{"id":"https://openalex.org/W7155053967","doi":"https://doi.org/10.1109/access.2026.3683761","title":"Deep Hidden Semi-Markov Model-Based Speech Synthesis","display_name":"Deep Hidden Semi-Markov Model-Based Speech Synthesis","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7155053967","doi":"https://doi.org/10.1109/access.2026.3683761"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3683761","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3683761","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3683761","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0000-3978-5130","affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039729197","display_name":"Takato Fujimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takato Fujimoto","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0008-5390-3701","affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101948311","display_name":"Takenori Yoshimura","orcid":"https://orcid.org/0000-0003-3964-5677"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takenori Yoshimura","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Takaki","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067594810","display_name":"Kei Hashimoto","orcid":"https://orcid.org/0000-0003-2081-0396"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Hashimoto","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-2081-0396","affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134166313","display_name":"Keiichiro Oura","orcid":"https://orcid.org/0009-0004-7611-9435"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Oura","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0004-7611-9435","affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":["Nagoya Institute of Technology, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6143-0133","affiliations":[{"raw_affiliation_string":"Nagoya Institute of Technology, Nagoya, Japan","institution_ids":["https://openalex.org/I197274945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197274945"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45725041,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"58495","last_page":"58514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7973999977111816,"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":0.7973999977111816,"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":0.07670000195503235,"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/T11448","display_name":"Face recognition and analysis","score":0.027300000190734863,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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-synthesis","display_name":"Speech synthesis","score":0.4595000147819519},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.36640000343322754},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.2985000014305115},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2732999920845032},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2678000032901764}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7476000189781189},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6116999983787537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47530001401901245},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2849000096321106},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3683761","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3683761","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:19944beb412e4246a039cc27cc4c9115","is_oa":true,"landing_page_url":"https://doaj.org/article/19944beb412e4246a039cc27cc4c9115","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 58495-58514 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3683761","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3683761","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2071120045","display_name":null,"funder_award_id":"JP23K24870","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G5543887244","display_name":null,"funder_award_id":"JP24H00170","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G6175235410","display_name":null,"funder_award_id":"JP24K02959","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G8326939981","display_name":null,"funder_award_id":"JP24K21322","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G947067277","display_name":null,"funder_award_id":"JP24H00741","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"},{"id":"https://openalex.org/F4320335839","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W102093577","https://openalex.org/W1516111018","https://openalex.org/W1600722501","https://openalex.org/W1976551160","https://openalex.org/W1979449467","https://openalex.org/W1990505856","https://openalex.org/W1991133427","https://openalex.org/W2035329354","https://openalex.org/W2064218608","https://openalex.org/W2064675550","https://openalex.org/W2076618452","https://openalex.org/W2106792148","https://openalex.org/W2111284386","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2129142580","https://openalex.org/W2154920538","https://openalex.org/W2524467597","https://openalex.org/W2747874407","https://openalex.org/W2750248772","https://openalex.org/W2767052532","https://openalex.org/W2807812398","https://openalex.org/W2886769154","https://openalex.org/W2904459034","https://openalex.org/W2915977493","https://openalex.org/W2962691331","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2972702018","https://openalex.org/W2997540646","https://openalex.org/W3004033428","https://openalex.org/W3015282541","https://openalex.org/W3015499482","https://openalex.org/W3015922793","https://openalex.org/W3016136182","https://openalex.org/W3016223359","https://openalex.org/W3095491807","https://openalex.org/W3095883095","https://openalex.org/W3096442195","https://openalex.org/W3097538987","https://openalex.org/W3097777922","https://openalex.org/W3161296985","https://openalex.org/W3163338468","https://openalex.org/W3193383128","https://openalex.org/W3195077602","https://openalex.org/W3197294703","https://openalex.org/W3198332267","https://openalex.org/W4224940982","https://openalex.org/W4225956675","https://openalex.org/W4283662594","https://openalex.org/W4375869198","https://openalex.org/W4386076493","https://openalex.org/W4392931276"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,9,91,103,109,161,171,185,194,206],"speech":[4,208,218],"synthesis":[5],"technique":[6],"based":[7],"on":[8,135,205],"neural":[10,221],"sequence-to-sequence":[11],"(Seq2Seq)":[12],"model":[13,89,96,183,187],"that":[14,59,97,211],"incorporates":[15],"the":[16,39,77,125,128,148,157,176,181,212],"structure":[17,101],"of":[18,41,67,76,127,144,150],"hidden":[19],"semi-Markov":[20],"models":[21,25,58],"(HSMMs).":[22],"Although":[23],"Seq2Seq":[24,186],"with":[26,165,188,231],"attention":[27,68,191,198],"mechanisms":[28,199],"have":[29,56],"achieved":[30,82],"high-quality":[31],"synthesis,":[32],"they":[33],"suffer":[34],"from":[35,124],"alignment":[36,62,112,202],"instability":[37],"and":[38,63,117,169,200],"absence":[40],"explicit":[42,61,201],"duration":[43,47,64,80,115],"modeling,":[44],"making":[45],"direct":[46],"control":[48],"difficult.":[49],"To":[50],"address":[51],"these":[52],"challenges,":[53],"recent":[54],"approaches":[55],"explored":[57],"incorporate":[60],"representations":[65],"instead":[66],"mechanisms.":[69],"However,":[70],"such":[71],"methods":[72],"still":[73],"fall":[74],"short":[75],"fully":[78],"consistent":[79],"handling":[81],"by":[83],"traditional":[84],"HSMM-based":[85],"synthesis.":[86],"The":[87],"proposed":[88,158,182,213],"is":[90,121,147],"theoretically":[92],"well-grounded":[93],"deep":[94],"generative":[95],"integrates":[98],"an":[99,151,166,189],"HSMM":[100,167],"into":[102],"variational":[104],"autoencoder":[105],"(VAE).":[106],"It":[107],"performs":[108],"probabilistic":[110],"full-space":[111],"search":[113],"considering":[114],"probabilities,":[116],"its":[118],"training":[119,233],"algorithm":[120],"derived":[122],"purely":[123],"maximization":[126],"evidence":[129],"lower":[130],"bound":[131],"(ELBO),":[132],"without":[133],"relying":[134],"heuristic":[136],"assumptions":[137],"or":[138],"auxiliary":[139],"criteria.":[140],"A":[141],"key":[142],"contribution":[143],"this":[145],"work":[146],"identification":[149],"essential":[152],"two-stage":[153],"approximation":[154,174],"necessary":[155],"for":[156,175],"model:":[159],"1)":[160],"conjugate":[162],"posterior":[163],"distribution":[164],"structure,":[168],"2)":[170],"subsequent":[172],"mean-field":[173],"VAE":[177],"decoder.":[178],"Furthermore,":[179],"interpreting":[180],"as":[184],"HSMM-structured":[190],"mechanism":[192],"establishes":[193],"theoretical":[195],"connection":[196],"between":[197],"modeling.":[203],"Experiments":[204],"Japanese":[207],"database":[209],"demonstrate":[210],"method":[214],"achieves":[215],"higher-quality":[216],"synthesized":[217],"than":[219],"conventional":[220],"network-based":[222],"acoustic":[223],"models,":[224],"while":[225],"maintaining":[226],"high":[227],"modeling":[228],"efficiency":[229],"even":[230],"limited":[232],"data.":[234]},"counts_by_year":[],"updated_date":"2026-04-23T06:14:38.165362","created_date":"2026-04-22T00:00:00"}