{"id":"https://openalex.org/W3018342478","doi":"https://doi.org/10.1109/o-cocosda46868.2019.9060845","title":"Phoneme-level speaking rate variation on waveform generation using GAN-TTS","display_name":"Phoneme-level speaking rate variation on waveform generation using GAN-TTS","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W3018342478","doi":"https://doi.org/10.1109/o-cocosda46868.2019.9060845","mag":"3018342478"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda46868.2019.9060845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda46868.2019.9060845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 22nd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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/A5090298607","display_name":"Mayuko Okamato","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Mayuko Okamato","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Advanced Intelligence Project AIP, Nara Institute of Science and Technology, RIKEN, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Intelligence Project AIP, Nara Institute of Science and Technology, RIKEN, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Advanced Intelligence Project AIP, Nara Institute of Science and Technology, RIKEN, Japan"],"affiliations":[{"raw_affiliation_string":"Advanced Intelligence Project AIP, Nara Institute of Science and Technology, RIKEN, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5090298607"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":0.4976,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65883147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9157999753952026,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9157999753952026,"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/waveform","display_name":"Waveform","score":0.8061950206756592},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.7392904758453369},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48649662733078003},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39878571033477783},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16379547119140625},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.158115953207016}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.8061950206756592},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.7392904758453369},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48649662733078003},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39878571033477783},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16379547119140625},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.158115953207016},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda46868.2019.9060845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda46868.2019.9060845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 22nd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2386430105","https://openalex.org/W2356521405","https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2038534795","https://openalex.org/W2364769705","https://openalex.org/W2384358604"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,13,60],"text-to-speech":[3],"synthesis":[4],"(TTS)":[5],"systems":[6,23],"continues":[7],"to":[8,51,54,57],"advance,":[9],"and":[10,33,49],"the":[11,35],"naturalness":[12],"their":[14,46],"generated":[15],"speech":[16],"has":[17],"significantly":[18],"improved.":[19],"But":[20],"most":[21],"TTS":[22],"now":[24],"learn":[25],"from":[26],"data":[27],"using":[28],"a":[29,38],"deep":[30],"learning":[31],"framework":[32],"generate":[34],"output":[36],"at":[37],"monotonous":[39],"speaking":[40,47],"rate.":[41],"In":[42],"contrast":[43],"humans":[44],"vary":[45],"rates":[48],"tend":[50],"slow":[52],"down":[53],"emphasize":[55],"words":[56],"distinguish":[58],"elements":[59],"focus":[61],"in":[62],"an":[63],"utterance.":[64]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}