{"id":"https://openalex.org/W4408353935","doi":"https://doi.org/10.1109/icassp49660.2025.10890786","title":"Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision","display_name":"Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353935","doi":"https://doi.org/10.1109/icassp49660.2025.10890786"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10890786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yafeng Chen","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"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/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siqi Zheng","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101427481","display_name":"Hui Wang","orcid":"https://orcid.org/0000-0002-8051-3695"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"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/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luyao Cheng","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428456","display_name":"Qian Chen","orcid":"https://orcid.org/0000-0002-1909-302X"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686893","display_name":"Chong Deng","orcid":"https://orcid.org/0000-0002-7287-7042"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chong Deng","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101777591","display_name":"Shiliang Zhang","orcid":"https://orcid.org/0000-0002-9524-1602"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiliang Zhang","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396367","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-6076-9714"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Alibaba Group,Speech Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group,Speech Lab","institution_ids":["https://openalex.org/I4210095624"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210095624"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"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":0.9894000291824341,"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":0.9894000291824341,"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":0.984499990940094,"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":0.9775000214576721,"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":0.7404149174690247},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.7071041464805603},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.438234806060791},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4117732048034668},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.332552969455719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404149174690247},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.7071041464805603},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.438234806060791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4117732048034668},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.332552969455719},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10890786","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10890786","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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":30,"referenced_works":["https://openalex.org/W2034996255","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2936774411","https://openalex.org/W3024869864","https://openalex.org/W3035524453","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3205635414","https://openalex.org/W4200633018","https://openalex.org/W4221144444","https://openalex.org/W4290995108","https://openalex.org/W4319862473","https://openalex.org/W4372346385","https://openalex.org/W4385823202","https://openalex.org/W4392910494","https://openalex.org/W4396982391","https://openalex.org/W4402112128","https://openalex.org/W4402115998","https://openalex.org/W6638667902","https://openalex.org/W6682962330","https://openalex.org/W6688816777","https://openalex.org/W6739879593","https://openalex.org/W6774314701","https://openalex.org/W6779326418","https://openalex.org/W6844194202","https://openalex.org/W6851784095","https://openalex.org/W6857495872"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Training":[0],"speaker-discriminative":[1],"and":[2,67,148,154,178],"robust":[3],"speaker":[4,9,23,34,127,138,163],"verification":[5,24,128,139,184],"systems":[6],"without":[7,160],"explicit":[8],"labels":[10,164],"remains":[11],"a":[12,20,94,106,132],"persistent":[13],"challenge.":[14],"In":[15],"this":[16,102],"paper,":[17],"we":[18,104],"propose":[19],"novel":[21],"self-supervised":[22,33,126],"approach,":[25],"Self-Distillation":[26],"Prototypes":[27],"Network":[28],"(SDPN),":[29],"which":[30],"effectively":[31],"facilitates":[32],"representation":[35,40,54],"learning.":[36],"SDPN":[37,78,124,130],"assigns":[38],"the":[39,42,49,53,56,65,77,81,91,117,121,136,183],"of":[41,45,55,73,123],"augmented":[43,66],"views":[44],"an":[46],"utterance":[47],"to":[48,71,84,110,182],"same":[50],"prototypes":[51,174],"as":[52,97],"original":[57,68],"view,":[58],"thereby":[59],"enabling":[60],"effective":[61],"knowledge":[62],"transfer":[63],"between":[64],"views.":[69],"Due":[70],"lack":[72],"negative":[74],"pairs":[75,87],"in":[76,90,112,165,175],"training":[79],"process,":[80],"network":[82,177],"tends":[83],"align":[85],"positive":[86],"quite":[88],"closely":[89],"embedding":[92],"space,":[93],"phenomenon":[95],"known":[96],"model":[98],"collapse.":[99],"To":[100],"mitigate":[101],"problem,":[103],"introduce":[105],"diversity":[107,179],"regularization":[108,180],"term":[109],"embeddings":[111],"SDPN.":[113],"Comprehensive":[114],"experiments":[115],"on":[116,135],"VoxCeleb":[118],"datasets":[119],"demonstrate":[120],"superiority":[122],"among":[125],"approaches.":[129],"sets":[131],"new":[133],"state-of-the-art":[134],"VoxCeleb1":[137],"evaluation":[140],"benchmark,":[141],"achieving":[142],"Equal":[143],"Error":[144],"Rate":[145],"1.80%,":[146],"1.99%,":[147],"3.62%":[149],"for":[150],"trial":[151],"VoxCeleb1-O,":[152],"VoxCeleb1-E":[153],"VoxCeleb1H":[155],"respectively":[156],"<sup":[157],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[158],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>,":[159],"using":[161],"any":[162],"training.":[166],"Ablation":[167],"studies":[168],"show":[169],"that":[170],"both":[171],"proposed":[172],"learnable":[173],"self-distillation":[176],"contribute":[181],"performance.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
