{"id":"https://openalex.org/W4366147765","doi":"https://doi.org/10.1109/taslp.2023.3267833","title":"Decomposition and Reorganization of Phonetic Information for Speaker Embedding Learning","display_name":"Decomposition and Reorganization of Phonetic Information for Speaker Embedding Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4366147765","doi":"https://doi.org/10.1109/taslp.2023.3267833"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3267833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3267833","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054849851","display_name":"Qian-Bei Hong","orcid":"https://orcid.org/0000-0003-2123-1601"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]},{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Qian-Bei Hong","raw_affiliation_strings":["Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-2123-1601","affiliations":[{"raw_affiliation_string":"Graduate Program of Multimedia Systems and Intelligent Computing, National Cheng Kung University and Academia Sinica, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558","https://openalex.org/I84653119"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan"],"raw_orcid":"https://orcid.org/0000-0002-3947-2123","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taipei, Taiwan"],"raw_orcid":"https://orcid.org/0000-0003-3599-5071","affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taipei, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.1211,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.89511273,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"1745","last_page":"1757"},"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":0.9968000054359436,"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":0.9965000152587891,"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":0.7833753824234009},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7246960401535034},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5331363677978516},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5298773050308228},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5076853036880493},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5010042190551758},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.45455941557884216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45009806752204895},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.415962815284729},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4069858193397522}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7833753824234009},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246960401535034},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5331363677978516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5298773050308228},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5076853036880493},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5010042190551758},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.45455941557884216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45009806752204895},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.415962815284729},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4069858193397522},{"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/taslp.2023.3267833","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3267833","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"},{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4169684317","display_name":null,"funder_award_id":"MOST 108-2221-E-006-103-MY3","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W67277430","https://openalex.org/W95152782","https://openalex.org/W125553504","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2046056978","https://openalex.org/W2107638917","https://openalex.org/W2112582577","https://openalex.org/W2114925438","https://openalex.org/W2117671523","https://openalex.org/W2121812409","https://openalex.org/W2144760012","https://openalex.org/W2148091317","https://openalex.org/W2167598627","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2219249508","https://openalex.org/W2290689761","https://openalex.org/W2406778302","https://openalex.org/W2407857848","https://openalex.org/W2516764878","https://openalex.org/W2566925314","https://openalex.org/W2587150483","https://openalex.org/W2696967604","https://openalex.org/W2726515241","https://openalex.org/W2748488820","https://openalex.org/W2752782242","https://openalex.org/W2770454110","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2809661872","https://openalex.org/W2889519245","https://openalex.org/W2890964092","https://openalex.org/W2922299546","https://openalex.org/W2928165649","https://openalex.org/W2938358845","https://openalex.org/W2964052309","https://openalex.org/W2964054038","https://openalex.org/W2964058423","https://openalex.org/W2964247977","https://openalex.org/W2972743990","https://openalex.org/W2973049979","https://openalex.org/W2981087920","https://openalex.org/W2993724474","https://openalex.org/W2999547272","https://openalex.org/W3012447314","https://openalex.org/W3015368919","https://openalex.org/W3015503328","https://openalex.org/W3015707499","https://openalex.org/W3024869864","https://openalex.org/W3085051942","https://openalex.org/W3093614836","https://openalex.org/W3097244734","https://openalex.org/W3103152812","https://openalex.org/W3139024197","https://openalex.org/W3142516134","https://openalex.org/W3160743249","https://openalex.org/W3160787318","https://openalex.org/W3163505255","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209376089","https://openalex.org/W3209984917","https://openalex.org/W4221154746","https://openalex.org/W4225096077","https://openalex.org/W4286981691","https://openalex.org/W4288091954","https://openalex.org/W4313387459","https://openalex.org/W6603838645","https://openalex.org/W6631362777","https://openalex.org/W6688816777","https://openalex.org/W6713713408","https://openalex.org/W6740167877","https://openalex.org/W6742911084","https://openalex.org/W6769178842","https://openalex.org/W6784400926"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W3081952170","https://openalex.org/W4385719553","https://openalex.org/W2349696592","https://openalex.org/W2083755708"],"abstract_inverted_index":{"Speech":[0],"content":[1],"is":[2,45,70],"closely":[3],"related":[4],"to":[5,32,47,72,124,164,197,214,217],"the":[6,34,49,59,63,88,95,101,114,119,125,130,136,140,151,155,159,165,169,173,177,184,198,202,206,210,218],"stability":[7],"of":[8,36,51,62,179,192],"speaker":[9,12,40,89],"embeddings":[10,61],"in":[11,77,139,194],"verification":[13],"tasks.":[14],"In":[15,85,150,168,201],"this":[16],"paper,":[17],"we":[18],"propose":[19],"a":[20,189],"novel":[21],"architecture":[22],"based":[23],"on":[24,39,81,94,100,110,142,153,171,204],"self-constraint":[25],"learning":[26],"(SCL)":[27],"and":[28,98,105,145,224],"reconstruction":[29],"task":[30],"(RT)":[31],"remove":[33,74],"influence":[35],"phonetic":[37,75,181],"information":[38,76,182],"embedding":[41,90],"generation.":[42],"First,":[43],"SCL":[44],"used":[46,71],"reduce":[48],"divergence":[50],"frame-level":[52,78],"features,":[53],"which":[54],"can":[55],"avoid":[56],"ambiguity":[57],"between":[58],"resulting":[60],"two":[64],"utterances":[65],"being":[66],"compared.":[67],"Second,":[68],"RT":[69],"further":[73],"layers,":[79],"focusing":[80],"speaker-discriminative":[82],"feature":[83],"transformation.":[84],"our":[86],"experiments,":[87],"models":[91],"were":[92],"trained":[93],"VoxCeleb2":[96],"dataset":[97],"evaluated":[99],"VoxCeleb1,":[102],"Librispeech,":[103,172],"SITW":[104],"VoxMovies":[106,146],"datasets.":[107],"Experimental":[108],"results":[109],"VoxCeleb1":[111],"show":[112],"that":[113],"proposed":[115,131,156,174,207],"DROP-TDNN":[116,132],"system":[117,133,138,157,175,208,220],"reduced":[118,158,209],"EER":[120,160,195,211],"by":[121,161,212],"7.5%,":[122],"compared":[123,163,196,216],"state-of-the-art":[126],"ECAPA-TDNN":[127,137,166,199,219],"system.":[128,167,200],"Furthermore,":[129],"also":[134],"outperformed":[135],"experiments":[141,152,170,203],"SITW,":[143,154],"Librispeech":[144],"under":[147,183,221],"cross-dataset":[148],"conditions.":[149,226],"3.4%":[162],"demonstrated":[176],"advantage":[178],"removing":[180],"clean":[185],"speech":[186],"condition,":[187],"with":[188],"significant":[190],"reduction":[191],"25.5%":[193],"VoxMovies,":[205],"up":[213],"7.9%":[215],"different":[222],"pronunciation":[223],"background":[225]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}