{"id":"https://openalex.org/W4392903355","doi":"https://doi.org/10.1109/icassp48485.2024.10447715","title":"Efficient Black-Box Speaker Verification Model Adaptation With Reprogramming And Backend Learning","display_name":"Efficient Black-Box Speaker Verification Model Adaptation With Reprogramming And Backend Learning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903355","doi":"https://doi.org/10.1109/icassp48485.2024.10447715"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447715","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101527946","display_name":"Jingyu Li","orcid":"https://orcid.org/0000-0002-1163-4557"},"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":["The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"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":["The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Electronic Engineering,Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"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":2,"corresponding_author_ids":["https://openalex.org/A5101527946"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61697932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"28","issue":null,"first_page":"12732","last_page":"12736"},"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":0.9962000250816345,"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":0.9958000183105469,"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":0.8590180277824402},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.7011536359786987},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.639389157295227},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.599725067615509},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5627278089523315},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5241183042526245},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.522239089012146},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5106151700019836},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4959963262081146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.481513112783432},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.440502405166626},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3404323160648346},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2681675851345062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8590180277824402},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.7011536359786987},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.639389157295227},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.599725067615509},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5627278089523315},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5241183042526245},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.522239089012146},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5106151700019836},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4959963262081146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.481513112783432},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.440502405166626},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3404323160648346},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2681675851345062},{"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447715","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447715","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":32,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2793459270","https://openalex.org/W2801581493","https://openalex.org/W2807373279","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2963450999","https://openalex.org/W2969985801","https://openalex.org/W2981087920","https://openalex.org/W3015598461","https://openalex.org/W3024869864","https://openalex.org/W3037590244","https://openalex.org/W3095862185","https://openalex.org/W3096127734","https://openalex.org/W3209059054","https://openalex.org/W4224919627","https://openalex.org/W4282961290","https://openalex.org/W4283008665","https://openalex.org/W4372260195","https://openalex.org/W4372341266","https://openalex.org/W4372346241","https://openalex.org/W4385823335","https://openalex.org/W6620707391","https://openalex.org/W6752946794","https://openalex.org/W6779945560","https://openalex.org/W6796456916","https://openalex.org/W6839562487","https://openalex.org/W6847613944"],"related_works":["https://openalex.org/W3184396788","https://openalex.org/W4377865163","https://openalex.org/W4312601715","https://openalex.org/W3193857078","https://openalex.org/W4392828243","https://openalex.org/W2888956734","https://openalex.org/W4312822655","https://openalex.org/W3000197790","https://openalex.org/W3157170264","https://openalex.org/W4315865067"],"abstract_inverted_index":{"The":[0,73,115,132,159],"development":[1],"of":[2,12,70,134],"deep":[3],"neural":[4],"networks":[5],"(DNN)":[6],"has":[7],"significantly":[8],"enhanced":[9],"the":[10,39,44,62,68,83,97,100,104,108,112,127,138,150,172,181],"performance":[11,40,179],"speaker":[13,130],"verification":[14],"(SV)":[15],"systems":[16,30],"in":[17,31,82,137,143,163,185],"recent":[18],"years.":[19],"However,":[20],"a":[21,87,121],"critical":[22],"issue":[23],"that":[24],"persists":[25],"when":[26],"applying":[27],"DNN-based":[28,57],"SV":[29,58,75],"practical":[32],"applications":[33],"is":[34,93,118,141],"domain":[35,46],"mismatch.":[36],"To":[37],"mitigate":[38],"degradation":[41],"caused":[42],"by":[43,60,67,120],"mismatch,":[45],"adaptation":[47],"becomes":[48],"necessary.":[49],"This":[50],"paper":[51],"introduces":[52],"an":[53],"approach":[54],"to":[55,95,180],"adapt":[56],"models":[59,184],"manipulating":[61],"learnable":[63,101],"model":[64,76],"inputs,":[65],"inspired":[66],"concept":[69],"adversarial":[71],"reprogramming.":[72],"pre-trained":[74],"remains":[77],"fixed":[78],"and":[79,156],"functions":[80],"solely":[81],"forward":[84],"process,":[85],"resembling":[86],"black-box":[88,113],"model.":[89,114],"A":[90],"lightweight":[91],"network":[92],"utilized":[94],"estimate":[96],"gradients":[98],"for":[99],"parameters":[102,135],"at":[103],"input,":[105],"which":[106,188],"bypasses":[107],"gradient":[109,139],"back-propagation":[110],"through":[111],"reprogrammed":[116],"output":[117],"processed":[119],"two-layer":[122],"backend":[123],"learning":[124],"module":[125],"as":[126],"final":[128],"adapted":[129],"embedding.":[131],"number":[133],"involved":[136],"calculation":[140],"small":[142],"our":[144,186],"design.":[145],"With":[146],"few":[147],"additional":[148],"parameters,":[149],"proposed":[151,173],"method":[152,174],"achieves":[153],"both":[154],"memory":[155],"parameter":[157],"efficiency.":[158],"experiments":[160],"are":[161],"conducted":[162],"language":[164],"mismatch":[165],"scenarios.":[166],"Using":[167],"much":[168],"less":[169],"computation":[170],"cost,":[171],"obtains":[175],"close":[176],"or":[177],"superior":[178],"fully":[182],"finetuned":[183],"experiments,":[187],"demonstrates":[189],"its":[190],"effectiveness.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}