{"id":"https://openalex.org/W3096634037","doi":"https://doi.org/10.1109/icassp39728.2021.9413696","title":"Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech","display_name":"Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3096634037","doi":"https://doi.org/10.1109/icassp39728.2021.9413696","mag":"3096634037"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.02252","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066855316","display_name":"Sri Karlapati","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":"Sri Karlapati","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom","[Amazon Research, Cambridge, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon Research, Cambridge, United Kingdom]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081086162","display_name":"Ammar Abbas","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":"Ammar Abbas","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom","[Amazon Research, Cambridge, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon Research, Cambridge, United Kingdom]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041839891","display_name":"Zack Hodari","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zack Hodari","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","University of Edinburgh,The Centre for Speech Technology Research,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"University of Edinburgh,The Centre for Speech Technology Research,United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014483986","display_name":"Alexis Moinet","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":"Alexis Moinet","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom","[Amazon Research, Cambridge, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon Research, Cambridge, United Kingdom]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083043476","display_name":"Arnaud Joly","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":"Arnaud Joly","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom","[Amazon Research, Cambridge, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon Research, Cambridge, United Kingdom]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006537074","display_name":"Penny Karanasou","orcid":"https://orcid.org/0000-0003-1939-4161"},"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":"Penny Karanasou","raw_affiliation_strings":["Amazon Research, Cambridge, United Kingdom","[Amazon Research, Cambridge, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon Research, Cambridge, United Kingdom]","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"last","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 Research, Cambridge, United Kingdom","[Amazon Research, Cambridge, United Kingdom]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"[Amazon Research, Cambridge, United Kingdom]","institution_ids":["https://openalex.org/I4210123934"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5861,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65821596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"6573","last_page":"6577"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998000264167786,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7287705540657043},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6272584795951843},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6074410080909729},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5967074036598206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5530326962471008},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.544013500213623},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4939144253730774},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4699687361717224},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46282511949539185},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.45740440487861633},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43468204140663147},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4243195056915283},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41700854897499084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7287705540657043},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6272584795951843},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6074410080909729},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5967074036598206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5530326962471008},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.544013500213623},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4939144253730774},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4699687361717224},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46282511949539185},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.45740440487861633},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43468204140663147},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4243195056915283},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41700854897499084},{"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/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2011.02252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02252","pdf_url":"https://arxiv.org/pdf/2011.02252","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:3096634037","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.02252.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2011.02252","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.02252","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/kg53-7006","is_oa":true,"landing_page_url":"https://doi.org/10.17023/kg53-7006","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.02252","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02252","pdf_url":"https://arxiv.org/pdf/2011.02252","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":0.6499999761581421,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3096634037.pdf","grobid_xml":"https://content.openalex.org/works/W3096634037.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W2069859485","https://openalex.org/W2244807774","https://openalex.org/W2269892441","https://openalex.org/W2519091744","https://openalex.org/W2795109282","https://openalex.org/W2795485067","https://openalex.org/W2808626814","https://openalex.org/W2903739847","https://openalex.org/W2904459034","https://openalex.org/W2905224888","https://openalex.org/W2907916773","https://openalex.org/W2962691331","https://openalex.org/W2963341956","https://openalex.org/W2963521945","https://openalex.org/W2963609956","https://openalex.org/W2963858333","https://openalex.org/W2963927338","https://openalex.org/W2964138190","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2971753973","https://openalex.org/W2972885185","https://openalex.org/W2973217961","https://openalex.org/W2990883660","https://openalex.org/W3006881356","https://openalex.org/W3022876224","https://openalex.org/W3118485687","https://openalex.org/W6690815549","https://openalex.org/W6748409065","https://openalex.org/W6755207826","https://openalex.org/W6757374366","https://openalex.org/W6757699683","https://openalex.org/W6767453231","https://openalex.org/W6770820927"],"related_works":["https://openalex.org/W2950349262","https://openalex.org/W2952712483","https://openalex.org/W2032899051","https://openalex.org/W3136576491","https://openalex.org/W2133604784","https://openalex.org/W2792578205","https://openalex.org/W1863882239","https://openalex.org/W2532440341","https://openalex.org/W2295125710","https://openalex.org/W2602144740","https://openalex.org/W2918149204","https://openalex.org/W774340019","https://openalex.org/W2471661991","https://openalex.org/W2396108715","https://openalex.org/W202301840","https://openalex.org/W3158085692","https://openalex.org/W111538421","https://openalex.org/W2335143280","https://openalex.org/W2085621450","https://openalex.org/W3113076898"],"abstract_inverted_index":{"In":[0,23,40],"this":[1,51],"paper,":[2],"we":[3,26,43,65],"introduce":[4],"Kathaka,":[5],"a":[6,10,28,45,81,91,112],"model":[7],"trained":[8],"with":[9,19],"novel":[11,46],"two-stage":[12],"training":[13],"process":[14],"for":[15],"neural":[16],"speech":[17],"synthesis":[18],"contextually":[20],"appropriate":[21],"prosody.":[22],"Stage":[24,41],"I,":[25],"learn":[27],"prosodic":[29,53],"distribution":[30,54],"at":[31],"the":[32,56,117],"sentence":[33],"level":[34],"from":[35,50,77],"mel-spectrograms":[36],"available":[37,59],"during":[38],"training.":[39],"II,":[42],"propose":[44],"method":[47],"to":[48,96],"sample":[49],"learnt":[52],"using":[55],"contextual":[57],"information":[58],"in":[60,88,119],"text.":[61,78],"To":[62],"do":[63],"this,":[64],"use":[66],"BERT":[67],"on":[68,73,104],"text,":[69],"and":[70,110],"graph-attention":[71],"networks":[72],"parse":[74],"trees":[75],"extracted":[76],"We":[79,98],"show":[80,111],"statistically":[82,113],"significant":[83,114],"relative":[84],"improvement":[85,115],"of":[86,106],"13.2%":[87],"naturalness":[89],"over":[90,116],"strong":[92],"baseline":[93,118],"when":[94],"compared":[95],"recordings.":[97],"also":[99],"conduct":[100],"an":[101],"ablation":[102],"study":[103],"variations":[105],"our":[107],"sampling":[108],"technique,":[109],"each":[120],"case.":[121]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}