{"id":"https://openalex.org/W4283662594","doi":"https://doi.org/10.21437/interspeech.2022-259","title":"End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue","display_name":"End-to-End Text-to-Speech Based on Latent Representation of Speaking Styles Using Spontaneous Dialogue","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283662594","doi":"https://doi.org/10.21437/interspeech.2022-259"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-259","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-259","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5102751752","display_name":"Kentaro Mitsui","orcid":"https://orcid.org/0000-0002-3551-9932"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kentaro Mitsui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100752905","display_name":"Tianyu Zhao","orcid":"https://orcid.org/0000-0001-7280-2190"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001979247","display_name":"Kei Sawada","orcid":"https://orcid.org/0009-0003-2396-681X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kei Sawada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086910479","display_name":"Yukiya Hono","orcid":"https://orcid.org/0000-0003-1245-8791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukiya Hono","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240652","display_name":"Yoshihiko Nankaku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yoshihiko Nankaku","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keiichi Tokuda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2328","last_page":"2332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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/T12031","display_name":"Speech and dialogue systems","score":0.9975000023841858,"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":0.992900013923645,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9922999739646912,"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/computer-science","display_name":"Computer science","score":0.6747249960899353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6606597900390625},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5857110619544983},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5285985469818115},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.46366575360298157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46085065603256226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6747249960899353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6606597900390625},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5857110619544983},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5285985469818115},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.46366575360298157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46085065603256226},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-259","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-259","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"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":0,"referenced_works":[],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3008587939","https://openalex.org/W3127005940","https://openalex.org/W4387301579","https://openalex.org/W2951281592","https://openalex.org/W2166381389","https://openalex.org/W3192589309"],"abstract_inverted_index":{"The":[0],"recent":[1],"text-to-speech":[2,80],"(TTS)":[3],"has":[4,18],"achieved":[5],"quality":[6],"comparable":[7],"to":[8,26,114,119,138,148],"that":[9,30,91,158],"of":[10,151,168],"humans;":[11],"however,":[12],"its":[13],"application":[14],"in":[15,50,144,166],"spoken":[16],"dialogue":[17,46,123],"not":[19],"been":[20],"widely":[21],"studied.":[22],"This":[23],"study":[24],"aims":[25],"realize":[27],"a":[28,82,93,109,145],"TTS":[29,47,86],"closely":[31],"resembles":[32],"human":[33],"dialogue.":[34,153],"First,":[35],"we":[36],"record":[37],"and":[38],"transcribe":[39],"actual":[40],"spontaneous":[41],"dialogues.":[42],"Then,":[43],"the":[44,106,116,129,135,149,152,159,163],"proposed":[45,84,160],"is":[48,64,100,112],"trained":[49,101,113],"two":[51],"stages:":[52],"first":[53],"stage,":[54,108],"variational":[55,61,73],"autoencoder":[56,62],"(VAE)-VITS":[57],"or":[58],"Gaussian":[59],"mixture":[60],"(GMVAE)-VITS":[63],"trained,":[65],"which":[66],"introduces":[67],"an":[68],"utterance-level":[69],"latent":[70,94],"variable":[71],"into":[72],"inference":[74],"with":[75,103],"adversarial":[76],"learning":[77],"for":[78],"end-to-end":[79,85],"(VITS),":[81],"recently":[83],"model.":[87],"A":[88],"style":[89,96,110,118,131,136,146],"encoder":[90],"extracts":[92],"speaking":[95,117,130],"representation":[97,132],"from":[98,122],"speech":[99,140],"jointly":[102],"TTS.":[104],"In":[105],"second":[107],"predictor":[111,137],"predict":[115],"be":[120,142],"synthesized":[121,143],"history.":[124],"During":[125],"inference,":[126],"by":[127,134],"passing":[128],"predicted":[133],"VAE/GMVAE-VITS,":[139],"can":[141],"appropriate":[147],"context":[150],"Subjective":[154],"evaluation":[155],"results":[156],"demonstrate":[157],"method":[161],"outperforms":[162],"original":[164],"VITS":[165],"terms":[167],"dialogue-level":[169],"naturalness.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}