{"id":"https://openalex.org/W4392902934","doi":"https://doi.org/10.1109/icassp48485.2024.10448284","title":"Contrastive Speaker Embedding With Sequential Disentanglement","display_name":"Contrastive Speaker Embedding With Sequential Disentanglement","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902934","doi":"https://doi.org/10.1109/icassp48485.2024.10448284"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/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":false,"raw_author_name":"Youzhi Tu","raw_affiliation_strings":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong,SAR","Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong,SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR","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":["The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong,SAR","Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Dept. of Electrical and Electronic Engineering,Hong Kong,SAR","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Dept. of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, SAR","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":["Inst. of Electrical and Computer Engineering National Yang Ming Chiao Tung University,Taiwan","Inst. of Electrical and Computer Engineering National Yang Ming Chiao Tung University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inst. of Electrical and Computer Engineering National Yang Ming Chiao Tung University,Taiwan","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Inst. of Electrical and Computer Engineering National Yang Ming Chiao Tung University, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10891","last_page":"10895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.9843999743461609,"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/discriminative-model","display_name":"Discriminative model","score":0.8088449239730835},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7623411417007446},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6702888011932373},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6688157916069031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6609379053115845},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5762497186660767},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5753433704376221},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5363534688949585},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4985654354095459},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46143317222595215},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4325740933418274},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3825964331626892},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23535355925559998},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1954950988292694}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8088449239730835},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7623411417007446},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6702888011932373},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6688157916069031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6609379053115845},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5762497186660767},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5753433704376221},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5363534688949585},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4985654354095459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46143317222595215},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4325740933418274},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3825964331626892},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23535355925559998},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1954950988292694},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2163922914","https://openalex.org/W2219249508","https://openalex.org/W2972403660","https://openalex.org/W2981087920","https://openalex.org/W3008391559","https://openalex.org/W3024962219","https://openalex.org/W3035524453","https://openalex.org/W3116256056","https://openalex.org/W3159481202","https://openalex.org/W3160397447","https://openalex.org/W3161606033","https://openalex.org/W3163187953","https://openalex.org/W3198310187","https://openalex.org/W3205635414","https://openalex.org/W3210384560","https://openalex.org/W4286981691","https://openalex.org/W4296068770","https://openalex.org/W4296069299","https://openalex.org/W4297841416","https://openalex.org/W4319781551","https://openalex.org/W4372346385","https://openalex.org/W6640963894","https://openalex.org/W6688816777","https://openalex.org/W6760212410","https://openalex.org/W6764882207","https://openalex.org/W6774314701","https://openalex.org/W6777437564","https://openalex.org/W6784400926","https://openalex.org/W6803240769","https://openalex.org/W6838117315","https://openalex.org/W6864750640"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W2053159670","https://openalex.org/W3148366653","https://openalex.org/W1521299571","https://openalex.org/W1996621592","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684"],"abstract_inverted_index":{"Contrastive":[0],"speaker":[1,19,33,73,86,108],"embedding":[2,80],"assumes":[3],"that":[4,83,118,127],"the":[5,8,64,85,103,106,119],"contrast":[6],"between":[7],"positive":[9],"and":[10],"negative":[11],"pairs":[12],"of":[13],"speech":[14,28],"segments":[15],"is":[16,25,131],"attributed":[17],"to":[18,51,71,133],"identity":[20,34],"only.":[21],"However,":[22],"this":[23,40],"assumption":[24],"incorrect":[26],"because":[27],"signals":[29],"contain":[30],"not":[31],"only":[32,84],"but":[35],"also":[36],"linguistic":[37,53],"content.":[38],"In":[39],"paper,":[41],"we":[42],"propose":[43],"a":[44,57,92],"contrastive":[45,93,104],"learning":[46,134],"framework":[47],"with":[48],"sequential":[49,59,129],"disentanglement":[50,130],"remove":[52],"content":[54,76,97],"by":[55],"incorporating":[56],"disentangled":[58],"variational":[60],"autoencoder":[61],"(DSVAE)":[62],"into":[63],"conventional":[65],"SimCLR":[66],"framework.":[67],"The":[68],"DSVAE":[69],"aims":[70],"disentangle":[72],"factors":[74,77,87,98],"from":[75,102],"in":[78],"an":[79],"space":[81],"so":[82],"are":[88],"used":[89],"for":[90],"constructing":[91],"loss":[94],"objective.":[95],"Because":[96],"have":[99],"been":[100],"removed":[101],"learning,":[105],"resulting":[107],"embeddings":[109],"will":[110],"be":[111],"content-invariant.":[112],"Experimental":[113],"results":[114],"on":[115],"VoxCeleb1-test":[116],"show":[117],"proposed":[120],"method":[121],"consistently":[122],"outperforms":[123],"SimCLR.":[124],"This":[125],"suggests":[126],"applying":[128],"beneficial":[132],"speaker-discriminative":[135],"embeddings.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
