{"id":"https://openalex.org/W2891535489","doi":"https://doi.org/10.1109/icassp.2018.8461569","title":"Vae-Space: Deep Generative Model of Voice Fundamental Frequency Contours","display_name":"Vae-Space: Deep Generative Model of Voice Fundamental Frequency Contours","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891535489","doi":"https://doi.org/10.1109/icassp.2018.8461569","mag":"2891535489"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5106710403","display_name":"Kou Tanaka","orcid":"https://orcid.org/0009-0003-7107-607X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kou Tanaka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085461768","display_name":"Kazuho Morikawa","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuho Morikawa","raw_affiliation_strings":["Graduate School of informatics, Nagoya University, japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of informatics, Nagoya University, japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5659,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71733567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"5779","last_page":"5783"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9958000183105469,"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/T11309","display_name":"Music and Audio Processing","score":0.9940999746322632,"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":0.6490300893783569},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6303080916404724},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6239212155342102},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5977420210838318},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5711000561714172},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.5575178265571594},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5537899732589722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5106161236763},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4731805622577667},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4544111490249634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37017449736595154},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.13806724548339844},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07937327027320862},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07045108079910278}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6490300893783569},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6303080916404724},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6239212155342102},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5977420210838318},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5711000561714172},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.5575178265571594},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5537899732589722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5106161236763},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4731805622577667},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4544111490249634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37017449736595154},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.13806724548339844},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07937327027320862},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07045108079910278}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1959608418","https://openalex.org/W1965255698","https://openalex.org/W2049686551","https://openalex.org/W2064675550","https://openalex.org/W2108501770","https://openalex.org/W2157331557","https://openalex.org/W2166472876","https://openalex.org/W2170667735","https://openalex.org/W2403321691","https://openalex.org/W2423557781","https://openalex.org/W2527569769","https://openalex.org/W2747744257","https://openalex.org/W2951326654","https://openalex.org/W2963223306","https://openalex.org/W2963636093","https://openalex.org/W3177493096","https://openalex.org/W4295177495","https://openalex.org/W6637242042","https://openalex.org/W6713575812","https://openalex.org/W6727654133","https://openalex.org/W6798415246"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W2387733758","https://openalex.org/W2376664795","https://openalex.org/W4379055549","https://openalex.org/W2963658876","https://openalex.org/W2885916054"],"abstract_inverted_index":{"Modeling":[0],"the":[1,53,61,68],"speech":[2,32,87],"generation":[3],"process":[4],"can":[5,81],"provide":[6],"flexible":[7],"and":[8,33,57,79,88],"interpretable":[9],"ways":[10],"to":[11,47],"generate":[12],"intended":[13],"synthetic":[14],"speech.":[15],"In":[16],"this":[17,42],"paper,":[18],"we":[19,39],"present":[20],"a":[21,64],"deep":[22],"generative":[23,37],"model":[24,38,66],"of":[25,30,55,60,71,84],"fundamental":[26],"frequency":[27],"(F0)":[28],"contours":[29],"normal":[31,86],"singing":[34,89],"voices.":[35],"The":[36],"propose":[40],"in":[41],"paper":[43],"1)":[44],"is":[45],"able":[46],"accurately":[48],"decompose":[49],"an":[50,76],"F0contour":[51],"into":[52],"sum":[54],"phrase":[56],"accent":[58],"components":[59],"Fujisaki":[62],"model,":[63],"mathematical":[65],"describing":[67],"control":[69],"mechanism":[70],"vocal":[72],"fold":[73],"vibration,":[74],"without":[75],"iterative":[77],"algorithm,":[78],"2)":[80],"represent/generate":[82],"F0contours":[83],"both":[85],"voices":[90],"reasonably":[91],"well.":[92]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}