{"id":"https://openalex.org/W2982817420","doi":"https://doi.org/10.1109/icassp40776.2020.9054601","title":"Robust Speaker Recognition Using Unsupervised Adversarial Invariance","display_name":"Robust Speaker Recognition Using Unsupervised Adversarial Invariance","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2982817420","doi":"https://doi.org/10.1109/icassp40776.2020.9054601","mag":"2982817420"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054601","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.00940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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, Los Angeles, CA, USA","University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","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":false,"raw_author_name":"Monisankha Pal","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA, USA","University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067289130","display_name":"Arindam Jati","orcid":"https://orcid.org/0000-0002-9498-8536"},"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":"Arindam Jati","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA, USA","University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008305849","display_name":"Krishna Somandepalli","orcid":"https://orcid.org/0000-0002-2845-1079"},"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":"Krishna Somandepalli","raw_affiliation_strings":["Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA, USA","University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"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, Los Angeles, CA, USA","University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Analysis and Interpretation Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Southern California,Signal Analysis and Interpretation Laboratory,Los Angeles,CA,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.115,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.30330212,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6614","last_page":"6618"},"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":0.9990000128746033,"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":0.9977999925613403,"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/discriminative-model","display_name":"Discriminative model","score":0.8521862626075745},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7820206880569458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7663849592208862},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7449229955673218},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7106173038482666},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.696255087852478},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6813666224479675},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5823404788970947},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5462141633033752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5090863108634949},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4652612507343292},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46000152826309204},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.4177202582359314}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8521862626075745},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7820206880569458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7663849592208862},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7449229955673218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7106173038482666},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.696255087852478},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6813666224479675},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5823404788970947},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5462141633033752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5090863108634949},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4652612507343292},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46000152826309204},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.4177202582359314},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054601","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054601","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:1911.00940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.00940","pdf_url":"https://arxiv.org/pdf/1911.00940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2982817420","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1911.00940","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.1911.00940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.00940","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},{"id":"doi:10.17023/g16s-gm92","is_oa":true,"landing_page_url":"https://doi.org/10.17023/g16s-gm92","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"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":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.00940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.00940","pdf_url":"https://arxiv.org/pdf/1911.00940","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7400000095367432,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2982817420.pdf","grobid_xml":"https://content.openalex.org/works/W2982817420.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W67277430","https://openalex.org/W1494198834","https://openalex.org/W1569447338","https://openalex.org/W2101234009","https://openalex.org/W2129379984","https://openalex.org/W2150769028","https://openalex.org/W2638067502","https://openalex.org/W2726515241","https://openalex.org/W2743167696","https://openalex.org/W2746742816","https://openalex.org/W2748488820","https://openalex.org/W2796485741","https://openalex.org/W2799462250","https://openalex.org/W2808631503","https://openalex.org/W2888955371","https://openalex.org/W2889418727","https://openalex.org/W2890189553","https://openalex.org/W2890964092","https://openalex.org/W2901368553","https://openalex.org/W2915347754","https://openalex.org/W2916024349","https://openalex.org/W2937328535","https://openalex.org/W2953598317","https://openalex.org/W2962788262","https://openalex.org/W2963040451","https://openalex.org/W2963446520","https://openalex.org/W2963962398","https://openalex.org/W2972403660","https://openalex.org/W2972478081","https://openalex.org/W2972533226","https://openalex.org/W2972921407","https://openalex.org/W2973099347","https://openalex.org/W3008391559","https://openalex.org/W6633847657","https://openalex.org/W6675354045","https://openalex.org/W6738077463","https://openalex.org/W6742972455","https://openalex.org/W6754215057","https://openalex.org/W6760112457"],"related_works":["https://openalex.org/W2788991015","https://openalex.org/W3208516011","https://openalex.org/W3131643166","https://openalex.org/W1981185131","https://openalex.org/W1559164507","https://openalex.org/W3163187953","https://openalex.org/W2618829015","https://openalex.org/W2963576203","https://openalex.org/W2889956729","https://openalex.org/W2981783623","https://openalex.org/W2926256696","https://openalex.org/W1592672653","https://openalex.org/W2972387750","https://openalex.org/W2467417825","https://openalex.org/W2896538040","https://openalex.org/W2626212216","https://openalex.org/W3015308613","https://openalex.org/W2156692643","https://openalex.org/W3134299941","https://openalex.org/W2239847623"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"address":[4],"the":[5,67,73,78,81,91,110,115,126,145,151],"problem":[6],"of":[7,80,87,120,128,142],"speaker":[8,39,94,103,129],"recognition":[9,104],"in":[10,66,90,117,144],"challenging":[11,121],"acoustic":[12,74,122],"conditions":[13],"using":[14,42],"a":[15,26,35,43,101,118,132,139],"novel":[16],"method":[17],"to":[18,33,57,84,150],"extract":[19],"robust":[20],"speaker-discriminative":[21,59],"speech":[22],"representations.":[23],"We":[24,76],"adopt":[25],"recently":[27],"proposed":[28,82,111],"unsupervised":[29,97],"adversarial":[30],"invariance":[31],"architecture":[32],"train":[34],"network":[36],"that":[37,109],"maps":[38],"embeddings":[40,83],"extracted":[41],"pretrained":[44],"model":[45],"onto":[46],"two":[47],"lower":[48],"dimensional":[49],"embedding":[50,53],"spaces.":[51],"The":[52],"spaces":[54],"are":[55],"learnt":[56],"disentangle":[58],"information":[60,64],"from":[61],"all":[62],"other":[63],"present":[65,89],"audio":[68],"recordings,":[69],"without":[70],"supervision":[71],"about":[72],"conditions.":[75],"analyze":[77],"robustness":[79],"various":[85],"sources":[86],"variability":[88],"signal":[92],"for":[93,125],"verification":[95],"and":[96],"clustering":[98],"tasks":[99],"on":[100,131],"large-scale":[102],"corpus.":[105],"Our":[106],"analyses":[107],"show":[108],"system":[112,137],"substantially":[113],"outperforms":[114],"baseline":[116],"variety":[119],"scenarios.":[123],"Furthermore,":[124],"task":[127],"diarization":[130,146],"real-world":[133],"meeting":[134],"corpus,":[135],"our":[136],"shows":[138],"relative":[140],"improvement":[141],"36%":[143],"error":[147],"rate":[148],"compared":[149],"state-of-the-art":[152],"baseline.":[153]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}