{"id":"https://openalex.org/W3015301038","doi":"https://doi.org/10.1109/icassp40776.2020.9053735","title":"Information Maximized Variational Domain Adversarial Learning for Speaker Verification","display_name":"Information Maximized Variational Domain Adversarial Learning for Speaker Verification","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015301038","doi":"https://doi.org/10.1109/icassp40776.2020.9053735","mag":"3015301038"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053735","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107138/1/Tu_Information_Maximized_Variational.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019467579","display_name":"Youzhi Tu","orcid":"https://orcid.org/0000-0002-9580-2414"},"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":"Youzhi Tu","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","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, Hong Kong SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, National Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, National Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6449","last_page":"6453"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9926999807357788,"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":0.9836999773979187,"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":0.8806694746017456},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.772282063961029},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6347684264183044},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6261391043663025},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6109749674797058},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5876665115356445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.578402578830719},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.569980263710022},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4755782186985016},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.45623278617858887},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4508136212825775},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44604507088661194},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43479806184768677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42415690422058105},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3749232292175293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35679197311401367},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14941474795341492}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8806694746017456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772282063961029},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6347684264183044},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6261391043663025},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6109749674797058},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5876665115356445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.578402578830719},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.569980263710022},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4755782186985016},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.45623278617858887},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4508136212825775},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44604507088661194},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43479806184768677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42415690422058105},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3749232292175293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35679197311401367},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14941474795341492},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053735","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053735","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:ira.lib.polyu.edu.hk:10397/107138","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107138","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107138/1/Tu_Information_Maximized_Variational.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:10397/107138","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107138","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107138/1/Tu_Information_Maximized_Variational.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":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015301038.pdf","grobid_xml":"https://content.openalex.org/works/W3015301038.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W101682403","https://openalex.org/W866349134","https://openalex.org/W1731081199","https://openalex.org/W1932968309","https://openalex.org/W1959608418","https://openalex.org/W2067301010","https://openalex.org/W2069739265","https://openalex.org/W2099471712","https://openalex.org/W2125865219","https://openalex.org/W2150769028","https://openalex.org/W2181594395","https://openalex.org/W2395750323","https://openalex.org/W2406312423","https://openalex.org/W2775654873","https://openalex.org/W2799976677","https://openalex.org/W2801581493","https://openalex.org/W2804397569","https://openalex.org/W2807692250","https://openalex.org/W2888473984","https://openalex.org/W2890964092","https://openalex.org/W2903782687","https://openalex.org/W2910135751","https://openalex.org/W2937418893","https://openalex.org/W2937866564","https://openalex.org/W2962738009","https://openalex.org/W2962911072","https://openalex.org/W2962928126","https://openalex.org/W2962964508","https://openalex.org/W2963090522","https://openalex.org/W2963145887","https://openalex.org/W2963223306","https://openalex.org/W2963450999","https://openalex.org/W2963987720","https://openalex.org/W2964000524","https://openalex.org/W2964168257","https://openalex.org/W2972899181","https://openalex.org/W2972956697","https://openalex.org/W2973099347","https://openalex.org/W2981087920","https://openalex.org/W3039832962","https://openalex.org/W4293568373","https://openalex.org/W4297940714","https://openalex.org/W4320013936","https://openalex.org/W6610566761","https://openalex.org/W6623950054","https://openalex.org/W6637618735","https://openalex.org/W6640963894","https://openalex.org/W6668080254","https://openalex.org/W6678814708","https://openalex.org/W6713727690","https://openalex.org/W6738543193","https://openalex.org/W6747888389","https://openalex.org/W6749101112","https://openalex.org/W6749820799","https://openalex.org/W6751660789","https://openalex.org/W6753417141","https://openalex.org/W6755991023","https://openalex.org/W6758151150","https://openalex.org/W6780248173"],"related_works":["https://openalex.org/W2053159670","https://openalex.org/W3148366653","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W2134501921","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W215245425","https://openalex.org/W4252590334"],"abstract_inverted_index":{"Domain":[0],"mismatch":[1,23],"is":[2,64,126],"a":[3,60],"common":[4],"problem":[5],"in":[6],"speaker":[7,37,86,123],"verification.":[8],"This":[9],"paper":[10],"proposes":[11],"an":[12,26],"information-maximized":[13],"variational":[14,50],"domain":[15,22,29],"adversarial":[16,30],"neural":[17],"network":[18],"(InfoVDANN)":[19],"to":[20,35,83,120],"reduce":[21],"by":[24],"incorporating":[25],"InfoVAE":[27,43],"into":[28],"training":[31,81],"(DAT).":[32],"DAT":[33],"aims":[34],"produce":[36],"discriminative":[38,87],"and":[39,79,93,114],"domain-invariant":[40],"features.":[41],"The":[42],"has":[44],"two":[45],"roles.":[46],"First,":[47],"it":[48,72],"performs":[49],"regularization":[51],"on":[52,90],"the":[53,67,77,80,97,100,107,111,118],"learned":[54],"features":[55,78,113,116],"so":[56],"that":[57,96,105,125],"they":[58],"follow":[59],"Gaussian":[61],"distribution,":[62],"which":[63,103],"essential":[65],"for":[66],"standard":[68],"PLDA":[69],"backend.":[70],"Second,":[71],"preserves":[73],"mutual":[74,108],"information":[75,109,124],"between":[76,110],"set":[82],"extract":[84,121],"extra":[85,122],"information.":[88],"Experiments":[89],"both":[91],"SRE16":[92],"SRE18-CMN2":[94],"show":[95],"InfoVDANN":[98,119],"outperforms":[99],"recent":[101],"VDANN,":[102],"suggests":[104],"increasing":[106],"latent":[112],"input":[115],"enables":[117],"otherwise":[127],"not":[128],"possible.":[129]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}