{"id":"https://openalex.org/W4406266642","doi":"https://doi.org/10.1109/gcce62371.2024.10760681","title":"End-to-End Neural Formant Synthesis Using Low-Dimensional Acoustic Parameters","display_name":"End-to-End Neural Formant Synthesis Using Low-Dimensional Acoustic Parameters","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4406266642","doi":"https://doi.org/10.1109/gcce62371.2024.10760681"},"language":"en","primary_location":{"id":"doi:10.1109/gcce62371.2024.10760681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","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":null,"display_name":"Sumiharu Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sumiharu Kobayashi","raw_affiliation_strings":["Yamagata University,Graduate School of Science and Engineering,Yonezawa,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University,Graduate School of Science and Engineering,Yonezawa,Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112342909","display_name":"Tetsuo Kosaka","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tetsuo Kosaka","raw_affiliation_strings":["Yamagata University,Graduate School of Sci. & Eng.,Yonezawa,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University,Graduate School of Sci. & Eng.,Yonezawa,Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Tohoku University,Graduate School of Engineering,Sendai,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tohoku University,Graduate School of Engineering,Sendai,Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9324,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76949153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"820","last_page":"823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13126","display_name":"Scientific Research and Discoveries","score":0.7405999898910522,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13126","display_name":"Scientific Research and Discoveries","score":0.7405999898910522,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.6735000014305115,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.6306999921798706,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/formant","display_name":"Formant","score":0.7546438574790955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5177627801895142},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4843834340572357},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4635659158229828},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.41098207235336304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.179448664188385},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11403855681419373}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7546438574790955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5177627801895142},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4843834340572357},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4635659158229828},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.41098207235336304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.179448664188385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11403855681419373},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce62371.2024.10760681","is_oa":false,"landing_page_url":"https://doi.org/10.1109/gcce62371.2024.10760681","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 13th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2471520273","https://openalex.org/W2902070858","https://openalex.org/W3197273793","https://openalex.org/W4225956675","https://openalex.org/W4372262501","https://openalex.org/W4385823333"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W37481168","https://openalex.org/W1990629684"],"abstract_inverted_index":{"Neural":[0,48],"vocoders":[1],"can":[2,28],"synthesize":[3],"high-quality":[4,53],"speech":[5,35,54,96],"waveforms":[6,55],"from":[7,60],"acoustic":[8,15,32,58],"features,":[9],"but":[10],"they":[11],"cannot":[12],"control":[13],"by":[14],"parameters,":[16,33],"such":[17],"as":[18,85,87],"F0and":[19],"formant":[20],"frequencies.":[21],"Although":[22],"analysis-synthesis":[23],"based":[24],"on":[25],"signal":[26],"processing":[27],"be":[29],"controlled":[30],"using":[31],"its":[34],"quality":[36,74,97],"is":[37],"inferior":[38],"to":[39],"that":[40,80],"of":[41,95],"neural":[42],"vocoders.":[43],"This":[44],"paper":[45],"proposes":[46],"End-to-End":[47],"Formant":[49],"Synthesis":[50],"for":[51],"generating":[52],"with":[56,67],"controllable":[57],"parameters":[59],"low-dimensional":[61],"representations.":[62],"We":[63],"compared":[64],"three":[65],"models":[66],"different":[68],"structures,":[69],"and":[70,75,98],"investigated":[71],"their":[72],"synthesis":[73],"controllability.":[76,99],"Experimental":[77],"results":[78],"showed":[79],"the":[81],"proposed":[82],"method":[83],"performed":[84],"well":[86],"or":[88],"better":[89],"than":[90],"conventional":[91],"methods":[92],"in":[93],"terms":[94]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}