{"id":"https://openalex.org/W4372346385","doi":"https://doi.org/10.1109/icassp49357.2023.10096915","title":"Pushing the Limits of Self-Supervised Speaker Verification using Regularized Distillation Framework","display_name":"Pushing the Limits of Self-Supervised Speaker Verification using Regularized Distillation Framework","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372346385","doi":"https://doi.org/10.1109/icassp49357.2023.10096915"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096915","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/A5003578886","display_name":"Yafeng Chen","orcid":"https://orcid.org/0000-0002-5459-4428"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Yafeng Chen","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101700479","display_name":"Siqi Zheng","orcid":"https://orcid.org/0000-0002-5481-7900"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460850","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8814-1988"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891716","display_name":"Luyao Cheng","orcid":"https://orcid.org/0009-0006-1311-8448"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Luyao Cheng","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X"},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Alibaba Group,Speech Lab of DAMO Academy","Speech Lab of DAMO Academy, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab of DAMO Academy","institution_ids":["https://openalex.org/I4210086143"]},{"raw_affiliation_string":"Speech Lab of DAMO Academy, Alibaba Group","institution_ids":["https://openalex.org/I4210086143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210086143"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9983999729156494,"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":0.9951000213623047,"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/regularization","display_name":"Regularization (linguistics)","score":0.8412590026855469},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7551438808441162},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5962570905685425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5598388314247131},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5274874567985535},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4809072017669678},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4647117853164673},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4472429156303406},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4301607012748718},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3990802764892578},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3920474648475647},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.35448962450027466},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34744757413864136}],"concepts":[{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.8412590026855469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7551438808441162},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5962570905685425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5598388314247131},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5274874567985535},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4809072017669678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4647117853164673},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4472429156303406},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4301607012748718},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3990802764892578},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3920474648475647},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.35448962450027466},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34744757413864136},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096915","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096915","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2842511635","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W2972405707","https://openalex.org/W2972450593","https://openalex.org/W3005680577","https://openalex.org/W3035060554","https://openalex.org/W3035524453","https://openalex.org/W3044308976","https://openalex.org/W3159481202","https://openalex.org/W3161606033","https://openalex.org/W3163187953","https://openalex.org/W3202801947","https://openalex.org/W3205635414","https://openalex.org/W4200633018","https://openalex.org/W4280634406","https://openalex.org/W4286695273","https://openalex.org/W4287635082","https://openalex.org/W4296068770","https://openalex.org/W4296069299","https://openalex.org/W4297808394","https://openalex.org/W4297841773","https://openalex.org/W6774314701","https://openalex.org/W6779326418","https://openalex.org/W6781368565","https://openalex.org/W6784330115","https://openalex.org/W6795754764"],"related_works":["https://openalex.org/W4235705411","https://openalex.org/W1521299571","https://openalex.org/W1996621592","https://openalex.org/W2134501921","https://openalex.org/W204267554","https://openalex.org/W2147062549","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W4317103504","https://openalex.org/W3096066489"],"abstract_inverted_index":{"Training":[0],"robust":[1],"speaker":[2,6,106,113],"verification":[3,114],"systems":[4],"without":[5],"labels":[7,41],"has":[8],"long":[9],"been":[10],"a":[11,17,32,117],"challenging":[12],"task.":[13],"Previous":[14],"studies":[15],"observed":[16],"large":[18],"performance":[19,115],"gap":[20],"between":[21],"self-supervised":[22,34,119],"and":[23,43,85],"fully":[24],"supervised":[25],"methods.":[26],"In":[27],"this":[28],"paper,":[29],"we":[30],"apply":[31],"non-contrastive":[33],"learning":[35],"framework":[36,104],"called":[37],"DIstillation":[38],"with":[39],"NO":[40],"(DINO)":[42],"propose":[44],"two":[45],"regularization":[46,54,65],"terms":[47],"applied":[48],"to":[49],"embeddings":[50],"in":[51,105],"DINO.":[52],"One":[53],"term":[55,66],"guarantees":[56],"the":[57,60,63,68,94,98,101,111],"diversity":[58],"of":[59,70,75,90,100],"embeddings,":[61],"while":[62],"other":[64],"decorrelates":[67],"variables":[69],"each":[71],"embedding.":[72],"The":[73],"effectiveness":[74],"various":[76],"data":[77],"augmentation":[78],"techniques":[79],"are":[80],"explored,":[81],"on":[82,93,121],"both":[83],"time":[84],"frequency":[86],"domain.":[87],"A":[88],"range":[89],"experiments":[91],"conducted":[92],"VoxCeleb":[95],"datasets":[96],"demonstrate":[97],"superiority":[99],"regularized":[102],"DINO":[103],"verification.":[107],"Our":[108],"method":[109],"achieves":[110],"stateof-the-art":[112],"under":[116],"singlestage":[118],"setting":[120],"VoxCeleb.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
