{"id":"https://openalex.org/W2128123288","doi":"https://doi.org/10.1109/icme.2010.5582961","title":"Voice conversion: From spoken vowels to singing vowels","display_name":"Voice conversion: From spoken vowels to singing vowels","publication_year":2010,"publication_date":"2010-07-01","ids":{"openalex":"https://openalex.org/W2128123288","doi":"https://doi.org/10.1109/icme.2010.5582961","mag":"2128123288"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2010.5582961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5582961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","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/A5082461870","display_name":"Tin L New","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Tin L New","raw_affiliation_strings":["Agency for Science Technology and Research, Singapore, SG"],"affiliations":[{"raw_affiliation_string":"Agency for Science Technology and Research, Singapore, SG","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021872761","display_name":"Minghui Dong","orcid":"https://orcid.org/0000-0001-6543-2929"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Minghui Dong","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Singapore","Institute of Infocomm Research-Agency for Science, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute of Infocomm Research-Agency for Science, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059762329","display_name":"Paul Chan","orcid":"https://orcid.org/0000-0002-5604-4905"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Paul Chan","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442245","display_name":"Xi Wang","orcid":"https://orcid.org/0009-0008-2264-3863"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xi Wang","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Singapore","Institute of Infocomm Research-Agency for Science, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute of Infocomm Research-Agency for Science, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute for Infocomm Research (I2R), Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (I2R), Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5082461870"],"corresponding_institution_ids":["https://openalex.org/I115228651"],"apc_list":null,"apc_paid":null,"fwci":0.9021,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.81203276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1421","last_page":"1426"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9997000098228455,"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":0.9993000030517578,"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/singing","display_name":"Singing","score":0.9079591035842896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7543214559555054},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6981596350669861},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.5943328142166138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5240157842636108},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.4221600592136383},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.39708489179611206},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06748166680335999}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9079591035842896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7543214559555054},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6981596350669861},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.5943328142166138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5240157842636108},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.4221600592136383},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.39708489179611206},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06748166680335999}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme.2010.5582961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2010.5582961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5600000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W31448757","https://openalex.org/W87468674","https://openalex.org/W1583154192","https://openalex.org/W2048752878","https://openalex.org/W2049686551","https://openalex.org/W2064005251","https://openalex.org/W2072389495","https://openalex.org/W2097873655","https://openalex.org/W2102870814","https://openalex.org/W2150933458","https://openalex.org/W2156142001","https://openalex.org/W2244925781","https://openalex.org/W4299030323","https://openalex.org/W6601203246","https://openalex.org/W6601280771","https://openalex.org/W6603621184","https://openalex.org/W6844210595","https://openalex.org/W6902064130"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W1995619422","https://openalex.org/W4390926392","https://openalex.org/W2940658159","https://openalex.org/W2741358513","https://openalex.org/W2078307554","https://openalex.org/W2011208577","https://openalex.org/W2416886761"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,154],"voice":[4,58],"conversion":[5],"system":[6,25,30,121,143],"that":[7,140],"converts":[8],"spoken":[9,18,148],"vowels":[10,13,19,149,152],"into":[11,150],"singing":[12,27,45,57,86,118,132,151,161],"is":[14,49,68,122,144],"proposed.":[15],"Given":[16],"the":[17,24,32,74,77,88,106,125,141,159],"and":[20,40,59,101,130],"their":[21],"musical":[22,79],"score,":[23],"generates":[26],"vowels.":[28,136],"The":[29,94,120,137],"modifies":[31],"speech":[33,67,83,116,129],"parameters":[34],"of":[35,63,66,76],"Fundamental":[36],"frequency":[37],"(F0),":[38],"duration":[39],"spectral":[41,98],"properties":[42],"to":[43,73,85,114,117,146,158],"produce":[44],"voice.":[46,162],"F0":[47,52],"contour":[48],"obtained":[50],"using":[51,135],"fluctuation":[53],"information":[54],"from":[55],"training":[56],"music":[60],"score.":[61],"Duration":[62],"each":[64],"vowel":[65],"stretched":[69],"or":[70],"shortened":[71],"according":[72],"length":[75],"corresponding":[78],"note.":[80],"To":[81],"transform":[82,115],"spectrum":[84,87],"following":[89],"two":[90],"approaches":[91],"are":[92],"employed.":[93],"first":[95],"method":[96,113],"employs":[97],"mean":[99],"shifting":[100],"variance":[102],"scaling":[103],"method.":[104],"And,":[105],"second":[107],"approach":[108],"uses":[109],"weighted":[110],"linear":[111],"transformation":[112],"spectrum.":[119],"tested":[123],"on":[124],"database":[126],"including":[127],"75":[128],"30":[131],"voices":[133],"sung":[134],"results":[138],"show":[139],"proposed":[142],"able":[145],"convert":[147],"with":[153],"quality":[155],"very":[156],"close":[157],"target":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}