{"id":"https://openalex.org/W2990883660","doi":"https://doi.org/10.21437/interspeech.2020-1411","title":"Dynamic Prosody Generation for Speech Synthesis Using Linguistics-Driven Acoustic Embedding Selection","display_name":"Dynamic Prosody Generation for Speech Synthesis Using Linguistics-Driven Acoustic Embedding Selection","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W2990883660","doi":"https://doi.org/10.21437/interspeech.2020-1411","mag":"2990883660"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1411","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.00955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020070184","display_name":"Shubhi Tyagi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shubhi Tyagi","raw_affiliation_strings":["Amazon.com, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054742272","display_name":"Marco Nicolis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Marco Nicolis","raw_affiliation_strings":["Amazon.com, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050067836","display_name":"Jonas Rohnke","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jonas Rohnke","raw_affiliation_strings":["Amazon.com, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029023520","display_name":"Thomas Drugman","orcid":"https://orcid.org/0000-0002-1491-7878"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon.com, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019530089","display_name":"Jaime Lorenzo-Trueba","orcid":"https://orcid.org/0000-0003-0459-1429"},"institutions":[{"id":"https://openalex.org/I4210123934","display_name":"Amazon (United Kingdom)","ror":"https://ror.org/02xey9634","country_code":"GB","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210123934"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon.com, Cambridge, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123934"],"apc_list":null,"apc_paid":null,"fwci":3.5126,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93908036,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4407","last_page":"4411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/naturalness","display_name":"Naturalness","score":0.8984206914901733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8019272089004517},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.7630413770675659},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6138685345649719},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5458952188491821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.522296667098999},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4953259527683258},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.43628332018852234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43213993310928345},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.32631275057792664}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8984206914901733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8019272089004517},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7630413770675659},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6138685345649719},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5458952188491821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.522296667098999},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4953259527683258},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.43628332018852234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43213993310928345},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.32631275057792664},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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":2,"locations":[{"id":"doi:10.21437/interspeech.2020-1411","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1912.00955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.00955","pdf_url":"https://arxiv.org/pdf/1912.00955","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.00955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.00955","pdf_url":"https://arxiv.org/pdf/1912.00955","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":[{"score":0.8299999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2069859485","https://openalex.org/W2121879602","https://openalex.org/W2153579005","https://openalex.org/W2251831371","https://openalex.org/W2507550121","https://openalex.org/W2798569372","https://openalex.org/W2885800352","https://openalex.org/W2888844474","https://openalex.org/W2896457183","https://openalex.org/W2908854766","https://openalex.org/W2941649920","https://openalex.org/W2954386831","https://openalex.org/W2962691331","https://openalex.org/W2963085091","https://openalex.org/W2963300588","https://openalex.org/W2963341956","https://openalex.org/W2963521945","https://openalex.org/W2963542120","https://openalex.org/W2963568578","https://openalex.org/W2963609956","https://openalex.org/W2963754491","https://openalex.org/W2964243274","https://openalex.org/W2967220154","https://openalex.org/W2972375191","https://openalex.org/W2972885185","https://openalex.org/W2973013313","https://openalex.org/W3104033643","https://openalex.org/W4288351520","https://openalex.org/W4289383906","https://openalex.org/W4294170691","https://openalex.org/W4313908941"],"related_works":["https://openalex.org/W4392904630","https://openalex.org/W169399214","https://openalex.org/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W1927421023","https://openalex.org/W10581632","https://openalex.org/W2108985546","https://openalex.org/W2081919107"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,23,53,82,113],"Text-to-Speech":[3],"(TTS)":[4],"have":[5],"improved":[6],"quality":[7],"and":[8,33,50,93,105],"naturalness":[9,106],"to":[10,25,41],"near-human":[11],"capabilities":[12],"when":[13],"considering":[14],"isolated":[15],"sentences.":[16],"But":[17],"something":[18],"which":[19,73],"is":[20,29],"still":[21],"lacking":[22],"order":[24],"achieve":[26],"human-like":[27],"communication":[28],"the":[30,43,62,78,83,88,100,103],"dynamic":[31,49],"variations":[32],"adaptability":[34],"of":[35,45,90],"human":[36],"speech.":[37],"This":[38],"work":[39],"attempts":[40],"solve":[42],"problem":[44],"achieving":[46],"a":[47,68],"more":[48],"natural":[51],"intonation":[52],"TTS":[54],"systems,":[55],"particularly":[56],"for":[57,107],"stylistic":[58],"speech":[59,79],"such":[60],"as":[61,110,112],"newscaster":[63],"speaking":[64],"style.":[65],"We":[66,86],"propose":[67],"novel":[69],"embedding":[70],"selection":[71],"approach":[72,101],"exploits":[74],"linguistic":[75],"information,":[76],"leveraging":[77],"variability":[80],"present":[81],"training":[84],"dataset.":[85],"analyze":[87],"contribution":[89],"both":[91],"semantic":[92],"syntactic":[94],"features.":[95],"Our":[96],"results":[97],"show":[98],"that":[99],"improves":[102],"prosody":[104],"complex":[108],"utterances":[109],"well":[111],"Long":[114],"Form":[115],"Reading":[116],"(LFR).":[117]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2019-12-05T00:00:00"}