{"id":"https://openalex.org/W2901796276","doi":"https://doi.org/10.1109/icassp.2019.8682168","title":"Effect of Data Reduction on Sequence-to-sequence Neural TTS","display_name":"Effect of Data Reduction on Sequence-to-sequence Neural TTS","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2901796276","doi":"https://doi.org/10.1109/icassp.2019.8682168","mag":"2901796276"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/1811.06315","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071418947","display_name":"Javier Latorre","orcid":null},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Javier Latorre","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063140150","display_name":"Jakub Lachowicz","orcid":null},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakub Lachowicz","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jaime Lorenzo-Trueba","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038417409","display_name":"Thomas Merritt","orcid":null},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Merritt","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"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/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Drugman","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004616142","display_name":"Srikanth Ronanki","orcid":null},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Srikanth Ronanki","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026578737","display_name":"Viacheslav Klimkov","orcid":null},"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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Viacheslav Klimkov","raw_affiliation_strings":["Amazon.com"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon.com","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7075","last_page":"7079"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.998199999332428,"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":0.8714806437492371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7300897836685181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7092198133468628},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6294087171554565},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5495532751083374},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5479375123977661},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.49960947036743164},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46336954832077026},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.44394201040267944},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36942794919013977},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13113093376159668},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.059909701347351074}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.8714806437492371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7300897836685181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092198133468628},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6294087171554565},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5495532751083374},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5479375123977661},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.49960947036743164},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46336954832077026},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.44394201040267944},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36942794919013977},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13113093376159668},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.059909701347351074},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2019.8682168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682168","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.06315","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06315","pdf_url":"https://arxiv.org/pdf/1811.06315","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":"text"},{"id":"mag:2901796276","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.06315.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":"doi:10.48550/arxiv.1811.06315","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.06315","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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.06315","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.06315","pdf_url":"https://arxiv.org/pdf/1811.06315","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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2901796276.pdf","grobid_xml":"https://content.openalex.org/works/W2901796276.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1580849279","https://openalex.org/W2078597717","https://openalex.org/W2116046013","https://openalex.org/W2153914468","https://openalex.org/W2191779130","https://openalex.org/W2591927543","https://openalex.org/W2788851830","https://openalex.org/W2792995953","https://openalex.org/W2793479148","https://openalex.org/W2808706139","https://openalex.org/W2889129899","https://openalex.org/W2901620353","https://openalex.org/W2949382160","https://openalex.org/W2963609956","https://openalex.org/W2963654953","https://openalex.org/W2963685250","https://openalex.org/W2963712897","https://openalex.org/W2964308564","https://openalex.org/W6634520857","https://openalex.org/W6635546818","https://openalex.org/W6677333272","https://openalex.org/W6679434410","https://openalex.org/W6695676441","https://openalex.org/W6734815144","https://openalex.org/W6738277540","https://openalex.org/W6745569068","https://openalex.org/W6745697700","https://openalex.org/W6746700228","https://openalex.org/W6748409065","https://openalex.org/W6752888775"],"related_works":["https://openalex.org/W2963542120","https://openalex.org/W1981865754","https://openalex.org/W3166514188","https://openalex.org/W3021975374","https://openalex.org/W1791154168","https://openalex.org/W158052051","https://openalex.org/W3197113339","https://openalex.org/W172728956","https://openalex.org/W2104117215","https://openalex.org/W2141673075","https://openalex.org/W2029996593","https://openalex.org/W2088699022","https://openalex.org/W2010097385","https://openalex.org/W1977273229","https://openalex.org/W2069237452","https://openalex.org/W2181384879","https://openalex.org/W2263270774","https://openalex.org/W2899253611","https://openalex.org/W297015806","https://openalex.org/W2055226387"],"abstract_inverted_index":{"Recent":[0],"speech":[1,14],"synthesis":[2],"systems":[3,118],"based":[4],"on":[5,53,74,120],"sampling":[6],"from":[7,17,36,44,59,97,104,127],"autoregressive":[8],"neural":[9],"network":[10],"models":[11,22,51,72,83,92],"can":[12,39,108],"generate":[13],"almost":[15],"indistinguishable":[16],"human":[18],"recordings.":[19],"However,":[20],"these":[21],"require":[23],"large":[24],"amounts":[25],"of":[26,34,49,56,69,80],"data.":[27],"This":[28],"paper":[29],"shows":[30],"that":[31,68,91],"the":[32,125,128],"lack":[33],"data":[35,43,126],"one":[37],"speaker":[38,70,100],"be":[40],"compensated":[41],"with":[42,101],"other":[45],"speakers.":[46],"The":[47],"naturalness":[48],"Tacotron2-like":[50],"trained":[52,73,119],"a":[54,98],"blend":[55],"5k":[57,102],"utterances":[58,96,103],"7":[60],"speakers":[61,107],"is":[62],"better":[63,111],"than":[64,113,122],"or":[65],"equivalent":[66],"to":[67],"dependent":[71],"15k":[75],"utterances.":[76],"Additionally,":[77],"in":[78],"terms":[79],"stability":[81],"multi-speaker":[82],"are":[84],"always":[85],"more":[86,121],"stable.":[87],"We":[88],"also":[89],"demonstrate":[90],"mixing":[93],"only":[94],"1250":[95],"target":[99,129],"another":[105],"6":[106],"produce":[109],"significantly":[110],"quality":[112],"state-of-the-art":[114],"DNN-guided":[115],"unit":[116],"selection":[117],"10":[123],"times":[124],"speaker.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}