{"id":"https://openalex.org/W4296069360","doi":"https://doi.org/10.21437/interspeech.2022-10585","title":"Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information","display_name":"Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296069360","doi":"https://doi.org/10.21437/interspeech.2022-10585"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10585","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10585","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5062968337","display_name":"Shaohuan Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohuan Zhou","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103014224","display_name":"Shun Lei","orcid":"https://orcid.org/0000-0003-3597-3913"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shun Lei","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071912411","display_name":"Weiya You","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiya You","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043757154","display_name":"Deyi Tuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deyi Tuo","raw_affiliation_strings":["Huya Inc., Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc., Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084481119","display_name":"Yuren You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuren You","raw_affiliation_strings":["Huya Inc., Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huya Inc., Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["XVerse Inc., Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"XVerse Inc., Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","The Chinese University of Hong Kong, Hong Kong SAR, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3374,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5489749,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4292","last_page":"4296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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":0.9937999844551086,"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":0.7636361122131348},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7099137306213379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4852747619152069},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3908717632293701},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34737300872802734},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08528399467468262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636361122131348},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7099137306213379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4852747619152069},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3908717632293701},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34737300872802734},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08528399467468262},{"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:10.21437/interspeech.2022-10585","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10585","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2603945996","display_name":null,"funder_award_id":"62076144","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335869","display_name":"National Social Science Fund of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2921576841","https://openalex.org/W3015499232","https://openalex.org/W3016137096","https://openalex.org/W3033411150","https://openalex.org/W3081279708","https://openalex.org/W3097152652","https://openalex.org/W3133525064","https://openalex.org/W3158374895","https://openalex.org/W4287121924","https://openalex.org/W4287672314","https://openalex.org/W4287761884","https://openalex.org/W4296068763","https://openalex.org/W4298017177","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,94],"end-to-end":[4],"high-quality":[5],"singing":[6,29,47,117,154],"voice":[7,48,101,155],"synthesis":[8],"(SVS)":[9],"system":[10,84,151],"that":[11,110,147],"uses":[12],"bidirectional":[13],"encoder":[14],"representation":[15,59,72],"from":[16,51,63],"Transformers":[17],"(BERT)":[18],"derived":[19],"semantic":[20],"embeddings":[21],"to":[22,69,97,113,123,133,137],"improve":[23],"the":[24,27,32,52,70,78,99,104,114,121,125,128,135,148],"expressiveness":[25,115],"of":[26,35,60,77,107,116],"synthesized":[28,100],"voice.Based":[30],"on":[31],"main":[33],"architecture":[34],"recently":[36],"proposed":[37,149],"VISinger,":[38],"we":[39,56,91],"put":[40],"forward":[41],"several":[42],"specific":[43],"designs":[44],"for":[45],"expressive":[46,87],"synthesis.First,":[49],"different":[50],"previous":[53],"SVS":[54,83,150],"models,":[55],"use":[57],"text":[58],"lyrics":[61],"extracted":[62],"pre-trained":[64],"BERT":[65],"as":[66],"additional":[67],"input":[68],"model.The":[71],"contains":[73],"information":[74],"about":[75],"semantics":[76],"lyrics,":[79],"which":[80],"could":[81],"help":[82],"produce":[85,153],"more":[86],"and":[88,102,142],"natural":[89],"voice.Second,":[90],"further":[92],"introduce":[93],"energy":[95,108],"predictor":[96,130],"stabilize":[98],"model":[103],"wider":[105],"range":[106],"variations":[109],"also":[111],"contribute":[112],"voice.Last":[118],"but":[119],"not":[120],"least,":[122],"attenuate":[124],"off-key":[126],"issues,":[127],"pitch":[129,139],"is":[131],"re-designed":[132],"predict":[134],"real":[136],"note":[138],"ratio.Both":[140],"objective":[141],"subjective":[143],"experimental":[144],"results":[145],"indicate":[146],"can":[152],"with":[156],"higher-quality":[157],"outperforming":[158],"VISinger":[159],"1":[160],".":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}