{"id":"https://openalex.org/W3047666748","doi":"https://doi.org/10.21437/interspeech.2020-2270","title":"Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings","display_name":"Cosine-Distance Virtual Adversarial Training for Semi-Supervised Speaker-Discriminative Acoustic Embeddings","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3047666748","doi":"https://doi.org/10.21437/interspeech.2020-2270","mag":"3047666748"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2270","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2008.03756","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069221660","display_name":"Florian Kreyssig","orcid":"https://orcid.org/0000-0002-8948-988X"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Florian L. Kreyssig","raw_affiliation_strings":["Univ. of Cambridge"],"affiliations":[{"raw_affiliation_string":"Univ. of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":["Univ. of Cambridge"],"affiliations":[{"raw_affiliation_string":"Univ. of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069221660"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.4114,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69589765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3241","last_page":"3245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9968000054359436,"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":0.8416367173194885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7507914304733276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6457595825195312},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6360434293746948},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6278950572013855},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5905059576034546},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5852203369140625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5071761608123779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4932255148887634},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.472819447517395},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4561116695404053},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4343462586402893},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.41526538133621216}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8416367173194885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7507914304733276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6457595825195312},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6360434293746948},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6278950572013855},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5905059576034546},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5852203369140625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5071761608123779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4932255148887634},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.472819447517395},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4561116695404053},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4343462586402893},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.41526538133621216},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-2270","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.03756","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03756","pdf_url":"https://arxiv.org/pdf/2008.03756","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:3047666748","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2008.03756.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":"doi:10.48550/arxiv.2008.03756","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.03756","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:2008.03756","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.03756","pdf_url":"https://arxiv.org/pdf/2008.03756","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":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3047666748.pdf","grobid_xml":"https://content.openalex.org/works/W3047666748.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1596641231","https://openalex.org/W1975113979","https://openalex.org/W2046056978","https://openalex.org/W2101210369","https://openalex.org/W2101234009","https://openalex.org/W2130037226","https://openalex.org/W2131775048","https://openalex.org/W2143577772","https://openalex.org/W2146766088","https://openalex.org/W2150769028","https://openalex.org/W2402146185","https://openalex.org/W2404463488","https://openalex.org/W2530816535","https://openalex.org/W2592691248","https://openalex.org/W2748488820","https://openalex.org/W2889060826","https://openalex.org/W2890964092","https://openalex.org/W2938372602","https://openalex.org/W2951970475","https://openalex.org/W2963207607","https://openalex.org/W2963466847","https://openalex.org/W2963558289","https://openalex.org/W2963654251","https://openalex.org/W2963956526","https://openalex.org/W2963962398","https://openalex.org/W2964153729","https://openalex.org/W2964159205","https://openalex.org/W2969985801","https://openalex.org/W2972451838","https://openalex.org/W2972680151","https://openalex.org/W2972986505","https://openalex.org/W2973190269","https://openalex.org/W2979593053","https://openalex.org/W2981608174","https://openalex.org/W3016175755","https://openalex.org/W3025125834","https://openalex.org/W3097794099"],"related_works":["https://openalex.org/W3097679055","https://openalex.org/W3170521904","https://openalex.org/W3205635414","https://openalex.org/W3015237657","https://openalex.org/W3165947001","https://openalex.org/W2181464176","https://openalex.org/W2766945538","https://openalex.org/W2997481653","https://openalex.org/W2968706510","https://openalex.org/W3205724820","https://openalex.org/W3100137005","https://openalex.org/W2991213871","https://openalex.org/W3183932535","https://openalex.org/W3091067756","https://openalex.org/W2949257576","https://openalex.org/W3096651426","https://openalex.org/W3116292642","https://openalex.org/W2894798093","https://openalex.org/W2801602507","https://openalex.org/W2407575458"],"abstract_inverted_index":{"In":[0,99],"this":[1],"paper,":[2],"we":[3,90],"propose":[4],"a":[5,57,69,141,147,158],"semi-supervised":[6],"learning":[7],"(SSL)":[8],"technique":[9,44,55,93],"for":[10,34,47,179],"training":[11,62,97,174],"deep":[12],"neural":[13],"networks":[14],"(DNNs)":[15],"to":[16,101,112,157],"generate":[17],"speaker-discriminative":[18],"acoustic":[19],"embeddings":[20],"(speaker":[21],"embeddings).":[22],"Obtaining":[23],"large":[24],"amounts":[25],"of":[26,59,68,77,118,128,154,165],"speaker":[27,79,142,177],"recognition":[28],"train-ing":[29],"data":[30,49,108,137,182],"can":[31],"be":[32,170],"difficult":[33],"desired":[35],"target":[36],"domains,":[37],"especially":[38],"under":[39],"privacy":[40],"constraints.":[41],"The":[42,54,126],"proposed":[43],"reduces":[45],"requirements":[46],"labelled":[48,124],"by":[50,86],"leveraging":[51],"unlabelled":[52,107,181],"data.":[53,125],"is":[56,72,130,163],"variant":[58],"virtual":[60,95],"adversarial":[61,96],"(VAT)":[63],"[1]":[64],"in":[65,149],"the":[66,75,78,87,92,106,115,123,133,166,176,180],"form":[67],"loss":[70],"that":[71,168],"defined":[73],"as":[74,84,122],"robustness":[76],"embedding":[80],"against":[81],"input":[82],"perturbations,":[83],"measured":[85],"cosine-distance.":[88],"Thus,":[89],"term":[91],"cosine-distance":[94],"(CD-VAT).":[98],"comparison":[100],"many":[102],"existing":[103],"SSL":[104],"techniques,":[105],"does":[109],"not":[110],"have":[111],"come":[113],"from":[114,172],"same":[116],"set":[117],"classes":[119],"(here":[120],"speakers)":[121],"effectiveness":[127],"CD-VAT":[129],"shown":[131],"on":[132,140],"2750+":[134],"hour":[135],"VoxCeleb":[136],"set,":[138],"where":[139],"verification":[143],"task":[144],"it":[145],"achieves":[146],"reduction":[148],"equal":[150],"error":[151],"rate":[152],"(EER)":[153],"11.1%":[155],"relative":[156],"purely":[159],"supervised":[160,173],"baseline.":[161],"This":[162],"32.5%":[164],"improvement":[167],"would":[169],"achieved":[171],"if":[175],"labels":[178],"were":[183],"available.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}