{"id":"https://openalex.org/W4391021389","doi":"https://doi.org/10.1109/asru57964.2023.10389659","title":"Bisinger: Bilingual Singing Voice Synthesis","display_name":"Bisinger: Bilingual Singing Voice Synthesis","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4391021389","doi":"https://doi.org/10.1109/asru57964.2023.10389659"},"language":"en","primary_location":{"id":"doi:10.1109/asru57964.2023.10389659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5102949163","display_name":"Huali Zhou","orcid":"https://orcid.org/0009-0008-6253-7379"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huali Zhou","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","School of Computer Science, Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768194","display_name":"Yueqian Lin","orcid":"https://orcid.org/0000-0003-1473-8981"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueqian Lin","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033120372","display_name":"Yao Shi","orcid":"https://orcid.org/0000-0003-0068-4804"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Shi","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614090","display_name":"Peng Sun","orcid":"https://orcid.org/0000-0002-1227-5533"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Sun","raw_affiliation_strings":["Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Duke Kunshan University,Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems,Kunshan,China","institution_ids":["https://openalex.org/I4210159968"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100351449","display_name":"Ming Li","orcid":"https://orcid.org/0000-0002-6406-1983"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Li","raw_affiliation_strings":["Wuhan University,School of Computer Science,Wuhan,China","School of Computer Science, Wuhan University, Wuhan, China","Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Duke Kunshan University, Kunshan, China","institution_ids":["https://openalex.org/I4210159968"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102949163"],"corresponding_institution_ids":["https://openalex.org/I37461747","https://openalex.org/I4210159968"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59618914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.9161171913146973},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7790533900260925},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6576389074325562},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5482044219970703},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.49566352367401123},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4897008240222931},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47180405259132385},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.46380308270454407},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3745473623275757},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27125000953674316},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.13687124848365784},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09282103180885315},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07635113596916199}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.9161171913146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7790533900260925},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6576389074325562},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5482044219970703},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.49566352367401123},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4897008240222931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47180405259132385},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.46380308270454407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3745473623275757},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27125000953674316},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.13687124848365784},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09282103180885315},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07635113596916199},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru57964.2023.10389659","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru57964.2023.10389659","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2066598518","https://openalex.org/W2067709094","https://openalex.org/W2124097505","https://openalex.org/W2471520273","https://openalex.org/W2516406502","https://openalex.org/W2747874407","https://openalex.org/W2901389167","https://openalex.org/W2936832667","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2964002616","https://openalex.org/W2972473628","https://openalex.org/W2990124956","https://openalex.org/W3081279708","https://openalex.org/W3092028330","https://openalex.org/W3095012670","https://openalex.org/W3096894480","https://openalex.org/W3097514409","https://openalex.org/W3133525064","https://openalex.org/W3158762648","https://openalex.org/W3207340675","https://openalex.org/W4280572880","https://openalex.org/W4285405598","https://openalex.org/W4310922606","https://openalex.org/W4372260026","https://openalex.org/W6678318511","https://openalex.org/W6713876852","https://openalex.org/W6757094361","https://openalex.org/W6763832098","https://openalex.org/W6770838157","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6847084890","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W127416991"],"abstract_inverted_index":{"Although":[0],"Singing":[1],"Voice":[2],"Synthesis":[3],"(SVS)":[4],"has":[5],"made":[6],"great":[7],"strides":[8],"with":[9,73,81,117],"Text-to-Speech":[10],"(TTS)":[11],"techniques,":[12],"multilingual":[13],"singing":[14,65,79,83,90],"voice":[15,84],"modeling":[16],"remains":[17],"relatively":[18],"unexplored.":[19],"This":[20],"paper":[21],"presents":[22],"BiSinger,":[23],"a":[24,58,114],"bilingual":[25,89,99],"pop":[26],"SVS":[27,124],"system":[28],"for":[29],"English":[30,64,121],"and":[31,41,47,63,108,122],"Chinese":[32,46,62,127],"Mandarin.":[33],"Current":[34],"systems":[35],"require":[36],"separate":[37],"models":[38],"per":[39],"language":[40],"cannot":[42],"accurately":[43],"represent":[44],"both":[45],"English,":[48],"hindering":[49],"code-switch":[50,123],"SVS.":[51],"To":[52],"address":[53],"this":[54],"gap,":[55],"we":[56],"design":[57],"shared":[59],"representation":[60,107],"between":[61],"voices,":[66],"achieved":[67],"by":[68],"using":[69],"the":[70,95],"CMU":[71],"dictionary":[72],"mapping":[74],"rules.":[75],"We":[76],"fuse":[77],"monolingual":[78],"datasets":[80,112],"open-source":[82],"conversion":[85],"techniques":[86],"to":[87],"generate":[88],"voices":[91],"while":[92,125],"also":[93],"exploring":[94],"potential":[96],"use":[97],"of":[98,110],"speech":[100],"data.":[101],"Experiments":[102],"affirm":[103],"that":[104],"our":[105],"language-independent":[106],"incorporation":[109],"related":[111],"enable":[113],"single":[115],"model":[116],"enhanced":[118],"performance":[119],"in":[120],"maintaining":[126],"song":[128],"performance.":[129],"Audio":[130],"samples":[131],"are":[132],"available":[133],"at":[134],"https://bisinger-svs.github.io.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
