{"id":"https://openalex.org/W4312468441","doi":"https://doi.org/10.1109/mmsp55362.2022.9948936","title":"Singing Voice Synthesis with Vibrato Modeling and Latent Energy Representation","display_name":"Singing Voice Synthesis with Vibrato Modeling and Latent Energy Representation","publication_year":2022,"publication_date":"2022-09-26","ids":{"openalex":"https://openalex.org/W4312468441","doi":"https://doi.org/10.1109/mmsp55362.2022.9948936"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp55362.2022.9948936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9948936","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","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/A5006593952","display_name":"Yingjie Song","orcid":"https://orcid.org/0000-0002-2331-2248"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yingjie Song","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University,Shanghai,China","School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University,Shanghai,China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023025722","display_name":"Wei Song","orcid":"https://orcid.org/0000-0003-0649-8850"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Song","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100441569","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0002-1492-8286"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057050780","display_name":"Zhengchen Zhang","orcid":"https://orcid.org/0009-0005-4225-3537"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengchen Zhang","raw_affiliation_strings":["JD AI Research,Beijing,China","JD AI Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"JD AI Research,Beijing,China","institution_ids":["https://openalex.org/I4210103986"]},{"raw_affiliation_string":"JD AI Research, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023724461","display_name":"Dan Zeng","orcid":"https://orcid.org/0000-0003-1300-1769"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Zeng","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University,Shanghai,China","School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University,Shanghai,China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382312","display_name":"Zhi Liu","orcid":"https://orcid.org/0000-0002-8428-1131"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Liu","raw_affiliation_strings":["School of Communication and Information Engineering, Shanghai University,Shanghai,China","School of Communication and Information Engineering, Shanghai University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University,Shanghai,China","institution_ids":["https://openalex.org/I113940042"]},{"raw_affiliation_string":"School of Communication and Information Engineering, Shanghai University, Shanghai, China","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067762815","display_name":"Yang Yu","orcid":"https://orcid.org/0009-0007-7047-1501"},"institutions":[{"id":"https://openalex.org/I350617331","display_name":"Shanghai Conservatory of Music","ror":"https://ror.org/012f6xc93","country_code":"CN","type":"education","lineage":["https://openalex.org/I350617331"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["Shanghai Conservatory of Music,Shanghai,China","Shanghai Conservatory of Music, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Conservatory of Music,Shanghai,China","institution_ids":["https://openalex.org/I350617331"]},{"raw_affiliation_string":"Shanghai Conservatory of Music, Shanghai, China","institution_ids":["https://openalex.org/I350617331"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5006593952"],"corresponding_institution_ids":["https://openalex.org/I113940042"],"apc_list":null,"apc_paid":null,"fwci":0.4175,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59495415,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9997000098228455,"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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/vibrato","display_name":"Vibrato","score":0.9788838028907776},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8899531364440918},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713230311870575},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.6866280436515808},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.653546154499054},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46407392621040344},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2896956205368042}],"concepts":[{"id":"https://openalex.org/C2781100714","wikidata":"https://www.wikidata.org/wiki/Q377435","display_name":"Vibrato","level":3,"score":0.9788838028907776},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8899531364440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713230311870575},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6866280436515808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.653546154499054},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46407392621040344},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2896956205368042},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp55362.2022.9948936","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp55362.2022.9948936","pdf_url":null,"source":{"id":"https://openalex.org/S4363605768","display_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 24th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W57034108","https://openalex.org/W241723195","https://openalex.org/W1522301498","https://openalex.org/W1836465849","https://openalex.org/W1904711963","https://openalex.org/W1978534304","https://openalex.org/W1995078524","https://openalex.org/W2067709094","https://openalex.org/W2067968869","https://openalex.org/W2108967524","https://openalex.org/W2123706540","https://openalex.org/W2128980425","https://openalex.org/W2256439705","https://openalex.org/W2317455283","https://openalex.org/W2408435475","https://openalex.org/W2471520273","https://openalex.org/W2575591213","https://openalex.org/W2792643794","https://openalex.org/W2940405045","https://openalex.org/W2963609956","https://openalex.org/W2972812066","https://openalex.org/W2972910332","https://openalex.org/W2984106626","https://openalex.org/W2989708046","https://openalex.org/W3015499232","https://openalex.org/W3015844196","https://openalex.org/W3016243847","https://openalex.org/W3026010363","https://openalex.org/W3033411150","https://openalex.org/W3081279708","https://openalex.org/W3095948607","https://openalex.org/W3114636111","https://openalex.org/W3133525064","https://openalex.org/W3135864795","https://openalex.org/W3160427568","https://openalex.org/W3161959914","https://openalex.org/W3163031268","https://openalex.org/W4385245566","https://openalex.org/W6602348752","https://openalex.org/W6631190155","https://openalex.org/W6638667902","https://openalex.org/W6692416122","https://openalex.org/W6713876852","https://openalex.org/W6739901393","https://openalex.org/W6749029207","https://openalex.org/W6770046961","https://openalex.org/W6778823374"],"related_works":["https://openalex.org/W2373880408","https://openalex.org/W405661683","https://openalex.org/W2532856746","https://openalex.org/W238390473","https://openalex.org/W2119168266","https://openalex.org/W2978145617","https://openalex.org/W4230480656","https://openalex.org/W2108382268","https://openalex.org/W3149963859","https://openalex.org/W2097873655"],"abstract_inverted_index":{"This":[0],"paper":[1,45],"proposes":[2],"an":[3],"expressive":[4,128],"singing":[5,73,87,129,156],"voice":[6,130],"synthesis":[7],"system":[8],"by":[9],"introducing":[10],"explicit":[11],"vibrato":[12,39,59,66,83,93,100,143],"modeling":[13,144],"and":[14,53,67,145],"latent":[15,121,147],"energy":[16,122,148],"representation.":[17],"Vibrato":[18],"is":[19,41,78,125],"essential":[20],"to":[21,28,46,97],"the":[22,29,48,58,62,72,99,104,115,135,142,146,153,164],"naturalness":[23],"of":[24,32,65,107,117,155],"synthesized":[25],"sound,":[26],"due":[27],"inherent":[30],"characteristics":[31],"human":[33],"singing.":[34,118],"Hence,":[35],"a":[36,91],"deep":[37],"learning-based":[38],"model":[40],"introduced":[42],"in":[43,55,85,163],"this":[44],"control":[47],"vibrato's":[49],"likeliness,":[50],"rate,":[51],"depth":[52],"phase":[54],"singing,":[56],"where":[57],"likeliness":[60,84,94,101],"represents":[61],"existence":[63],"probability":[64],"it":[68],"would":[69],"help":[70],"improve":[71,114,152],"voice's":[74],"naturalness.":[75],"Actually,":[76],"there":[77],"no":[79],"annotated":[80],"label":[81,98],"about":[82],"existing":[86],"corpus.":[88],"We":[89],"adopt":[90],"novel":[92],"labeling":[95],"method":[96],"automatically.":[102],"Meanwhile,":[103],"power":[105],"spectrogram":[106],"audio":[108,159],"contains":[109],"rich":[110],"information":[111],"that":[112,140],"can":[113],"expressiveness":[116,154],"An":[119],"autoencoder-based":[120],"bottleneck":[123],"feature":[124],"proposed":[126],"for":[127],"synthesis.":[131],"Experimental":[132],"results":[133],"on":[134],"open":[136],"dataset":[137],"NUS48E":[138],"show":[139],"both":[141],"representation":[149],"could":[150],"significantly":[151],"voice.":[157],"The":[158],"samples":[160],"are":[161],"shown":[162],"demo":[165],"website":[166],"<sup":[167,170],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[168,171],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[169,172],"https://mango321321.github.io/ExpressiveSing/.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
