{"id":"https://openalex.org/W3163338468","doi":"https://doi.org/10.1109/icassp39728.2021.9414499","title":"End-to-End Text-to-Speech Using Latent Duration Based on VQ-VAE","display_name":"End-to-End Text-to-Speech Using Latent Duration Based on VQ-VAE","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163338468","doi":"https://doi.org/10.1109/icassp39728.2021.9414499","mag":"3163338468"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414499","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/A5068072475","display_name":"Yusuke Yasuda","orcid":"https://orcid.org/0000-0002-2130-747X"},"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"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yusuke Yasuda","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan","The Graduate University for Advanced Sciences, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Sciences, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"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":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072342844","display_name":"Junichi Yamagishd","orcid":null},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"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 Yamagishd","raw_affiliation_strings":["National Institute of Informatics,Japan","National Institute of Informatics, Japan","The Graduate University for Advanced Sciences, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"The Graduate University for Advanced Sciences, Japan","institution_ids":["https://openalex.org/I200475212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068072475"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":null,"apc_paid":null,"fwci":1.3597,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8426662,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5694","last_page":"5698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.8650637865066528},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6683056950569153},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5856439471244812},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5603666305541992},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5539683699607849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48192501068115234},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4687991738319397},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.445929616689682},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4441138505935669},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3455425500869751},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2078602910041809},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08044874668121338}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8650637865066528},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6683056950569153},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5856439471244812},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5603666305541992},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5539683699607849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48192501068115234},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4687991738319397},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.445929616689682},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4441138505935669},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3455425500869751},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2078602910041809},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08044874668121338},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414499","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414499","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":[{"display_name":"Peace, Justice and strong institutions","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W175280642","https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1959608418","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2519091744","https://openalex.org/W2752796333","https://openalex.org/W2884607399","https://openalex.org/W2903739847","https://openalex.org/W2935711438","https://openalex.org/W2946200149","https://openalex.org/W2949382160","https://openalex.org/W2963609956","https://openalex.org/W2963799213","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W2970730223","https://openalex.org/W2971753973","https://openalex.org/W2972374322","https://openalex.org/W2972702018","https://openalex.org/W2972746749","https://openalex.org/W2972849140","https://openalex.org/W2973158936","https://openalex.org/W2982602185","https://openalex.org/W3015440759","https://openalex.org/W3015922793","https://openalex.org/W3016136182","https://openalex.org/W3016160783","https://openalex.org/W3024605872","https://openalex.org/W3025793647","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3094917204","https://openalex.org/W3096442195","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W3130016944","https://openalex.org/W3163338468","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6640963894","https://openalex.org/W6679434410","https://openalex.org/W6753540710","https://openalex.org/W6763832098","https://openalex.org/W6769328215","https://openalex.org/W6773153034","https://openalex.org/W6777028661","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6784520556"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W3013693939","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W4402568167","https://openalex.org/W2988134182","https://openalex.org/W2770818364"],"abstract_inverted_index":{"Explicit":[0],"duration":[1,24,28,56,117,133],"modeling":[2,25],"is":[3],"a":[4,18,30,58,63,73,102],"key":[5],"to":[6,34,53,66],"achieving":[7],"robust":[8],"and":[9,36,61,86,105,131],"efficient":[10],"alignment":[11],"in":[12,57,92],"text-to-speech":[13],"synthesis":[14],"(TTS).":[15],"We":[16,45,96],"propose":[17],"new":[19],"TTS":[20,35,110],"framework":[21],"using":[22],"explicit":[23,116,132],"that":[26,122],"incorporates":[27],"as":[29,82,89],"discrete":[31,55],"latent":[32],"variable":[33],"enables":[37],"joint":[38],"optimization":[39],"of":[40],"whole":[41],"modules":[42],"from":[43],"scratch.":[44],"formulate":[46],"our":[47,68,71,98,123],"method":[48,100],"based":[49,112],"on":[50,113],"conditional":[51],"VQ-VAE":[52],"handle":[54],"variational":[59,94],"autoencoder":[60],"provide":[62],"theoretical":[64],"explanation":[65],"justify":[67],"method.":[69],"In":[70],"framework,":[72],"connectionist":[74],"temporal":[75],"classification":[76],"(CTC)":[77],"-based":[78],"force":[79],"aligner":[80],"acts":[81],"the":[83,90,93],"approximate":[84],"posterior,":[85],"text-to-duration":[87],"works":[88],"prior":[91],"autoencoder.":[95],"evaluated":[97],"proposed":[99],"with":[101,108],"listening":[103],"test":[104],"compared":[106],"it":[107],"other":[109],"methods":[111,128,135],"soft-attention":[114],"or":[115],"modeling.":[118],"The":[119],"results":[120],"showed":[121],"systems":[124],"rated":[125],"between":[126],"soft-attention-based":[127],"(Transformer-TTS,":[129],"Tacotron2)":[130],"modeling-based":[134],"(Fastspeech).":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}