{"id":"https://openalex.org/W3131702728","doi":"https://doi.org/10.21437/interspeech.2021-275","title":"Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text Input","display_name":"Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text Input","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3131702728","doi":"https://doi.org/10.21437/interspeech.2021-275","mag":"3131702728"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-275","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.09914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088405848","display_name":"Brooke Stephenson","orcid":"https://orcid.org/0000-0001-7507-7393"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Brooke Stephenson","raw_affiliation_strings":["Grenoble Institute of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Grenoble Institute of Technology#TAB#","institution_ids":["https://openalex.org/I106785703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060372031","display_name":"Thomas Hueber","orcid":"https://orcid.org/0000-0002-8296-5177"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Hueber","raw_affiliation_strings":["Grenoble Institute of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Grenoble Institute of Technology#TAB#","institution_ids":["https://openalex.org/I106785703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":["Grenoble Institute of Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Grenoble Institute of Technology#TAB#","institution_ids":["https://openalex.org/I106785703"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108120865","display_name":"Laurent Besacier","orcid":null},"institutions":[{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Besacier","raw_affiliation_strings":["Universite Grenoble-Alpes"],"affiliations":[{"raw_affiliation_string":"Universite Grenoble-Alpes","institution_ids":["https://openalex.org/I899635006"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088405848"],"corresponding_institution_ids":["https://openalex.org/I106785703"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61382981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3865","last_page":"3869"},"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/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.8698475360870361},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8011928796768188},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.73853999376297},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6682944893836975},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6445242762565613},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6393256187438965},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5464732050895691},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.484391987323761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4465564787387848},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4395481050014496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41775041818618774},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19565033912658691},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10011309385299683},{"id":"https://openalex.org/keywords/particle-physics","display_name":"Particle physics","score":0.06940513849258423}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8698475360870361},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8011928796768188},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.73853999376297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682944893836975},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6445242762565613},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6393256187438965},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5464732050895691},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.484391987323761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4465564787387848},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4395481050014496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41775041818618774},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19565033912658691},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10011309385299683},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.06940513849258423},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-275","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-275","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.09914","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09914","pdf_url":"https://arxiv.org/pdf/2102.09914","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":null,"raw_type":"text"},{"id":"mag:3131702728","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2102.09914.pdf","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:HAL:hal-03372802v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03372802","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.interspeech2021.org/","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2102.09914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.09914","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:2102.09914","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.09914","pdf_url":"https://arxiv.org/pdf/2102.09914","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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W44352932","https://openalex.org/W2056890381","https://openalex.org/W2065722210","https://openalex.org/W2129367645","https://openalex.org/W2191779130","https://openalex.org/W2273480558","https://openalex.org/W2294763331","https://openalex.org/W2470606929","https://openalex.org/W2517566275","https://openalex.org/W2884225676","https://openalex.org/W2889028433","https://openalex.org/W2952127920","https://openalex.org/W2963341956","https://openalex.org/W2970084653","https://openalex.org/W2972359262","https://openalex.org/W3015338123","https://openalex.org/W3016160783","https://openalex.org/W3030163527","https://openalex.org/W3048023795","https://openalex.org/W3092316169","https://openalex.org/W3094671762","https://openalex.org/W3098566014","https://openalex.org/W3098824823","https://openalex.org/W3100608856","https://openalex.org/W3104081910","https://openalex.org/W3130016944","https://openalex.org/W3156563027","https://openalex.org/W3216401400"],"related_works":["https://openalex.org/W3197407562","https://openalex.org/W3043750461","https://openalex.org/W2517266855","https://openalex.org/W3202111322","https://openalex.org/W2056503573","https://openalex.org/W1482606043","https://openalex.org/W1669398567","https://openalex.org/W2591264712","https://openalex.org/W2295412326","https://openalex.org/W2936047981","https://openalex.org/W40007074","https://openalex.org/W1525797625","https://openalex.org/W2952021518","https://openalex.org/W2397842403","https://openalex.org/W767271433","https://openalex.org/W2471661991","https://openalex.org/W2003430732","https://openalex.org/W2392368133","https://openalex.org/W1940136498","https://openalex.org/W1999038628"],"abstract_inverted_index":{"The":[0],"prosody":[1],"of":[2,42,56,69],"a":[3,40,104,119],"spoken":[4],"word":[5],"is":[6,33],"determined":[7],"by":[8],"its":[9],"surrounding":[10],"context.":[11],"In":[12,48],"incremental":[13],"text-to-speech":[14],"synthesis,":[15],"where":[16],"the":[17,27,30,45,54,88],"synthesizer":[18],"produces":[19],"an":[20],"output":[21],"before":[22],"it":[23],"has":[24],"access":[25],"to":[26],"complete":[28],"input,":[29],"full":[31],"context":[32],"often":[34],"unknown":[35,74],"which":[36],"can":[37,60],"result":[38],"in":[39,44],"loss":[41],"naturalness":[43],"synthesized":[46],"speech.":[47],"this":[49,62],"paper,":[50],"we":[51],"investigate":[52],"whether":[53],"use":[55],"predicted":[57,82,98],"future":[58,71],"text":[59,99],"attenuate":[61],"loss.":[63],"We":[64,86,114],"compare":[65],"several":[66],"test":[67],"conditions":[68],"next":[70],"word:":[72],"(a)":[73],"(zero-word),":[75],"(b)":[76],"language":[77],"model":[78],"predicted,":[79],"(c)":[80],"randomly":[81],"and":[83,93,95],"(d)":[84],"ground-truth.":[85],"measure":[87],"prosodic":[89],"features":[90],"(pitch,":[91],"energy":[92],"duration)":[94],"find":[96],"that":[97],"provides":[100],"significant":[101],"improvements":[102],"over":[103,111],"zero-word":[105],"lookahead,":[106],"but":[107],"only":[108],"slight":[109],"gains":[110],"random-word":[112],"lookahead.":[113],"confirm":[115],"these":[116],"results":[117],"with":[118],"perceptive":[120],"test.":[121]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}