{"id":"https://openalex.org/W4409348103","doi":"https://doi.org/10.1609/aaai.v39i22.34571","title":"TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching","display_name":"TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409348103","doi":"https://doi.org/10.1609/aaai.v39i22.34571"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i22.34571","doi":"https://doi.org/10.1609/aaai.v39i22.34571","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i22.34571","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34571/36726","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34571/36726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104320351","display_name":"Wenxiang Guo","orcid":"https://orcid.org/0009-0006-7997-4140","observed_orcids":["https://orcid.org/0009-0006-7997-4140"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxiang Guo","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103228451","display_name":"Changhao Pan","orcid":"https://orcid.org/0009-0004-6023-1764","observed_orcids":["https://orcid.org/0009-0004-6023-1764"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhao Pan","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002111548","display_name":"Rongjie Huang","orcid":"https://orcid.org/0009-0004-2827-9485","observed_orcids":["https://orcid.org/0009-0004-2827-9485"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongjie Huang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041383884","display_name":"Lihua Tang","orcid":"https://orcid.org/0000-0001-9031-4190","observed_orcids":["https://orcid.org/0000-0001-9031-4190"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Tang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345532","display_name":"Ruiqi Li","orcid":"https://orcid.org/0000-0002-3290-9476","observed_orcids":["https://orcid.org/0000-0002-3290-9476"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Li","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiqing Hong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqing Hong","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068548095","display_name":"Yongqi Wang","orcid":"https://orcid.org/0000-0003-1292-0384","observed_orcids":["https://orcid.org/0000-0003-1292-0384"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongqi Wang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384","observed_orcids":["https://orcid.org/0000-0001-6121-0384","https://orcid.org/0000-0002-6651-1802"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":9.4825,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.98345749,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"39","issue":"22","first_page":"23978","last_page":"23986"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8359000086784363,"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":0.8359000086784363,"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":0.07199999690055847,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.0697999969124794,"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/singing-voice-synthesis","display_name":"singing voice synthesis","score":0.9990000128746033},{"id":"https://openalex.org/keywords/flow-matching","display_name":"flow matching","score":0.8859999775886536},{"id":"https://openalex.org/keywords/multilingual-speech-synthesis","display_name":"multilingual speech synthesis","score":0.8309999704360962},{"id":"https://openalex.org/keywords/intensity-control","display_name":"intensity control","score":0.4659999907016754},{"id":"https://openalex.org/keywords/mixed-voices","display_name":"mixed voices","score":0.8849999904632568},{"id":"https://openalex.org/keywords/falsetto","display_name":"falsetto","score":0.9980000257492065},{"id":"https://openalex.org/keywords/breathy-voice","display_name":"breathy voice","score":0.9929999709129333}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8632137775421143},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6034218668937683},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5866541862487793},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5106456875801086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5041271448135376},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.38436612486839294},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3350244462490082},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17014318704605103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1614721715450287},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05008348822593689},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v39i22.34571","doi":"https://doi.org/10.1609/aaai.v39i22.34571","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i22.34571","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34571/36726","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2502.12572","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.12572","pdf_url":"https://arxiv.org/pdf/2502.12572","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/34571","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/34571","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2502.12572","doi":"https://doi.org/10.48550/arxiv.2502.12572","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.12572","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i22.34571","doi":"https://doi.org/10.1609/aaai.v39i22.34571","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i22.34571","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34571/36726","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1101031052","display_name":null,"funder_award_id":"U24A20326","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409348103.pdf","grobid_xml":"https://content.openalex.org/works/W4409348103.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4396214748","https://openalex.org/W4403791262","https://openalex.org/W4392971546","https://openalex.org/W4404783513","https://openalex.org/W4415708059","https://openalex.org/W7161564849","https://openalex.org/W4412888141","https://openalex.org/W3081279708","https://openalex.org/W4415799264","https://openalex.org/W4402112011"],"abstract_inverted_index":{"Singing":[0],"voice":[1,50],"synthesis":[2,51],"has":[3],"made":[4],"remarkable":[5],"progress":[6],"in":[7,139],"generating":[8],"natural":[9,112],"and":[10,30,56,130,144],"high-quality":[11],"voices.":[12,40],"However,":[13],"existing":[14,137],"methods":[15,138],"rarely":[16],"provide":[17],"precise":[18],"control":[19,73,116],"over":[20,74,117],"vocal":[21,58,109],"techniques":[22],"such":[23],"as":[24],"intensity,":[25],"mixed":[26],"voice,":[27],"falsetto,":[28],"bubble,":[29],"breathy":[31],"tones,":[32],"thus":[33],"limiting":[34],"the":[35,79,118,128],"expressive":[36,72],"potential":[37],"of":[38,81,132,141],"synthetic":[39,133],"We":[41],"introduce":[42],"TechSinger,":[43],"an":[44],"advanced":[45],"system":[46],"for":[47],"controllable":[48],"singing":[49,68,134],"that":[52,90,124],"supports":[53],"five":[54],"languages":[55],"seven":[57],"techniques.":[59,76],"TechSinger":[60,125],"leverages":[61],"a":[62,86],"flow-matching-based":[63],"generative":[64],"model":[65,89,103],"to":[66,106],"produce":[67],"voices":[69],"with":[70,94],"enhanced":[71],"various":[75],"To":[77],"enhance":[78],"diversity":[80],"training":[82],"data,":[83],"we":[84],"develop":[85],"technique":[87,96,101],"detection":[88],"automatically":[91],"annotates":[92],"datasets":[93],"phoneme-level":[95],"labels.":[97],"Additionally,":[98],"our":[99],"prompt-based":[100],"prediction":[102],"enables":[104],"users":[105],"specify":[107],"desired":[108],"attributes":[110],"through":[111],"language,":[113],"offering":[114],"fine-grained":[115],"synthesized":[119],"singing.":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"significantly":[126],"enhances":[127],"expressiveness":[129],"realism":[131],"voices,":[135],"outperforming":[136],"terms":[140],"audio":[142],"quality":[143],"technique-specific":[145],"control.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-17T09:40:24.721904","created_date":"2025-04-11T00:00:00"}
