],"one-hot":[66],"encoded":[67],"original":[71],"labels.":[73],"We":[74],"benchmark":[75],"our":[76,122],"on":[79,133,157],"AMI":[81,158],"meeting":[82],"corpus,":[83],"two":[85],"child-clinician":[86],"interaction":[87],"corpora":[88,163],"(ADOS":[89],"BOSCC)":[91],"autism":[94],"diagnosis":[95],"domain.":[96],"ADOS":[97,160],"BOSCC":[99,162],"contain":[100],"diagnostic":[101],"treatment":[103],"outcome":[104],"sessions":[105],"respectively":[106],"obtained":[107],"in":[108],"clinical":[109],"settings":[110],"verbal":[112],"children":[113],"adolescents":[115],"autism.":[117],"Experimental":[118],"results":[119],"show":[120],"that":[121],"significantly":[125],"outperform":[126],"state-of-the-art":[128],"based":[130],"these":[134],"databases.":[135],"Further,":[136],"perform":[138],"embedding":[139],"fusion":[140],"x-vectors":[142],"to":[143,167],"achieve":[144],"relative":[146],"error":[148],"rate":[149],"(DER)":[150],"improvement":[151],"31%,":[153],"36%":[154],"49%":[156],"eval,":[159],"respectively,":[164],"when":[165],"compared":[166],"baseline":[170],"oracle":[172],"speech":[173],"segmentation.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}