{"id":"https://openalex.org/W3015964387","doi":"https://doi.org/10.1109/icassp40776.2020.9054134","title":"Multi-Level Deep Neural Network Adaptation for Speaker Verification Using MMD and Consistency Regularization","display_name":"Multi-Level Deep Neural Network Adaptation for Speaker Verification Using MMD and Consistency Regularization","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015964387","doi":"https://doi.org/10.1109/icassp40776.2020.9054134","mag":"3015964387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054134","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107142/1/Lin_Multi-Level_Deep_Neural.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090644975","display_name":"Weiwei Lin","orcid":"https://orcid.org/0000-0002-9241-0271"},"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":true,"raw_author_name":"Weiwei Lin","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087595528","display_name":"Man-Mai Mak","orcid":null},"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-Mai Mak","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Tencent AI Lab, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090644975"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":3.8414,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.94474513,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6839","last_page":"6843"},"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":0.9961000084877014,"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":0.9904999732971191,"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/computer-science","display_name":"Computer science","score":0.7726911306381226},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.6892099976539612},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6324007511138916},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5892781019210815},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5744008421897888},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.56456458568573},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5445199608802795},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5355624556541443},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4944603443145752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44328880310058594},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44101274013519287},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.440432608127594},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4264652729034424},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33494454622268677},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.33465293049812317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7726911306381226},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.6892099976539612},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6324007511138916},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5892781019210815},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5744008421897888},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.56456458568573},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5445199608802795},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5355624556541443},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4944603443145752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44328880310058594},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44101274013519287},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.440432608127594},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4264652729034424},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33494454622268677},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.33465293049812317},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054134","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:10397/107142","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107142","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107142/1/Lin_Multi-Level_Deep_Neural.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:10397/107142","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/107142","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/107142/1/Lin_Multi-Level_Deep_Neural.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":[{"display_name":"Quality Education","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3015964387.pdf","grobid_xml":"https://content.openalex.org/works/W3015964387.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1487641199","https://openalex.org/W1522301498","https://openalex.org/W1617650991","https://openalex.org/W2125865219","https://openalex.org/W2156557681","https://openalex.org/W2159291411","https://openalex.org/W2402146185","https://openalex.org/W2404617565","https://openalex.org/W2584886900","https://openalex.org/W2590953969","https://openalex.org/W2735780771","https://openalex.org/W2747476845","https://openalex.org/W2756073160","https://openalex.org/W2807246346","https://openalex.org/W2888473984","https://openalex.org/W2890964092","https://openalex.org/W2942203175","https://openalex.org/W2962788262","https://openalex.org/W2963446838","https://openalex.org/W2964121744","https://openalex.org/W2964154960","https://openalex.org/W2970971581","https://openalex.org/W4295312788","https://openalex.org/W6629354409","https://openalex.org/W6631190155","https://openalex.org/W6636267554","https://openalex.org/W6678814708","https://openalex.org/W6683633756","https://openalex.org/W6712930963","https://openalex.org/W6761827036","https://openalex.org/W6766978945"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W2767892728","https://openalex.org/W4235705411","https://openalex.org/W3095180122","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506"],"abstract_inverted_index":{"Adapting":[0],"speaker":[1,31,114],"verification":[2],"(SV)":[3],"systems":[4],"to":[5,88,117],"a":[6,10,41,101,161],"new":[7],"environment":[8],"is":[9,26],"very":[11],"challenging":[12],"task.":[13],"Current":[14],"adaptation":[15,25,43,85,131,140,166],"methods":[16],"in":[17,167],"SV":[18],"mainly":[19],"focus":[20],"on":[21,121],"the":[22,30,84,89,112,136,153],"backend,":[23],"i.e,":[24],"carried":[27],"out":[28],"after":[29],"embeddings":[32,115],"have":[33],"been":[34],"created.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39,80,99,159],"present":[40],"DNN-based":[42],"method":[44,51,70,145,155],"using":[45],"maximum":[46],"mean":[47],"discrepancy":[48,65,73,91],"(MMD).":[49],"Our":[50],"exploits":[52],"two":[53],"important":[54],"aspects":[55],"neglected":[56],"by":[57],"previous":[58],"research.":[59],"First,":[60],"instead":[61],"of":[62],"minimizing":[63],"domain":[64,72],"at":[66,74],"utterance-level":[67],"alone,":[68],"our":[69,129,144],"minimizes":[71],"both":[75],"frame-level":[76],"and":[77,95,125],"utterance-level,":[78],"which":[79],"believe":[81],"will":[82],"make":[83],"more":[86],"robust":[87,116],"duration":[90],"between":[92],"training":[93],"data":[94],"test":[96],"data.":[97,107],"Second,":[98],"introduce":[100],"consistency":[102,109],"regularization":[103,110],"for":[104],"unlabelled":[105],"target-domain":[106],"The":[108],"encourages":[111],"target":[113],"adverse":[118],"perturbations.":[119],"Experiments":[120],"NIST":[122],"SRE":[123],"2016":[124],"2018":[126],"show":[127],"that":[128],"DNN":[130,139],"works":[132,146],"significantly":[133],"better":[134],"than":[135],"previously":[137],"proposed":[138,154],"methods.":[141],"What's":[142],"more,":[143],"well":[147],"with":[148,156],"backend":[149,157,165],"adaptation.":[150],"By":[151],"combining":[152],"adaptation,":[158],"achieve":[160],"9%":[162],"improvement":[163],"over":[164],"SRE18.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}