{"id":"https://openalex.org/W4405710101","doi":"https://doi.org/10.1109/iscslp63861.2024.10799952","title":"A Systematic Exploration of Joint-Training for Singing Voice Synthesis","display_name":"A Systematic Exploration of Joint-Training for Singing Voice Synthesis","publication_year":2024,"publication_date":"2024-11-07","ids":{"openalex":"https://openalex.org/W4405710101","doi":"https://doi.org/10.1109/iscslp63861.2024.10799952"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp63861.2024.10799952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10799952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5101011479","display_name":"Yuning Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuning Wu","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102256715","display_name":"Yifeng Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifeng Yu","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tao Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qian","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":["Renmin University of China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101011479"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.9786,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79961229,"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":"289","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.8259999752044678,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.8259999752044678,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7770000100135803,"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":0.7414664030075073},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.7033039331436157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6775475740432739},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.605923593044281},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5604563355445862},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15275877714157104},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11366823315620422}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7414664030075073},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.7033039331436157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775475740432739},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.605923593044281},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5604563355445862},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15275877714157104},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11366823315620422},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"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/iscslp63861.2024.10799952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp63861.2024.10799952","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W2030149476","https://openalex.org/W2471520273","https://openalex.org/W2515336442","https://openalex.org/W2889244839","https://openalex.org/W2940405045","https://openalex.org/W2962780374","https://openalex.org/W3015499232","https://openalex.org/W3081279708","https://openalex.org/W3097514409","https://openalex.org/W3133525064","https://openalex.org/W3158762648","https://openalex.org/W3160427568","https://openalex.org/W3161782335","https://openalex.org/W3163031268","https://openalex.org/W3187128306","https://openalex.org/W3196760057","https://openalex.org/W3206191467","https://openalex.org/W3207340675","https://openalex.org/W3212754542","https://openalex.org/W4210682690","https://openalex.org/W4224612669","https://openalex.org/W4225463329","https://openalex.org/W4280572880","https://openalex.org/W4285345683","https://openalex.org/W4296068763","https://openalex.org/W4296068811","https://openalex.org/W4297841605","https://openalex.org/W4312625753","https://openalex.org/W4402111425","https://openalex.org/W6678318511","https://openalex.org/W6783382068","https://openalex.org/W6783867762","https://openalex.org/W6796464841","https://openalex.org/W6802659129","https://openalex.org/W6809850657"],"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":{"There":[0],"has":[1,61,95],"been":[2,62,97],"a":[3,45,58,77,105,120],"growing":[4],"interest":[5],"in":[6,64,92],"using":[7],"end-to-end":[8],"acoustic":[9,27,36,74,117],"models":[10,18],"for":[11,83,122],"singing":[12],"voice":[13],"synthesis":[14],"(SVS).":[15],"Typically,":[16],"these":[17,81],"require":[19],"an":[20,116],"additional":[21],"vocoder":[22,40,121],"to":[23,54,110],"transform":[24],"the":[25,30,35,39,50,112,148,151],"generated":[26],"features":[28,75],"into":[29,108],"final":[31],"waveform.":[32],"However,":[33],"since":[34],"model":[37,118],"and":[38,119,129],"are":[41],"not":[42,96],"jointly":[43],"optimized,":[44],"gap":[46],"can":[47],"exist":[48],"between":[49],"two":[51],"models,":[52],"leading":[53],"suboptimal":[55],"performance.":[56],"Although":[57],"similar":[59],"problem":[60],"addressed":[63],"text-to-speech":[65],"(TTS)":[66],"systems":[67,94],"through":[68],"joint":[69,90,113],"training":[70,91,114],"or":[71],"by":[72],"replacing":[73],"with":[76],"latent":[78],"representation,":[79],"adopting":[80],"approaches":[82],"SVS":[84,93],"is":[85],"challenging.":[86],"The":[87],"improvement":[88],"of":[89,115,150],"thoroughly":[98],"explored.":[99],"In":[100],"this":[101],"paper,":[102],"we":[103],"conduct":[104],"systematic":[106],"investigation":[107],"how":[109],"enhance":[111],"SVS.":[123],"We":[124],"carry":[125],"out":[126],"extensive":[127],"experiments":[128],"demonstrate":[130],"that":[131],"our":[132],"joint-training":[133],"strategy":[134],"outperforms":[135],"base-line":[136],"methods,":[137],"achieving":[138],"more":[139],"stable":[140],"performance":[141],"across":[142],"different":[143],"datasets":[144],"while":[145],"also":[146],"increasing":[147],"interpretability":[149],"entire":[152],"framework.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
