{"id":"https://openalex.org/W4283008665","doi":"https://doi.org/10.21437/interspeech.2022-967","title":"EDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verification","display_name":"EDITnet: A Lightweight Network for Unsupervised Domain Adaptation in Speaker Verification","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283008665","doi":"https://doi.org/10.21437/interspeech.2022-967"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-967","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-967","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100379862","display_name":"Jingyu Li","orcid":"https://orcid.org/0000-0001-9909-0277"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyu Li","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100431792","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3865-8145"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100379862"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.9355,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.7588343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"3694","last_page":"3698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9739999771118164,"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/T10860","display_name":"Speech and Audio Processing","score":0.9728999733924866,"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":0.8155800104141235},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6857379674911499},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6201789379119873},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5888198614120483},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5528782606124878},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5472119450569153},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.525489866733551},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5102353096008301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.503246009349823},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4743993282318115},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46681949496269226},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4579519033432007},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41957271099090576},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.41098552942276},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34669962525367737},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07377684116363525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8155800104141235},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6857379674911499},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6201789379119873},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5888198614120483},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5528782606124878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5472119450569153},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.525489866733551},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5102353096008301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503246009349823},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4743993282318115},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46681949496269226},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4579519033432007},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41957271099090576},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.41098552942276},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34669962525367737},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07377684116363525},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-967","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-967","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1006777433","https://openalex.org/W1522301498","https://openalex.org/W1882958252","https://openalex.org/W2046056978","https://openalex.org/W2188365844","https://openalex.org/W2191779130","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2801581493","https://openalex.org/W2807373279","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2936780106","https://openalex.org/W2963263347","https://openalex.org/W2963275094","https://openalex.org/W2963450999","https://openalex.org/W2964288524","https://openalex.org/W2973099347","https://openalex.org/W2981087920","https://openalex.org/W3013020904","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3037590244","https://openalex.org/W3038083940","https://openalex.org/W3095862185","https://openalex.org/W3096127734","https://openalex.org/W3097470351","https://openalex.org/W3103152812","https://openalex.org/W3160646455","https://openalex.org/W3198506310","https://openalex.org/W4283014282","https://openalex.org/W4295312788","https://openalex.org/W4309845474","https://openalex.org/W4391602018"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2134501921","https://openalex.org/W3095180122","https://openalex.org/W2144470400"],"abstract_inverted_index":{"Performance":[0],"degradation":[1],"caused":[2],"by":[3,110,116],"language":[4],"mismatch":[5],"is":[6,62,90],"a":[7,12,24,44],"common":[8],"problem":[9,34],"when":[10],"applying":[11],"speaker":[13,36,40],"verification":[14],"system":[15],"on":[16,35,64,101],"speech":[17],"data":[18],"in":[19],"different":[20,78],"languages.This":[21],"paper":[22],"proposes":[23],"domain":[25,54],"transfer":[26,49],"network,":[27],"named":[28],"EDITnet,":[29,85],"to":[30,48,70],"alleviate":[31],"the":[32,52,56,65,72,80,84,86,96,107,113,120],"language-mismatch":[33],"embeddings":[37,50,67,76,108],"without":[38,92],"requiring":[39],"labels.The":[41],"network":[42],"leverages":[43],"conditional":[45],"variational":[46],"auto-encoder":[47],"from":[51,77],"target":[53],"into":[55],"source":[57],"domain.A":[58],"self-supervised":[59],"learning":[60],"strategy":[61],"imposed":[63],"transferred":[66,109],"so":[68],"as":[69],"increase":[71],"cosine":[73],"distance":[74],"between":[75],"speakers.In":[79],"training":[81,97],"process":[82],"of":[83],"embedding":[87,129],"extraction":[88,130],"model":[89],"fixed":[91],"fine-tuning,":[93],"which":[94],"renders":[95],"efficient":[98],"and":[99,103],"low-cost.Experiments":[100],"Voxceleb":[102],"CN-Celeb":[104],"show":[105],"that":[106],"ED-ITnet":[111],"outperform":[112],"un-transferred":[114],"ones":[115],"around":[117],"30%":[118],"with":[119,127],"ECAPA-TDNN512.Performance":[121],"improvement":[122],"can":[123],"also":[124],"be":[125],"achieved":[126],"other":[128],"models,":[131],"e.g.,":[132],"TDNN,":[133],"SE-ResNet34.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}