{"id":"https://openalex.org/W2963945466","doi":"https://doi.org/10.1109/icassp.2019.8682353","title":"Investigation of Enhanced Tacotron Text-to-speech Synthesis Systems with Self-attention for Pitch Accent Language","display_name":"Investigation of Enhanced Tacotron Text-to-speech Synthesis Systems with Self-attention for Pitch Accent Language","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2963945466","doi":"https://doi.org/10.1109/icassp.2019.8682353","mag":"2963945466"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682353","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068072475","display_name":"Yusuke Yasuda","orcid":"https://orcid.org/0000-0002-2130-747X"},"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":"Yusuke Yasuda","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, 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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062895056","display_name":"Shinji Takaki","orcid":"https://orcid.org/0000-0001-7294-7699"},"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":"Shinji Takaki","raw_affiliation_strings":["National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","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, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184597095"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":81,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6905","last_page":"6909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9991999864578247,"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/T12031","display_name":"Speech and dialogue systems","score":0.9991999864578247,"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":0.7274353504180908},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6811062693595886},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6529533863067627},{"id":"https://openalex.org/keywords/pitch-accent","display_name":"Pitch accent","score":0.632249116897583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.610909640789032},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49318021535873413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4002499580383301},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.22158995270729065}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7274353504180908},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6811062693595886},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6529533863067627},{"id":"https://openalex.org/C2777672088","wikidata":"https://www.wikidata.org/wiki/Q1441804","display_name":"Pitch accent","level":3,"score":0.632249116897583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.610909640789032},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49318021535873413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002499580383301},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.22158995270729065}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2019.8682353","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682353","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:pure.ed.ac.uk:publications/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","pdf_url":"http://hdl.handle.net/20.500.11820/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":null,"raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","is_oa":true,"landing_page_url":"https://hdl.handle.net/20.500.11820/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":null,"raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","pdf_url":"http://hdl.handle.net/20.500.11820/a0c1b235-3613-4ea8-a511-cb1692d1fd1b","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":null,"raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2963945466.pdf"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2519091744","https://openalex.org/W2597655663","https://openalex.org/W2801493797","https://openalex.org/W2886022419","https://openalex.org/W2886769154","https://openalex.org/W2888796807","https://openalex.org/W2892140764","https://openalex.org/W2962970071","https://openalex.org/W2963386218","https://openalex.org/W2963403868","https://openalex.org/W2963522141","https://openalex.org/W2963609956","https://openalex.org/W2963975282","https://openalex.org/W2964034111","https://openalex.org/W2964121744","https://openalex.org/W2964195110","https://openalex.org/W2964243274","https://openalex.org/W2964308564","https://openalex.org/W4293714597","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6714142977","https://openalex.org/W6735377749","https://openalex.org/W6739901393","https://openalex.org/W6753855596","https://openalex.org/W6754925833"],"related_works":["https://openalex.org/W2088008556","https://openalex.org/W4360877803","https://openalex.org/W4298046075","https://openalex.org/W2334135487","https://openalex.org/W4207066001","https://openalex.org/W2381837697","https://openalex.org/W162378616","https://openalex.org/W4251666207","https://openalex.org/W2087397317","https://openalex.org/W2350046259"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,52,86,184],"synthesis":[2],"is":[3,35],"a":[4,70,76,122,170],"promising":[5],"approach":[6],"that":[7,18,74,158],"directly":[8],"converts":[9],"raw":[10],"text":[11,78],"to":[12,26,32,49,56,91,95,100,115],"speech.":[13],"Although":[14],"it":[15],"was":[16],"shown":[17],"Tacotron2":[19],"outperforms":[20],"classical":[21,109],"pipeline":[22,72,110,172],"systems":[23,65,92,111,162],"with":[24,93,108],"regards":[25],"naturalness":[27],"in":[28],"English,":[29],"its":[30,57],"applicability":[31],"other":[33],"languages":[34,46],"still":[36,67,163],"unknown.":[37],"Japanese":[38,85,183],"could":[39],"be":[40],"one":[41],"of":[42,130,133,138,151,169],"the":[43,128,131,136,152,160,167],"most":[44],"difficult":[45],"for":[47,174],"which":[48],"achieve":[50],"end-to-end":[51,84,182],"synthesis,":[53,87],"largely":[54],"due":[55],"character":[58],"diversity":[59],"and":[60,80,103,119,143],"pitch":[61,101],"accents.":[62],"Therefore,":[63],"state-of-the-art":[64],"are":[66],"based":[68],"on":[69],"traditional":[71],"framework":[73],"requires":[75],"separate":[77],"analyzer":[79],"duration":[81],"model.":[82],"Towards":[83],"we":[88,126,176],"extend":[89],"Tacotron":[90],"self-attention":[94],"capture":[96],"long-term":[97],"dependencies":[98],"related":[99],"accents":[102],"compare":[104],"their":[105,117],"audio":[106],"quality":[107,168],"under":[112],"various":[113],"conditions":[114],"show":[116,177],"pros":[118],"cons.":[120],"In":[121],"large-scale":[123],"listening":[124],"test,":[125],"investigated":[127],"impacts":[129],"presence":[132],"accentual-type":[134],"labels,":[135],"use":[137],"force":[139],"or":[140],"predicted":[141],"alignments,":[142],"acoustic":[144],"features":[145],"used":[146],"as":[147],"local":[148],"condition":[149],"parameters":[150],"Wavenet":[153],"vocoder.":[154],"Our":[155],"results":[156],"reveal":[157],"although":[159],"proposed":[161],"do":[164],"not":[165],"match":[166],"top-line":[171],"system":[173],"Japanese,":[175],"important":[178],"stepping":[179],"stones":[180],"towards":[181],"synthesis.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":16}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}