{"id":"https://openalex.org/W3161436426","doi":"https://doi.org/10.1109/icassp39728.2021.9414226","title":"Disentangled Speaker and Language Representations Using Mutual Information Minimization and Domain Adaptation for Cross-Lingual TTS","display_name":"Disentangled Speaker and Language Representations Using Mutual Information Minimization and Domain Adaptation for Cross-Lingual TTS","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161436426","doi":"https://doi.org/10.1109/icassp39728.2021.9414226","mag":"3161436426"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414226","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/A5072398606","display_name":"Detai Xin","orcid":"https://orcid.org/0009-0007-1908-1137"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Detai Xin","raw_affiliation_strings":["LINE Corporation,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan","LINE Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113730169","display_name":"Tatsuya Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096607","display_name":"Line Corporation (Japan)","ror":"https://ror.org/00qg8pm87","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210096607","https://openalex.org/I60922564"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Komatsu","raw_affiliation_strings":["LINE Corporation,Japan","LINE Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"LINE Corporation,Japan","institution_ids":["https://openalex.org/I4210096607"]},{"raw_affiliation_string":"LINE Corporation, Japan","institution_ids":["https://openalex.org/I4210096607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013050263","display_name":"Shinnosuke Takamichi","orcid":"https://orcid.org/0000-0003-0520-7847"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinnosuke Takamichi","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003814223","display_name":"Hiroshi Saruwatari","orcid":"https://orcid.org/0000-0003-0876-5617"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi Saruwatari","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo,Japan","Graduate School of Information Science and Technology, The University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072398606"],"corresponding_institution_ids":["https://openalex.org/I4210096607","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":2.8553,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.92136206,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6608","last_page":"6612"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9962999820709229,"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":0.9955000281333923,"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":0.7734404802322388},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6571393013000488},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6379220485687256},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5789467096328735},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49345818161964417},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4409998059272766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4383179247379303},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4382854998111725},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.4295244812965393},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.4158358573913574},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15218770503997803}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734404802322388},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6571393013000488},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6379220485687256},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5789467096328735},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49345818161964417},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4409998059272766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4383179247379303},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4382854998111725},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.4295244812965393},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.4158358573913574},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15218770503997803},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/icassp39728.2021.9414226","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414226","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":0.6000000238418579,"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":45,"referenced_works":["https://openalex.org/W89093025","https://openalex.org/W1522301498","https://openalex.org/W1731081199","https://openalex.org/W2046056978","https://openalex.org/W2120847449","https://openalex.org/W2494654097","https://openalex.org/W2527729766","https://openalex.org/W2612434969","https://openalex.org/W2788357188","https://openalex.org/W2794235490","https://openalex.org/W2808706139","https://openalex.org/W2907262790","https://openalex.org/W2936780106","https://openalex.org/W2940579548","https://openalex.org/W2962739369","https://openalex.org/W2963192573","https://openalex.org/W2963432880","https://openalex.org/W2963964591","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2969049672","https://openalex.org/W2972473628","https://openalex.org/W2973084242","https://openalex.org/W2993842823","https://openalex.org/W3016090709","https://openalex.org/W3016139610","https://openalex.org/W3035060230","https://openalex.org/W3036928441","https://openalex.org/W3096514088","https://openalex.org/W3106587939","https://openalex.org/W3108400054","https://openalex.org/W4298174729","https://openalex.org/W6603576222","https://openalex.org/W6631190155","https://openalex.org/W6637618735","https://openalex.org/W6662018943","https://openalex.org/W6737575990","https://openalex.org/W6748573829","https://openalex.org/W6748588790","https://openalex.org/W6752888775","https://openalex.org/W6761687776","https://openalex.org/W6767245602","https://openalex.org/W6771146561","https://openalex.org/W6779459370","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W172797710","https://openalex.org/W3165080709","https://openalex.org/W2945105049","https://openalex.org/W2626699140","https://openalex.org/W2909357361","https://openalex.org/W4387098302","https://openalex.org/W4288365855","https://openalex.org/W2948317131","https://openalex.org/W2111961547"],"abstract_inverted_index":{"We":[0,119],"propose":[1],"a":[2,35,39,131,165],"method":[3,25,45,69,123,142,163],"for":[4,18,94],"obtaining":[5],"disentangled":[6,65],"speaker":[7,27,36,56,89,106,148,171],"and":[8,15,28,38,58,90,114,126,147,153],"language":[9,29,40,60,91,112],"representations":[10,87,100],"via":[11],"mutual":[12,72],"information":[13,73,82,108],"minimization":[14,74],"domain":[16,47],"adaptation":[17,48],"cross-lingual":[19,95,154],"text-to-speech":[20],"(TTS)":[21],"synthesis.":[22,156],"The":[23],"proposed":[24,44,68,122,141,162],"extracts":[26],"embeddings":[30,52,78],"from":[31],"acoustic":[32],"features":[33],"by":[34],"encoder":[37],"encoder.":[41],"Then":[42],"the":[43,50,67,76,111,121,140,145,161,170],"applies":[46],"on":[49],"two":[51,77],"to":[53,79,104],"obtain":[54],"language-invariant":[55],"embedding":[57],"speaker-invariant":[59],"embedding.":[61,85],"To":[62],"get":[63],"more":[64],"representations,":[66],"further":[70],"uses":[71],"between":[75,173],"remove":[80],"entangled":[81,99],"within":[83],"each":[84],"Disentangled":[86],"of":[88,133,150,168],"are":[92],"critical":[93],"TTS":[96,155],"synthesis":[97],"since":[98],"make":[101],"it":[102],"difficult":[103],"maintain":[105],"identity":[107,172],"when":[109],"changing":[110],"representation":[113],"consequently":[115],"causes":[116],"performance":[117],"degradation.":[118],"evaluate":[120],"using":[124],"English":[125],"Japanese":[127],"multi-speaker":[128],"datasets":[129],"with":[130],"total":[132],"207":[134],"speakers.":[135],"Experimental":[136],"result":[137],"demonstrates":[138],"that":[139,160],"significantly":[143],"improves":[144],"naturalness":[146],"similarity":[149],"both":[151],"intra-lingual":[152],"Furthermore,":[157],"we":[158],"show":[159],"has":[164],"good":[166],"capability":[167],"maintaining":[169],"languages.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
