{"id":"https://openalex.org/W2800788625","doi":"https://doi.org/10.1109/icassp.2018.8461960","title":"On the Analysis of Training Data for Wavenet-Based Speech Synthesis","display_name":"On the Analysis of Training Data for Wavenet-Based Speech Synthesis","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2800788625","doi":"https://doi.org/10.1109/icassp.2018.8461960","mag":"2800788625"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041401157","display_name":"Jakub V\u00edt","orcid":"https://orcid.org/0000-0001-5828-0605"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jakub Vit","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064576255","display_name":"Zden\u011bk Hanzl\u00ed\u010dek","orcid":"https://orcid.org/0000-0002-4001-9289"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Zdenek Hanzlicek","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030642609","display_name":"Jind\u0159ich Matou\u0161ek","orcid":"https://orcid.org/0000-0002-7408-7730"},"institutions":[{"id":"https://openalex.org/I92715842","display_name":"University of West Bohemia in Pilsen","ror":"https://ror.org/040t43x18","country_code":"CZ","type":"education","lineage":["https://openalex.org/I92715842"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jindrich Matousek","raw_affiliation_strings":["Department of Cybernetics, University of West Bohemia, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, University of West Bohemia, Czech Republic","institution_ids":["https://openalex.org/I92715842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5206,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86856176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5684","last_page":"5688"},"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":0.9961000084877014,"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":0.9901000261306763,"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":0.7995829582214355},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.74955815076828},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6604173183441162},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6585176587104797},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6029550433158875},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5673097968101501},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4977603256702423},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.485838383436203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4624055027961731},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44594821333885193},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.06776607036590576}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995829582214355},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.74955815076828},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6604173183441162},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6585176587104797},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6029550433158875},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5673097968101501},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4977603256702423},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.485838383436203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4624055027961731},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44594821333885193},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06776607036590576},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461960","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1539777262","https://openalex.org/W1655397831","https://openalex.org/W2024093103","https://openalex.org/W2102003408","https://openalex.org/W2129142580","https://openalex.org/W2150658333","https://openalex.org/W2169711598","https://openalex.org/W2188827208","https://openalex.org/W2236675820","https://openalex.org/W2395689816","https://openalex.org/W2406990556","https://openalex.org/W2519091744","https://openalex.org/W2591927543","https://openalex.org/W2674088828","https://openalex.org/W2746474733","https://openalex.org/W2747681982","https://openalex.org/W2749651610","https://openalex.org/W2787437524","https://openalex.org/W2901997113","https://openalex.org/W6682221467","https://openalex.org/W6687241212","https://openalex.org/W6712374067","https://openalex.org/W6713766066","https://openalex.org/W6734815144","https://openalex.org/W6756197946"],"related_works":["https://openalex.org/W2317723112","https://openalex.org/W2475724061","https://openalex.org/W2361861616","https://openalex.org/W2773393136","https://openalex.org/W2174706483","https://openalex.org/W2997121352","https://openalex.org/W419536403","https://openalex.org/W2506280730","https://openalex.org/W4237969969","https://openalex.org/W1594297642"],"abstract_inverted_index":{"In":[0],"this":[1,29],"paper,":[2],"we":[3,52,63],"analyze":[4],"how":[5,7,10,43],"much,":[6],"consistent":[8],"and":[9,41,47,59,62,89,122],"accurate":[11],"data":[12,40,70,142],"WaveNet-based":[13],"speech":[14,23,95,128],"synthesis":[15],"method":[16],"needs":[17],"to":[18,21,34,55,93,117,119],"be":[19],"able":[20],"generate":[22],"of":[24,37,68,76,80,114,127,140],"good":[25],"quality.":[26],"We":[27,84,101],"do":[28],"by":[30,71],"adding":[31,110],"artificial":[32],"noise":[33,54,115],"the":[35,66,98],"description":[36],"our":[38,133],"training":[39,69,79,141],"observing":[42],"well":[44],"WaveNet":[45,82,104,134],"trains":[46],"produces":[48],"speech.":[49],"More":[50],"specifically,":[51],"add":[53],"both":[56],"phonetic":[57,120],"segmentation":[58,121],"annotation":[60],"accuracy,":[61],"also":[64],"reduce":[65],"size":[67],"using":[72],"a":[73,81,111],"fewer":[74],"number":[75],"sentences":[77],"during":[78],"model.":[83],"conducted":[85,99],"MUSHRA":[86],"listening":[87],"tests":[88],"used":[90],"objective":[91],"measures":[92],"track":[94],"quality":[96,107,129],"within":[97],"experiments.":[100],"show":[102],"that":[103],"retains":[105],"high":[106],"even":[108],"after":[109],"small":[112,125],"amount":[113],"(up":[116],"10%)":[118],"annotation.":[123],"A":[124],"degradation":[126],"was":[130],"observed":[131],"for":[132],"configuration":[135],"when":[136],"only":[137],"3":[138],"hours":[139],"were":[143],"used.":[144]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
