{"id":"https://openalex.org/W3104281589","doi":"https://doi.org/10.1109/icassp39728.2021.9413466","title":"Low-Resource Expressive Text-To-Speech Using Data Augmentation","display_name":"Low-Resource Expressive Text-To-Speech Using Data Augmentation","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3104281589","doi":"https://doi.org/10.1109/icassp39728.2021.9413466","mag":"3104281589"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413466","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.05707","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058343897","display_name":"Goeric Huybrechts","orcid":"https://orcid.org/0000-0003-0222-3008"},"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":true,"raw_author_name":"Goeric Huybrechts","raw_affiliation_strings":["Amazon Alexa - TTS Research, Cambridge, United Kingdom","Amazon Alexa - TTS Research,Cambridge,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa - TTS Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Alexa - TTS Research,Cambridge,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","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":"Thomas Merritt","raw_affiliation_strings":["Amazon Alexa - TTS Research, Cambridge, United Kingdom","Amazon Alexa - TTS Research,Cambridge,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa - TTS Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Alexa - TTS Research,Cambridge,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041378836","display_name":"Giulia Comini","orcid":"https://orcid.org/0000-0002-9391-6565"},"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":"Giulia Comini","raw_affiliation_strings":["Amazon Alexa - TTS Research, Cambridge, United Kingdom","Amazon Alexa - TTS Research,Cambridge,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa - TTS Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Alexa - TTS Research,Cambridge,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033936072","display_name":"Bartek Perz","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":"Bartek Perz","raw_affiliation_strings":["Amazon Alexa - TTS Research, Cambridge, United Kingdom","Amazon Alexa - TTS Research,Cambridge,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa - TTS Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Alexa - TTS Research,Cambridge,United Kingdom","institution_ids":["https://openalex.org/I4210123934"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089445018","display_name":"Raahil Shah","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":"Raahil Shah","raw_affiliation_strings":["Amazon Alexa - TTS Research, Cambridge, United Kingdom","Amazon Alexa - TTS Research,Cambridge,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa - TTS Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon Alexa - TTS Research,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/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]},{"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":["DE","GB"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon Alexa - TTS Research, Cambridge, United Kingdom","Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa - TTS Research, Cambridge, United Kingdom","institution_ids":["https://openalex.org/I4210123934"]},{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058343897"],"corresponding_institution_ids":["https://openalex.org/I4210123934"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6593","last_page":"6597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8156227469444275},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7714958190917969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7065088748931885},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4935957193374634},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.44589000940322876},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.41937020421028137},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3712301254272461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3125994801521301},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27703651785850525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156227469444275},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7714958190917969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7065088748931885},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4935957193374634},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.44589000940322876},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.41937020421028137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3712301254272461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3125994801521301},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27703651785850525},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413466","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413466","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:2011.05707","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.05707","pdf_url":"https://arxiv.org/pdf/2011.05707","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":null},{"id":"doi:10.48550/arxiv.2011.05707","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.05707","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/py4v-tx30","is_oa":true,"landing_page_url":"https://doi.org/10.17023/py4v-tx30","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"article"},{"id":"mag:3104281589","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.05707","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.05707","pdf_url":"https://arxiv.org/pdf/2011.05707","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":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3104281589.pdf","grobid_xml":"https://content.openalex.org/works/W3104281589.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W2407080277","https://openalex.org/W2576309025","https://openalex.org/W2608338293","https://openalex.org/W2696967604","https://openalex.org/W2775795276","https://openalex.org/W2795109282","https://openalex.org/W2796495654","https://openalex.org/W2809598685","https://openalex.org/W2889028433","https://openalex.org/W2901997113","https://openalex.org/W2904459034","https://openalex.org/W2936774411","https://openalex.org/W2937579788","https://openalex.org/W2949382160","https://openalex.org/W2954996726","https://openalex.org/W2963035245","https://openalex.org/W2963432880","https://openalex.org/W2963542120","https://openalex.org/W2963609956","https://openalex.org/W2963712897","https://openalex.org/W2963782041","https://openalex.org/W2963927338","https://openalex.org/W2964307104","https://openalex.org/W2969658393","https://openalex.org/W2973034126","https://openalex.org/W2990883660","https://openalex.org/W3022876224","https://openalex.org/W3048379951","https://openalex.org/W3081416955","https://openalex.org/W3096303254","https://openalex.org/W6640963894","https://openalex.org/W6713762819","https://openalex.org/W6736996214","https://openalex.org/W6737196085","https://openalex.org/W6747218270","https://openalex.org/W6748409065","https://openalex.org/W6752888775","https://openalex.org/W6758366080","https://openalex.org/W6765987481","https://openalex.org/W6770820927","https://openalex.org/W6777168481","https://openalex.org/W6843673214"],"related_works":["https://openalex.org/W3161492781","https://openalex.org/W3194822862","https://openalex.org/W3205133942","https://openalex.org/W3184134242","https://openalex.org/W2898532037","https://openalex.org/W3178839419","https://openalex.org/W3207961486","https://openalex.org/W3146104336","https://openalex.org/W3195366621","https://openalex.org/W2251498782","https://openalex.org/W1515194102","https://openalex.org/W2890301597","https://openalex.org/W2546627663","https://openalex.org/W2737982026","https://openalex.org/W3123318516","https://openalex.org/W3201341142","https://openalex.org/W2964171275","https://openalex.org/W2914049472","https://openalex.org/W3203614938","https://openalex.org/W3035626590"],"abstract_inverted_index":{"While":[0],"recent":[1],"neural":[2],"text-to-speech":[3],"(TTS)":[4],"systems":[5],"perform":[6],"remarkably":[7],"well,":[8],"they":[9],"typically":[10],"require":[11],"a":[12,32,96],"substantial":[13],"amount":[14],"of":[15,41,45,61,90,125,152],"recordings":[16,73,93],"from":[17,79],"the":[18,23,38,75,91,112,130,150],"target":[19,46],"speaker":[20],"reading":[21],"in":[22,48,74],"desired":[24,76],"speaking":[25,77],"style.":[26],"In":[27],"this":[28],"work,":[29],"we":[30,65,83,100],"present":[31],"novel":[33],"3-step":[34],"methodology":[35],"to":[36,50,94,104],"circumvent":[37],"costly":[39],"operation":[40],"recording":[42],"large":[43],"amounts":[44],"data":[47,67,87],"order":[49],"build":[51],"expressive":[52],"style":[53,78],"voices":[54],"with":[55],"as":[56,58],"little":[57],"15":[59],"minutes":[60],"such":[62],"recordings.":[63],"First,":[64],"augment":[66],"via":[68],"voice":[69],"conversion":[70],"by":[71],"leveraging":[72],"other":[80],"speakers.":[81],"Next,":[82],"use":[84],"that":[85,102,111],"synthetic":[86],"on":[88,133,139,143],"top":[89],"available":[92],"train":[95],"TTS":[97],"model.":[98],"Finally,":[99],"fine-tune":[101],"model":[103],"further":[105],"increase":[106],"quality.":[107],"Our":[108],"evaluations":[109],"show":[110],"proposed":[113,131],"changes":[114],"bring":[115],"significant":[116],"improvements":[117],"over":[118],"non-augmented":[119],"models":[120],"across":[121],"many":[122],"perceived":[123],"aspects":[124],"synthesised":[126],"speech.":[127],"We":[128],"demonstrate":[129],"approach":[132],"2":[134],"styles":[135],"(news-caster":[136],"and":[137,142,146],"conversational),":[138],"various":[140],"speakers,":[141],"both":[144],"single":[145],"multi-speaker":[147],"models,":[148],"illustrating":[149],"robustness":[151],"our":[153],"approach.":[154],"<sup":[155],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[157]},"counts_by_year":[],"updated_date":"2026-04-02T13:48:15.688549","created_date":"2025-10-10T00:00:00"}