{"id":"https://openalex.org/W4375868932","doi":"https://doi.org/10.1109/icassp49357.2023.10096659","title":"Pretraining Conformer with ASR for Speaker Verification","display_name":"Pretraining Conformer with ASR for Speaker Verification","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868932","doi":"https://doi.org/10.1109/icassp49357.2023.10096659"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096659","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":"conference-paper","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/A5090055875","display_name":"Danwei Cai","orcid":"https://orcid.org/0000-0002-5122-0623"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danwei Cai","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,USA","Department of Electrical and Computer Engineering, Duke University, Durham, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100372965","display_name":"Weiqing Wang","orcid":"https://orcid.org/0000-0002-9578-819X"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiqing Wang","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,USA","Department of Electrical and Computer Engineering, Duke University, Durham, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Duke University,Department of Electrical and Computer Engineering,Durham,USA","Data Science Research Center, Duke Kunshan University, Kunshan, China","Department of Electrical and Computer Engineering, Duke University, Durham, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University,Department of Electrical and Computer Engineering,Durham,USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Data Science Research Center, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035534911","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0002-0621-1058"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["Speech, Audio, and Music (SAMI) Group,Bytedance,China","Speech, Audio, and Music (SAMI) Group, Bytedance, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music (SAMI) Group,Bytedance,China","institution_ids":[]},{"raw_affiliation_string":"Speech, Audio, and Music (SAMI) Group, Bytedance, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018343941","display_name":"Chuanzeng Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuanzeng Huang","raw_affiliation_strings":["Speech, Audio, and Music (SAMI) Group,Bytedance,China","Speech, Audio, and Music (SAMI) Group, Bytedance, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech, Audio, and Music (SAMI) Group,Bytedance,China","institution_ids":[]},{"raw_affiliation_string":"Speech, Audio, and Music (SAMI) Group, Bytedance, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4846,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9415048,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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":0.9980000257492065,"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":0.9957000017166138,"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/conformational-isomerism","display_name":"Conformational isomerism","score":0.9215035438537598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7640876770019531},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6721370816230774},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540972888469696},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47771382331848145},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4667190909385681},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4333902895450592},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36892378330230713},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3315545916557312},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2678629755973816},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07759985327720642}],"concepts":[{"id":"https://openalex.org/C18705241","wikidata":"https://www.wikidata.org/wiki/Q1128023","display_name":"Conformational isomerism","level":3,"score":0.9215035438537598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640876770019531},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6721370816230774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540972888469696},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47771382331848145},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4667190909385681},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4333902895450592},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36892378330230713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3315545916557312},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2678629755973816},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07759985327720642},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C32909587","wikidata":"https://www.wikidata.org/wiki/Q11369","display_name":"Molecule","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096659","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W996208672","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2549139847","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2747165665","https://openalex.org/W2752782242","https://openalex.org/W2794506738","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2928165649","https://openalex.org/W2963371159","https://openalex.org/W2964110616","https://openalex.org/W2969985801","https://openalex.org/W2974231335","https://openalex.org/W2999547272","https://openalex.org/W3010893827","https://openalex.org/W3010925296","https://openalex.org/W3013020904","https://openalex.org/W3024541814","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3097777922","https://openalex.org/W3142516134","https://openalex.org/W3163842642","https://openalex.org/W3174726724","https://openalex.org/W3198275944","https://openalex.org/W3202370288","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221154745","https://openalex.org/W4234330420","https://openalex.org/W4385245566","https://openalex.org/W6688816777","https://openalex.org/W6739901393","https://openalex.org/W6767671539","https://openalex.org/W6775243439","https://openalex.org/W6784686509"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W2490526372","https://openalex.org/W4221142204"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"to":[3,76,83,93,111],"pretrain":[4],"Conformer":[5,15,35,50,60,90,107],"with":[6,65,108],"automatic":[7,41],"speech":[8],"recognition":[9,68],"(ASR)":[10],"task":[11],"for":[12,24,40,52,99],"speaker":[13,42,67,84,100],"verification.":[14,43,85,101],"combines":[16],"convolution":[17],"neural":[18],"network":[19],"(CNN)":[20],"and":[21,27,124,130],"Transformer":[22],"model":[23,116,120],"modeling":[25],"local":[26],"global":[28],"features,":[29],"respectively.":[30,132],"Recently,":[31],"multi-scale":[32],"feature":[33],"aggregation":[34],"(MFA-Conformer)":[36],"has":[37],"been":[38],"proposed":[39],"MFA-Conformer":[44,98],"concatenates":[45],"frame-level":[46],"outputs":[47],"from":[48,81],"all":[49],"blocks":[51],"further":[53],"pooling.":[54],"However,":[55],"our":[56],"experiments":[57,103],"show":[58,104],"that":[59,105],"can":[61],"be":[62],"easily":[63],"overfitted":[64],"limited":[66],"training":[69,96],"data.":[70],"To":[71],"avoid":[72],"overfitting,":[73],"we":[74],"propose":[75],"transfer":[77],"the":[78,95],"knowledge":[79],"learned":[80],"ASR":[82,88,109],"Specifically,":[86],"an":[87],"pretrained":[89],"is":[91],"used":[92],"initialize":[94],"of":[97],"Our":[102],"pretraining":[106],"leads":[110],"significant":[112],"performance":[113],"gains":[114],"across":[115],"sizes.":[117],"The":[118],"best":[119],"achieves":[121],"0.48%,":[122],"0.71%":[123],"1.54%":[125],"EER":[126],"on":[127],"Voxceleb1-O,":[128],"Voxceleb1-E,":[129],"Voxceleb1-H,":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}