{"id":"https://openalex.org/W2886022419","doi":"https://doi.org/10.21437/interspeech.2018-1227","title":"Investigating Accuracy of Pitch-accent Annotations in Neural Network-based Speech Synthesis and Denoising Effects","display_name":"Investigating Accuracy of Pitch-accent Annotations in Neural Network-based Speech Synthesis and Denoising Effects","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2886022419","doi":"https://doi.org/10.21437/interspeech.2018-1227","mag":"2886022419"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1227","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/283358d6-fb46-4234-b27f-8023cf2d67a0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002145453","display_name":"Hieu-Thi Luong","orcid":"https://orcid.org/0000-0002-4772-5995"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hieu-Thi Luong","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327839","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-8246-0606"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["National Institute of Informatics, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035313377","display_name":"Nobuyuki Nishizawa","orcid":"https://orcid.org/0009-0007-6242-5695"},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobuyuki Nishizawa","raw_affiliation_strings":["KDDI Research Inc., Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"KDDI Research Inc., Saitama, Japan","institution_ids":["https://openalex.org/I4210164495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002145453"],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":3.2062,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.9354725,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"41"},"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":0.9959999918937683,"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":0.9958999752998352,"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":0.7371507883071899},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.6988266706466675},{"id":"https://openalex.org/keywords/turing-test","display_name":"Turing test","score":0.6368108987808228},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6345658302307129},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5870459079742432},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5734796524047852},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5723880529403687},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5662555694580078},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5027892589569092},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.48244649171829224},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4544229805469513},{"id":"https://openalex.org/keywords/ideal","display_name":"Ideal (ethics)","score":0.43575310707092285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4189508855342865},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.09357753396034241}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7371507883071899},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.6988266706466675},{"id":"https://openalex.org/C577917","wikidata":"https://www.wikidata.org/wiki/Q189223","display_name":"Turing test","level":2,"score":0.6368108987808228},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6345658302307129},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5870459079742432},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5734796524047852},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5723880529403687},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5662555694580078},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5027892589569092},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.48244649171829224},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4544229805469513},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.43575310707092285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4189508855342865},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.09357753396034241},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1227","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1227","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/283358d6-fb46-4234-b27f-8023cf2d67a0","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/283358d6-fb46-4234-b27f-8023cf2d67a0","pdf_url":"https://www.research.ed.ac.uk/en/publications/283358d6-fb46-4234-b27f-8023cf2d67a0","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/283358d6-fb46-4234-b27f-8023cf2d67a0","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/283358d6-fb46-4234-b27f-8023cf2d67a0","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Luong, H-T, Wang, X, Yamagishi, J & Nishizawa, N 2018, Investigating accuracy of pitch-accent annotations in neural network-based speech synthesis and denoising effects. in Proc. Interspeech 2018. Interspeech, International Speech Communication Association, Hyderabad, India, pp. 37-41, Interspeech 2018, Hyderabad, India, 2/09/18. < http://10.21437/Interspeech.2018-1227 >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/283358d6-fb46-4234-b27f-8023cf2d67a0","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/283358d6-fb46-4234-b27f-8023cf2d67a0","pdf_url":"https://www.research.ed.ac.uk/en/publications/283358d6-fb46-4234-b27f-8023cf2d67a0","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2886022419.pdf","grobid_xml":"https://content.openalex.org/works/W2886022419.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1579853615","https://openalex.org/W1783473872","https://openalex.org/W2039800941","https://openalex.org/W2043003570","https://openalex.org/W2102003408","https://openalex.org/W2152205330","https://openalex.org/W2294797155","https://openalex.org/W2394921947","https://openalex.org/W2395689816","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2595110011","https://openalex.org/W2604184139","https://openalex.org/W2745595539","https://openalex.org/W2747914378","https://openalex.org/W2749651610","https://openalex.org/W2759925408","https://openalex.org/W2766812927","https://openalex.org/W2901997113","https://openalex.org/W2963522141","https://openalex.org/W2964243274"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2154644810","https://openalex.org/W2154237089","https://openalex.org/W1489682032"],"abstract_inverted_index":{"We":[0,25],"investigated":[1],"the":[2,9,69,73,88,119,123,129,132,135,139,147],"impact":[3],"of":[4,11,131,146],"noisy":[5],"linguistic":[6,34,54,64,120,144],"features":[7,35,121,145],"on":[8,18],"performance":[10,76],"a":[12,47,79,84,103],"Japanese":[13,158],"speech":[14,108,153],"synthesis":[15],"system":[16,29,140],"based":[17],"neural":[19,156],"network":[20],"that":[21,30,51,62,100,115],"uses":[22,31],"WaveNet":[23,160],"vocoder.":[24],"compared":[26],"an":[27,95],"ideal":[28,74],"manually":[32],"corrected":[33],"including":[36],"phoneme":[37],"and":[38,43,58,90,137],"prosodic":[39],"information":[40],"in":[41,68,78,122],"training":[42,89,124],"test":[44,70,91,98,148],"sets":[45],"against":[46],"few":[48],"other":[49],"systems":[50],"use":[52],"corrupted":[53,63],"features.":[55],"Both":[56],"subjective":[57],"objective":[59],"results":[60],"demonstrate":[61],"features,":[65],"especially":[66],"those":[67],"set,":[71],"affected":[72],"system\u2019s":[75],"significantly":[77],"statistical":[80],"sense":[81],"due":[82],"to":[83,118],"mismatched":[85],"condition":[86],"between":[87],"sets.":[92],"Interestingly,":[93],"while":[94],"utterance-level":[96],"Turing":[97],"showed":[99],"listeners":[101],"had":[102],"difficult":[104],"time":[105],"differentiating":[106],"synthetic":[107],"from":[109],"natural":[110],"speech,":[111],"it":[112],"further":[113],"indicated":[114],"adding":[116],"noise":[117],"set":[125,149],"can":[126],"partially":[127],"reduce":[128],"effect":[130],"mismatch,":[133],"regularize":[134],"model,":[136],"help":[138],"perform":[141],"better":[142],"when":[143],"are":[150],"noisy.<br/><b>Index":[151],"Terms</b>:":[152],"synthesis,":[154],"deep":[155],"network,":[157],"prosody,":[159]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}