{"id":"https://openalex.org/W4372260283","doi":"https://doi.org/10.1109/icassp49357.2023.10096790","title":"Distance-Based Weight Transfer for Fine-Tuning From Near-Field to Far-Field Speaker Verification","display_name":"Distance-Based Weight Transfer for Fine-Tuning From Near-Field to Far-Field Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260283","doi":"https://doi.org/10.1109/icassp49357.2023.10096790"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5100425399","display_name":"Li Zhang","orcid":"https://orcid.org/0000-0001-5077-9962"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Zhang","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107808955","display_name":"Qing Wang","orcid":"https://orcid.org/0009-0008-5449-4815"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406825","display_name":"Hongji Wang","orcid":"https://orcid.org/0000-0002-8834-1592"},"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":"Hongji Wang","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387862","display_name":"Yue Li","orcid":"https://orcid.org/0000-0003-3906-7280"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072851763","display_name":"Wei Rao","orcid":null},"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":"Wei Rao","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084128157","display_name":"Yannan Wang","orcid":"https://orcid.org/0000-0001-7248-4954"},"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":"Yannan Wang","raw_affiliation_strings":["Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Corporation,Tencent Ethereal Audio Lab,Shenzhen,China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent Ethereal Audio Lab, Tencent Corporation, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University (NPU),Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xi’an,China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3053,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.83797201,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9991999864578247,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7527857422828674},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"Fine-tuning","score":0.6858317255973816},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6843542456626892},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4850101172924042},{"id":"https://openalex.org/keywords/norm","display_name":"Norm (philosophy)","score":0.4829915761947632},{"id":"https://openalex.org/keywords/near-and-far-field","display_name":"Near and far field","score":0.4658995568752289},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4574006199836731},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4287773370742798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42001569271087646},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.41931796073913574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37225112318992615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2422875463962555},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19564780592918396}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7527857422828674},{"id":"https://openalex.org/C157524613","wikidata":"https://www.wikidata.org/wiki/Q2828883","display_name":"Fine-tuning","level":2,"score":0.6858317255973816},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6843542456626892},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4850101172924042},{"id":"https://openalex.org/C191795146","wikidata":"https://www.wikidata.org/wiki/Q3878446","display_name":"Norm (philosophy)","level":2,"score":0.4829915761947632},{"id":"https://openalex.org/C25227671","wikidata":"https://www.wikidata.org/wiki/Q13405516","display_name":"Near and far field","level":2,"score":0.4658995568752289},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4574006199836731},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4287773370742798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42001569271087646},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.41931796073913574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37225112318992615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2422875463962555},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19564780592918396},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W123007118","https://openalex.org/W2029029543","https://openalex.org/W2062714872","https://openalex.org/W2121812409","https://openalex.org/W2219249508","https://openalex.org/W2360384684","https://openalex.org/W2404617565","https://openalex.org/W2726515241","https://openalex.org/W2784941364","https://openalex.org/W2801581493","https://openalex.org/W2910715461","https://openalex.org/W2936774411","https://openalex.org/W2963376890","https://openalex.org/W2963446838","https://openalex.org/W2963450999","https://openalex.org/W2964054038","https://openalex.org/W2969985801","https://openalex.org/W2981087920","https://openalex.org/W2992043355","https://openalex.org/W3015503328","https://openalex.org/W3015964387","https://openalex.org/W3024869864","https://openalex.org/W3094872920","https://openalex.org/W3096066489","https://openalex.org/W3128642798","https://openalex.org/W3212414183","https://openalex.org/W6688816777","https://openalex.org/W6769867024","https://openalex.org/W6771233102","https://openalex.org/W6773431534","https://openalex.org/W6775957535","https://openalex.org/W6790463934"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W3040691452","https://openalex.org/W4390929683","https://openalex.org/W2735783528"],"abstract_inverted_index":{"The":[0],"scarcity":[1],"of":[2,31,67,87,154],"labeled":[3],"far-field":[4,12,32],"speech":[5,26,33,97],"is":[6],"a":[7,28,57,122],"constraint":[8],"for":[9,136],"training":[10,36],"superior":[11],"speaker":[13],"verification":[14],"systems.":[15],"In":[16,52],"general,":[17],"fine-tuning":[18,42,83,173],"the":[19,40,65,68,71,75,79,82,88,94,104,108,114,118,128,152,155,169],"model":[20,73,120],"pre-trained":[21,72],"on":[22,107,158],"large-scale":[23,95],"near-":[24],"field":[25],"through":[27],"small":[29],"amount":[30],"substantially":[34],"outperforms":[35,176],"from":[37,44,93],"scratch.":[38],"However,":[39],"vanilla":[41,177],"suffers":[43],"two":[45],"limitations":[46],"\u2013":[47],"catastrophic":[48,100],"forgetting":[49],"and":[50,74,98,147,161,180],"overfitting.":[51],"this":[53],"paper,":[54],"we":[55],"propose":[56],"weight":[58,137,171],"transfer":[59,138,172],"regularization":[60],"(WTR)":[61],"loss":[62,116,157],"to":[63],"constrain":[64],"distance":[66],"weights":[69],"between":[70],"fine-tuned":[76,119],"model.":[77],"With":[78],"WTR":[80,115,156],"loss,":[81],"process":[84],"takes":[85],"advantage":[86],"previously":[89],"acquired":[90],"discriminative":[91],"ability":[92],"near-field":[96],"avoids":[99],"for-":[101],"getting.":[102],"Meanwhile,":[103],"analysis":[105],"based":[106],"PAC-Bayes":[109],"generalization":[110,124],"theory":[111],"indicates":[112],"that":[113,168],"makes":[117],"have":[121],"tighter":[123],"bound,":[125],"thus":[126],"mitigating":[127],"overfitting":[129],"problem.":[130],"Moreover,":[131],"three":[132],"different":[133],"norm":[134],"distances":[135],"are":[139,142],"explored,":[140],"which":[141],"L1-norm":[143],"distance,":[144,146],"L2-norm":[145],"Max-norm":[148],"distance.":[149],"We":[150],"evaluate":[151],"effectiveness":[153],"VoxCeleb":[159],"(pre-trained)":[160],"FFSVC":[162],"(fine-tuned)":[163],"datasets.":[164],"Experimental":[165],"results":[166],"show":[167],"distance-based":[170],"strategy":[174],"significantly":[175],"fine-":[178],"tuning":[179],"other":[181],"competitive":[182],"domain":[183],"adaptation":[184],"methods.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}