{"id":"https://openalex.org/W7148423963","doi":"https://doi.org/10.1109/asru65441.2025.11434730","title":"Robust Training of Singing Voice Synthesis Using Prior and Posterior Uncertainty","display_name":"Robust Training of Singing Voice Synthesis Using Prior and Posterior Uncertainty","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148423963","doi":"https://doi.org/10.1109/asru65441.2025.11434730"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5132752133","display_name":"Yiwen Zhao","orcid":null},"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":true,"raw_author_name":"Yiwen Zhao","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132803092","display_name":"Jiatong Shi","orcid":null},"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":"https://openalex.org/A5113110576","display_name":"Yuxun Tang","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":"Yuxun Tang","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/A5101779022","display_name":"William Chen","orcid":"https://orcid.org/0000-0002-3251-3084"},"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":"William Chen","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132789061","display_name":"Shinji Watanabe","orcid":null},"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":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5132752133"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87564262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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":0.26249998807907104,"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":0.26249998807907104,"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":0.17499999701976776,"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":0.06759999692440033,"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","display_name":"Singing","score":0.7461000084877014},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6017000079154968},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5548999905586243},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5117999911308289},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.5012999773025513},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4323999881744385}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7461000084877014},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217000126838684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6274999976158142},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6017000079154968},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5548999905586243},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5117999911308289},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43320000171661377},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4323999881744385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434730","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434730","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":36,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W2030149476","https://openalex.org/W2107860279","https://openalex.org/W2750787464","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W3003301247","https://openalex.org/W3015338123","https://openalex.org/W3015499232","https://openalex.org/W3016160783","https://openalex.org/W3081279708","https://openalex.org/W3097514409","https://openalex.org/W3158762648","https://openalex.org/W3159302906","https://openalex.org/W3160427568","https://openalex.org/W3183048323","https://openalex.org/W3187128306","https://openalex.org/W3207038517","https://openalex.org/W3207340675","https://openalex.org/W3209059054","https://openalex.org/W4200177005","https://openalex.org/W4225463329","https://openalex.org/W4280572880","https://openalex.org/W4296068763","https://openalex.org/W4312790183","https://openalex.org/W4312986363","https://openalex.org/W4385823416","https://openalex.org/W4401042666","https://openalex.org/W4402112388","https://openalex.org/W4403779097","https://openalex.org/W4403780508","https://openalex.org/W4405710101","https://openalex.org/W4406461437","https://openalex.org/W4406461759","https://openalex.org/W4411119792","https://openalex.org/W4415798227"],"related_works":[],"abstract_inverted_index":{"Singing":[0],"voice":[1],"synthesis":[2],"(SVS)":[3],"has":[4],"seen":[5],"remarkable":[6],"advancements":[7],"in":[8,35,70,76,126],"recent":[9],"years.":[10],"However,":[11],"compared":[12],"to":[13,32,55,80,101,106],"speech":[14],"and":[15,114,118],"general":[16],"audio":[17],"data,":[18],"publicly":[19],"available":[20],"singing":[21,45],"datasets":[22],"remain":[23],"limited.":[24],"In":[25],"practice,":[26],"this":[27],"data":[28,68],"scarcity":[29],"often":[30],"leads":[31],"performance":[33,125],"degradation":[34],"long-tail":[36],"scenarios,":[37],"such":[38],"as":[39],"imbalanced":[40],"pitch":[41],"distributions":[42],"or":[43],"rare":[44],"styles.":[46],"To":[47],"mitigate":[48],"these":[49],"challenges,":[50],"we":[51,65,86],"propose":[52],"uncertainty-based":[53],"optimization":[54],"improve":[56],"the":[57,71,82,95,99,112],"training":[58],"process":[59],"of":[60],"end-to-end":[61],"SVS":[62],"models.":[63],"First,":[64],"introduce":[66],"differentiable":[67],"augmentation":[69],"adversarial":[72],"training,":[73],"which":[74],"operates":[75],"a":[77,88],"sample-wise":[78],"manner":[79],"increase":[81],"prior":[83],"uncertainty.":[84],"Second,":[85],"incorporate":[87],"frame-level":[89],"uncertainty":[90],"prediction":[91],"module":[92],"that":[93,121],"estimates":[94],"posterior":[96],"uncertainty,":[97],"enabling":[98],"model":[100],"allocate":[102],"more":[103],"learning":[104],"capacity":[105],"low-confidence":[107],"segments.":[108],"Empirical":[109],"results":[110],"on":[111],"Opencpop":[113],"Ofuton-P,":[115],"across":[116],"Chinese":[117],"Japanese,":[119],"demonstrate":[120],"our":[122],"approach":[123],"improves":[124],"various":[127],"perspectives.":[128]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}