{"id":"https://openalex.org/W4406858702","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849075","title":"Speech Synthesis from IPA Sequences through EMA Data","display_name":"Speech Synthesis from IPA Sequences through EMA Data","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4406858702","doi":"https://doi.org/10.1109/apsipaasc63619.2025.10849075"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc63619.2025.10849075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102168789","display_name":"Koki Maruyama","orcid":null},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koki Maruyama","raw_affiliation_strings":["Tokyo University of Science,Noda, Chiba,Japan,278-8510"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University of Science,Noda, Chiba,Japan,278-8510","institution_ids":["https://openalex.org/I161296585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068803377","display_name":"Shun Sawada","orcid":null},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shun Sawada","raw_affiliation_strings":["Tokyo University of Science,Noda, Chiba,Japan,278-8510"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University of Science,Noda, Chiba,Japan,278-8510","institution_ids":["https://openalex.org/I161296585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112302385","display_name":"Hidefumi Ohmura","orcid":null},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hidefumi Ohmura","raw_affiliation_strings":["Tokyo University of Science,Noda, Chiba,Japan,278-8510"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University of Science,Noda, Chiba,Japan,278-8510","institution_ids":["https://openalex.org/I161296585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108640197","display_name":"Kouichi Katsurada","orcid":null},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kouichi Katsurada","raw_affiliation_strings":["Tokyo University of Science,Noda, Chiba,Japan,278-8510"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo University of Science,Noda, Chiba,Japan,278-8510","institution_ids":["https://openalex.org/I161296585"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161296585"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29353963,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9939000010490417,"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":0.9939000010490417,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.974399983882904,"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/computer-science","display_name":"Computer science","score":0.6653867959976196},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5171201229095459},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42627447843551636},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37308117747306824}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6653867959976196},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5171201229095459},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42627447843551636},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37308117747306824}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc63619.2025.10849075","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc63619.2025.10849075","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1965255698","https://openalex.org/W1986593580","https://openalex.org/W2013317861","https://openalex.org/W2107860279","https://openalex.org/W2508425411","https://openalex.org/W2573340898","https://openalex.org/W2747070883","https://openalex.org/W2752782242","https://openalex.org/W2941048526","https://openalex.org/W3086311074","https://openalex.org/W3095458540","https://openalex.org/W3097777922","https://openalex.org/W3159506701","https://openalex.org/W3197843258","https://openalex.org/W4372341338","https://openalex.org/W4375868790","https://openalex.org/W4385823362","https://openalex.org/W6602935006","https://openalex.org/W6767245602","https://openalex.org/W6779143599","https://openalex.org/W6783867762"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Previous":[0],"research":[1],"on":[2],"articulatory":[3,50,90,127],"synthesis":[4,12,25],"has":[5],"partially":[6],"implemented":[7],"and":[8,55,76,114],"verified":[9],"the":[10,16,31,43,61,97,123,133,143],"speech":[11,24,75,118,136],"systems":[13],"that":[14,27,39,70,88],"mimic":[15],"human":[17,32],"vocalization":[18,33],"process.":[19],"This":[20],"study":[21],"proposes":[22],"a":[23,37,80],"system":[26],"more":[28],"faithfully":[29],"replicates":[30],"process":[34],"by":[35],"constructing":[36],"model":[38],"generates":[40],"speeches":[41,101],"from":[42],"international":[44],"phonetic":[45],"alphabet":[46],"(IPA)":[47],"sequence":[48],"through":[49],"movement":[51,91,128],"data.":[52],"For":[53],"training":[54],"evaluating":[56],"this":[57],"model,":[58],"we":[59],"used":[60],"ATR":[62],"phoneme-balanced":[63],"503":[64],"sentence":[65],"electromagnetic":[66],"articulography":[67],"(EMA)":[68],"database":[69],"contains":[71],"pair":[72],"data":[73,78,92,129],"of":[74,79,99,117,125,135],"EMA":[77,144],"male":[81],"Japanese":[82],"speaker.":[83],"The":[84],"experimental":[85],"results":[86],"showed":[87],"using":[89,126],"as":[93,106],"intermediate":[94],"information":[95],"improved":[96],"quality":[98,119],"synthesized":[100],"regarding":[102],"objective":[103],"scores":[104],"such":[105],"melcepstral":[107],"distortion":[108],"(MCD),":[109],"phoneme":[110],"error":[111],"rate":[112],"(PER),":[113],"perceptual":[115],"evaluation":[116],"(PESQ).":[120],"In":[121],"particular,":[122],"effectiveness":[124],"was":[130],"confirmed":[131],"in":[132,142],"case":[134],"where":[137],"articulation":[138],"points":[139],"were":[140],"included":[141],"database.":[145]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}