{"id":"https://openalex.org/W4375869045","doi":"https://doi.org/10.1109/icassp49357.2023.10094298","title":"Text-To-Speech Synthesis Based on Latent Variable Conversion Using Diffusion Probabilistic Model and Variational Autoencoder","display_name":"Text-To-Speech Synthesis Based on Latent Variable Conversion Using Diffusion Probabilistic Model and Variational Autoencoder","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869045","doi":"https://doi.org/10.1109/icassp49357.2023.10094298"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103119769","display_name":"Yusuke Yasuda","orcid":"https://orcid.org/0009-0002-3392-3963"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yusuke Yasuda","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","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/latent-variable","display_name":"Latent variable","score":0.8323178291320801},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7936854362487793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6923661828041077},{"id":"https://openalex.org/keywords/latent-variable-model","display_name":"Latent variable model","score":0.6393244862556458},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6262571811676025},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5609802007675171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5400041341781616},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.43202945590019226},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40725189447402954},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3810117244720459},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19869646430015564},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.16986069083213806},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07743066549301147}],"concepts":[{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.8323178291320801},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7936854362487793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923661828041077},{"id":"https://openalex.org/C65965080","wikidata":"https://www.wikidata.org/wiki/Q1806885","display_name":"Latent variable model","level":3,"score":0.6393244862556458},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6262571811676025},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5609802007675171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5400041341781616},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.43202945590019226},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40725189447402954},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3810117244720459},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19869646430015564},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16986069083213806},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07743066549301147},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094298","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094298","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"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":52,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W1972978214","https://openalex.org/W2519091744","https://openalex.org/W2752796333","https://openalex.org/W2892140764","https://openalex.org/W2959300817","https://openalex.org/W2963090522","https://openalex.org/W2963799213","https://openalex.org/W2964243274","https://openalex.org/W2973158936","https://openalex.org/W2996573371","https://openalex.org/W3026874504","https://openalex.org/W3033411150","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3123097577","https://openalex.org/W3168053944","https://openalex.org/W3169905056","https://openalex.org/W3172148458","https://openalex.org/W3197324626","https://openalex.org/W3198213150","https://openalex.org/W3198769980","https://openalex.org/W4224035735","https://openalex.org/W4285412695","https://openalex.org/W4287120591","https://openalex.org/W4289383906","https://openalex.org/W4296068981","https://openalex.org/W4297841714","https://openalex.org/W4304099317","https://openalex.org/W4320013936","https://openalex.org/W4320169845","https://openalex.org/W4385245566","https://openalex.org/W6610566761","https://openalex.org/W6639824700","https://openalex.org/W6640963894","https://openalex.org/W6739901393","https://openalex.org/W6754925833","https://openalex.org/W6755300632","https://openalex.org/W6765775151","https://openalex.org/W6768443183","https://openalex.org/W6777694618","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6782760101","https://openalex.org/W6783867762","https://openalex.org/W6788990321","https://openalex.org/W6795261426","https://openalex.org/W6796464841","https://openalex.org/W6809885388","https://openalex.org/W6840257003","https://openalex.org/W6849953009"],"related_works":["https://openalex.org/W2988134182","https://openalex.org/W2461917396","https://openalex.org/W2037497866","https://openalex.org/W4243467573","https://openalex.org/W1502435251","https://openalex.org/W62001224","https://openalex.org/W3032390039","https://openalex.org/W1584341211","https://openalex.org/W3122667150","https://openalex.org/W4393387622"],"abstract_inverted_index":{"Text-to-speech":[0],"synthesis":[1],"(TTS)":[2],"is":[3,111,138],"a":[4,32,41,56,62],"task":[5],"to":[6,125,140],"convert":[7],"texts":[8],"into":[9],"speech.":[10],"Two":[11],"of":[12,23,69],"the":[13,21,46,67,73,86,108],"factors":[14],"that":[15,65,82,135],"have":[16],"been":[17],"driving":[18],"TTS":[19,33,52],"are":[20],"advancements":[22],"probabilistic":[24,43],"models":[25],"and":[26,45,78,88,102,146],"latent":[27,37,70,90,118,129],"representation":[28],"learning.":[29],"We":[30],"propose":[31],"method":[34,93,137],"based":[35,59],"on":[36,60],"variable":[38,119],"conversion":[39,120],"using":[40],"diffusion":[42,63,95],"model":[44,58,64,75,81],"variational":[47],"autoencoder":[48],"(VAE).":[49],"In":[50],"our":[51,136],"method,":[53],"we":[54],"use":[55],"waveform":[57,74],"VAE,":[61],"predicts":[66],"distribution":[68,110],"variables":[71],"in":[72],"from":[76,115],"texts,":[77],"an":[79],"alignment":[80,147],"learns":[83],"alignments":[84],"between":[85],"text":[87],"speech":[89],"sequences.":[91],"Our":[92,132],"integrates":[94],"with":[96,105,143],"VAE":[97],"by":[98,113],"modeling":[99],"both":[100],"mean":[101],"variance":[103],"parameters":[104],"diffusion,":[106],"where":[107],"target":[109],"determined":[112],"approximation":[114],"VAE.":[116],"This":[117],"framework":[121],"potentially":[122],"enables":[123],"us":[124],"flexibly":[126],"incorporate":[127],"various":[128],"feature":[130],"extractors.":[131],"experiments":[133],"show":[134],"robust":[139],"linguistic":[141],"labels":[142],"ambiguous":[144],"orthography":[145],"errors.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}