{"id":"https://openalex.org/W4396982391","doi":"https://doi.org/10.1109/taslp.2024.3402077","title":"Contrastive Self-Supervised Speaker Embedding With Sequential Disentanglement","display_name":"Contrastive Self-Supervised Speaker Embedding With Sequential Disentanglement","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396982391","doi":"https://doi.org/10.1109/taslp.2024.3402077"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3402077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402077","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/106862/1/Tu_Contrastive_Self-Supervised_Speaker.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019467579","display_name":"Youzhi Tu","orcid":"https://orcid.org/0000-0002-9580-2414"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Youzhi Tu","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong SAR, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019467579"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":4.1344,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9452012,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"2704","last_page":"2715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9944000244140625,"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":0.9168999791145325,"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/speech-recognition","display_name":"Speech recognition","score":0.6040504574775696},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5867182612419128},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5757757425308228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36661607027053833},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35871124267578125}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6040504574775696},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5867182612419128},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5757757425308228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36661607027053833},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35871124267578125}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3402077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3402077","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/106862","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/106862","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/106862/1/Tu_Contrastive_Self-Supervised_Speaker.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/106862","is_oa":true,"landing_page_url":"http://hdl.handle.net/10397/106862","pdf_url":"http://ira.lib.polyu.edu.hk/bitstream/10397/106862/1/Tu_Contrastive_Self-Supervised_Speaker.pdf","source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396982391.pdf","grobid_xml":"https://content.openalex.org/works/W4396982391.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2104457544","https://openalex.org/W2127589108","https://openalex.org/W2163922914","https://openalex.org/W2219249508","https://openalex.org/W2784163702","https://openalex.org/W2842511635","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2902476877","https://openalex.org/W2916104401","https://openalex.org/W2938358845","https://openalex.org/W2964247977","https://openalex.org/W2969985801","https://openalex.org/W2972403660","https://openalex.org/W2972743990","https://openalex.org/W2978904488","https://openalex.org/W2981087920","https://openalex.org/W3008391559","https://openalex.org/W3015555484","https://openalex.org/W3024869864","https://openalex.org/W3024962219","https://openalex.org/W3035524453","https://openalex.org/W3103152812","https://openalex.org/W3139878283","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3162224131","https://openalex.org/W3163187953","https://openalex.org/W3171007011","https://openalex.org/W3198310187","https://openalex.org/W3205635414","https://openalex.org/W3209059054","https://openalex.org/W4206908380","https://openalex.org/W4221167533","https://openalex.org/W4224924624","https://openalex.org/W4226230385","https://openalex.org/W4286981691","https://openalex.org/W4296068770","https://openalex.org/W4296069299","https://openalex.org/W4296069358","https://openalex.org/W4297808394","https://openalex.org/W4297841416","https://openalex.org/W4319781551","https://openalex.org/W4372346385","https://openalex.org/W4392902934","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6688816777","https://openalex.org/W6754215057","https://openalex.org/W6756663807","https://openalex.org/W6756824971","https://openalex.org/W6760212410","https://openalex.org/W6764882207","https://openalex.org/W6766489549","https://openalex.org/W6784400926","https://openalex.org/W6803240769","https://openalex.org/W6809668307","https://openalex.org/W6838117315","https://openalex.org/W6839738141","https://openalex.org/W6852280171","https://openalex.org/W6864750640"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Contrastive":[0,15],"self-supervised":[1],"learning":[2,61,82,166],"has":[3],"been":[4,115],"widely":[5],"used":[6],"in":[7,94],"speaker":[8,16,34,48,89,101,122,148],"embedding":[9,17,96,149],"to":[10,33,66,87,107,133,165],"address":[11],"the":[12,20,23,79,100,104,108,120,140,145,151],"labeling":[13],"challenge.":[14],"assumes":[18],"that":[19,99,139,159],"contrast":[21],"between":[22],"positive":[24],"and":[25,153],"negative":[26],"pairs":[27],"of":[28],"speech":[29,43],"segments":[30],"is":[31,40,137,163],"attributed":[32],"identity":[35,49],"only.":[36],"However,":[37],"this":[38,55],"assumption":[39],"incorrect":[41],"because":[42],"signals":[44],"contain":[45],"not":[46],"only":[47],"but":[50],"also":[51,131],"linguistic":[52,68],"content.":[53],"In":[54],"paper,":[56],"we":[57],"propose":[58],"a":[59,72],"contrastive":[60,81,109,118,147],"framework":[62],"with":[63],"sequential":[64,74,161],"disentanglement":[65,162],"remove":[67],"content":[69,92,112],"by":[70],"incorporating":[71],"disentangled":[73],"variational":[75],"autoencoder":[76],"(DSVAE)":[77],"into":[78],"conventional":[80,146],"framework.":[83],"The":[84,127],"DSVAE":[85],"aims":[86],"disentangle":[88],"factors":[90,93,102,113],"from":[91,117],"an":[95],"space":[97],"so":[98],"become":[103],"main":[105],"contributor":[106],"loss.":[110],"Because":[111],"have":[114],"removed":[116],"learning,":[119],"resulting":[121],"embeddings":[123,129],"will":[124],"be":[125],"content-invariant.":[126],"learned":[128],"are":[130],"robust":[132],"language":[134],"mismatch.":[135],"It":[136],"shown":[138],"proposed":[141],"method":[142],"consistently":[143],"outperforms":[144],"on":[150],"VoxCeleb1":[152],"CN-Celeb":[154],"datasets.":[155],"This":[156],"finding":[157],"suggests":[158],"applying":[160],"beneficial":[164],"speaker-discriminative":[167],"embeddings.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}