{"id":"https://openalex.org/W4226227837","doi":"https://doi.org/10.1109/slt54892.2023.10022739","title":"VTTS: Visual-Text To Speech","display_name":"VTTS: Visual-Text To Speech","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4226227837","doi":"https://doi.org/10.1109/slt54892.2023.10022739"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022739","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.14725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yoshifumi Nakano","orcid":null},"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":true,"raw_author_name":"Yoshifumi Nakano","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025983709","display_name":"Takaaki Saeki","orcid":"https://orcid.org/0000-0001-6003-768X"},"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":"Takaaki Saeki","raw_affiliation_strings":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"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":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051961507","display_name":"Katsuhito Sudoh","orcid":"https://orcid.org/0000-0002-2122-9846"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuhito Sudoh","raw_affiliation_strings":["Nara Institute of Science and Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology,Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"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":["The University of Tokyo,Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo,Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00167785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"936","last_page":"942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.20829999446868896,"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"}},"topics":[{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.20829999446868896,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.16200000047683716,"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"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.16050000488758087,"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/naturalness","display_name":"Naturalness","score":0.8994206190109253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7013370394706726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6699576377868652},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6026540994644165},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5644115209579468},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.44964396953582764},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4490998089313507},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37794214487075806},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11300992965698242},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07062897086143494}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8994206190109253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7013370394706726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6699576377868652},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6026540994644165},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5644115209579468},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.44964396953582764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4490998089313507},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37794214487075806},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11300992965698242},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07062897086143494},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt54892.2023.10022739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022739","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.14725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.14725","pdf_url":"https://arxiv.org/pdf/2203.14725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2203.14725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.14725","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.14725","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.14725","pdf_url":"https://arxiv.org/pdf/2203.14725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1919652261","https://openalex.org/W1999540762","https://openalex.org/W2111798208","https://openalex.org/W2519091744","https://openalex.org/W2531410232","https://openalex.org/W2896631555","https://openalex.org/W2962784628","https://openalex.org/W2963223057","https://openalex.org/W2963609956","https://openalex.org/W2964002616","https://openalex.org/W2964123686","https://openalex.org/W2964243274","https://openalex.org/W2964325863","https://openalex.org/W2985344220","https://openalex.org/W3016021263","https://openalex.org/W3088892837","https://openalex.org/W3095491807","https://openalex.org/W3096806995","https://openalex.org/W3115462295","https://openalex.org/W3154987757","https://openalex.org/W3197034238","https://openalex.org/W3198791321","https://openalex.org/W6637242042","https://openalex.org/W6723250868","https://openalex.org/W6745289305","https://openalex.org/W6750489868","https://openalex.org/W6763832098","https://openalex.org/W6778823374","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W8844810","https://openalex.org/W10994108","https://openalex.org/W9746140","https://openalex.org/W10951541","https://openalex.org/W3164750","https://openalex.org/W469815","https://openalex.org/W3296475","https://openalex.org/W18611454","https://openalex.org/W2066944","https://openalex.org/W7389584"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,9,69,79,106],"visual-text":[4],"to":[5,102,120],"speech":[6,13,36,98,121,136],"(vTTS)":[7],"method,":[8],"method":[10,64,93],"for":[11,35],"synthesizing":[12],"directly":[14],"from":[15,137],"visual":[16,26,29,66,118],"text":[17,19,30,119],"(i.e.,":[18],"as":[20,39,58],"an":[21,83],"image).":[22],"vTTS":[23,63,92],"can":[24,111,130],"use":[25],"features":[27,67,77],"in":[28,44,52,82,117],"that":[31,89],"should":[32],"be":[33],"important":[34],"synthesis":[37],"such":[38],"emphasis":[40,113],"and":[41,73,114,125,127,134,139],"radicals":[42],"(components":[43],"Chinese":[45],"characters),":[46],"but":[47],"they":[48],"are":[49],"not":[50],"available":[51],"conventional":[53,107,143],"TTS":[54],"using":[55],"discrete":[56],"symbols":[57],"the":[59,91],"input.":[60],"The":[61],"proposed":[62],"extracts":[65],"with":[68,78,99],"convolutional":[70],"neural":[71],"network":[72],"then":[74],"generates":[75],"acoustic":[76],"non-autoregressive":[80],"model":[81],"end-to-end":[84],"manner.":[85],"Experimental":[86],"results":[87],"show":[88],"1)":[90],"is":[94],"capable":[95],"of":[96],"generating":[97],"naturalness":[100],"comparable":[101],"or":[103],"better":[104],"than":[105,142],"TTS,":[108],"2)":[109],"it":[110,129],"transfer":[112],"emotion":[115],"attributes":[116],"without":[122],"additional":[123],"labels":[124],"architectures,":[126],"3)":[128],"synthesize":[131],"more":[132],"natural":[133],"intelligible":[135],"unseen":[138],"rare":[140],"characters":[141],"TTS.":[144]},"counts_by_year":[],"updated_date":"2026-03-03T08:47:05.690250","created_date":"2022-05-05T00:00:00"}