{"id":"https://openalex.org/W3160584619","doi":"https://doi.org/10.1109/icassp39728.2021.9413543","title":"Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm","display_name":"Learning Disentangled Phone and Speaker Representations in a Semi-Supervised VQ-VAE Paradigm","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160584619","doi":"https://doi.org/10.1109/icassp39728.2021.9413543","mag":"3160584619"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5040626187","display_name":"Jennifer Williams","orcid":"https://orcid.org/0000-0003-1410-0427"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jennifer Williams","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103063144","display_name":"Yi Zhao","orcid":"https://orcid.org/0000-0002-3555-9408"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Zhao","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082349516","display_name":"Erica Cooper","orcid":"https://orcid.org/0000-0002-2978-2793"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Erica Cooper","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040626187"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":2.4474,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90714917,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7053","last_page":"7057"},"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":0.9936000108718872,"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":0.9909999966621399,"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/codebook","display_name":"Codebook","score":0.8650597333908081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6979314684867859},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6877492070198059},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5834441781044006},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5256316065788269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5085052251815796},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5071649551391602},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.503093421459198},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.4712572395801544},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4082726240158081}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8650597333908081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6979314684867859},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6877492070198059},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5834441781044006},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5256316065788269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5085052251815796},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5071649551391602},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.503093421459198},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.4712572395801544},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4082726240158081},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413543","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W38194800","https://openalex.org/W1635512741","https://openalex.org/W1731081199","https://openalex.org/W2150769028","https://openalex.org/W2526425061","https://openalex.org/W2527729766","https://openalex.org/W2752796333","https://openalex.org/W2889418727","https://openalex.org/W2890964092","https://openalex.org/W2963371159","https://openalex.org/W2963799213","https://openalex.org/W2972403660","https://openalex.org/W2972849140","https://openalex.org/W2972921407","https://openalex.org/W2998572311","https://openalex.org/W3008391559","https://openalex.org/W3015826515","https://openalex.org/W3024752295","https://openalex.org/W3024962219","https://openalex.org/W3030987249","https://openalex.org/W3037217258","https://openalex.org/W3094917204","https://openalex.org/W6601576264","https://openalex.org/W6637618735","https://openalex.org/W6728030952","https://openalex.org/W6772349387","https://openalex.org/W6778356106"],"related_works":["https://openalex.org/W2148772884","https://openalex.org/W2017514583","https://openalex.org/W2100120615","https://openalex.org/W2147406819","https://openalex.org/W2352648934","https://openalex.org/W1929869830","https://openalex.org/W2387054321","https://openalex.org/W2017401491","https://openalex.org/W2062765737","https://openalex.org/W2012827167"],"abstract_inverted_index":{"We":[0,61],"present":[1],"a":[2,42,77,110],"new":[3,14],"approach":[4],"to":[5,16,30],"disentangle":[6],"speaker":[7,43,46,52,74,78,90,102,112],"voice":[8],"and":[9,45,71,94,115],"phone":[10],"content":[11],"by":[12],"introducing":[13],"components":[15],"the":[17,57],"VQ-VAE":[18,25,136],"architecture":[19],"for":[20],"speech":[21,85],"synthesis.":[22],"The":[23],"original":[24],"does":[26],"not":[27],"generalize":[28],"well":[29],"unseen":[31],"speakers":[32],"or":[33],"content.":[34],"To":[35],"alleviate":[36],"this":[37],"problem,":[38],"we":[39],"have":[40],"incorporated":[41],"encoder":[44],"VQ":[47,79,103,130],"codebook":[48,104,131],"that":[49,98],"learns":[50],"global":[51,69,141],"characteristics":[53],"entirely":[54],"separate":[55],"from":[56,128],"existing":[58],"sub-phone":[59,129],"codebooks.":[60],"also":[62],"compare":[63],"two":[64],"training":[65],"methods:":[66],"self-supervised":[67,139],"with":[68,73,140],"conditions":[70],"semi-supervised":[72,135],"labels.":[75],"Adding":[76],"component":[80],"improves":[81],"objective":[82],"measures":[83],"of":[84],"synthesis":[86],"quality":[87],"(estimated":[88],"MOS,":[89],"similarity,":[91],"ASR-based":[92],"intelligibility)":[93],"provides":[95],"learned":[96],"representations":[97],"are":[99],"meaningful.":[100],"Our":[101],"indices":[105,132],"can":[106,125],"be":[107,126],"used":[108],"in":[109,133],"simple":[111],"diarization":[113],"task":[114],"perform":[116],"slightly":[117],"better":[118,137],"than":[119,138],"an":[120],"x-vector":[121],"baseline.":[122],"Additionally,":[123],"phones":[124],"recognized":[127],"our":[134],"conditions.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}