{"id":"https://openalex.org/W7225397248","doi":"https://doi.org/10.17743/jaes.2026.0303","title":"Singing Voice Synthesis via Guided Diffusion","display_name":"Singing Voice Synthesis via Guided Diffusion","publication_year":2026,"publication_date":"2026-11-06","ids":{"openalex":"https://openalex.org/W7225397248","doi":"https://doi.org/10.17743/jaes.2026.0303"},"language":"en","primary_location":{"id":"doi:10.17743/jaes.2026.0303","doi":"https://doi.org/10.17743/jaes.2026.0303","is_oa":false,"landing_page_url":"https://doi.org/10.17743/jaes.2026.0303","pdf_url":null,"source":{"id":"https://openalex.org/S62507282","display_name":"Journal of the Audio Engineering Society","issn_l":"1549-4950","issn":["1549-4950"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","erih-plus","jufo-2","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4320800558","host_organization_name":"Audio Engineering Society","host_organization_lineage":["https://openalex.org/P4320800558"],"host_organization_lineage_names":["Audio Engineering Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Audio Engineering Society","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5161060073","display_name":"Sijia Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sijia Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161137198","display_name":"Shiguang Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiguang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5161032562","display_name":"Wenhuan Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhuan Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"74","issue":"11","first_page":"811","last_page":"824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9794999957084656,"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":0.9794999957084656,"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":0.007899999618530273,"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":0.0034000000450760126,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/singing-voice-synthesis","display_name":"singing voice synthesis","score":1.0},{"id":"https://openalex.org/keywords/guided-diffusion","display_name":"guided diffusion","score":0.9620000123977661},{"id":"https://openalex.org/keywords/annotation-free-training","display_name":"annotation-free training","score":0.7070000171661377},{"id":"https://openalex.org/keywords/virtual-singers","display_name":"virtual singers","score":0.7670000195503235},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.6320000290870667}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8228999972343445},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800999879837036},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6435999870300293},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6383000016212463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6187999844551086},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5181999802589417},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43689998984336853},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2778744346","wikidata":"https://www.wikidata.org/wiki/Q1152224","display_name":"Distinctive feature","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.25589999556541443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.17743/jaes.2026.0303","doi":"https://doi.org/10.17743/jaes.2026.0303","is_oa":false,"landing_page_url":"https://doi.org/10.17743/jaes.2026.0303","pdf_url":null,"source":{"id":"https://openalex.org/S62507282","display_name":"Journal of the Audio Engineering Society","issn_l":"1549-4950","issn":["1549-4950"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-c","erih-plus","jufo-2","norway-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4320800558","host_organization_name":"Audio Engineering Society","host_organization_lineage":["https://openalex.org/P4320800558"],"host_organization_lineage_names":["Audio Engineering Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Audio Engineering Society","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402112011","https://openalex.org/W4415183912","https://openalex.org/W4417087090","https://openalex.org/W3158762648","https://openalex.org/W4417119521","https://openalex.org/W4404340985","https://openalex.org/W3169635929","https://openalex.org/W7220128575","https://openalex.org/W4402905495","https://openalex.org/W4416799063"],"abstract_inverted_index":{"Singing":[0],"voice":[1,30],"synthesis":[2,31],"has":[3],"emerged":[4],"as":[5,85],"a":[6,49,60,88,96,166],"popular":[7],"research":[8],"area":[9],"recently.":[10],"Different":[11],"from":[12,119],"standard":[13],"text-to-speech,":[14],"it":[15],"demands":[16],"simultaneous":[17],"adherence":[18],"to":[19,91,99,113],"both":[20],"lyrical":[21],"and":[22,43,82,95,111,132,143],"musical":[23],"constraints.":[24],"This":[25,74],"multiconditional":[26],"nature":[27],"makes":[28],"singing":[29,158],"systems":[32],"highly":[33],"dependent":[34],"on":[35,68],"accurately":[36],"annotated":[37],"datasets,":[38],"making":[39],"data":[40],"preparation":[41],"laborious":[42],"expensive.":[44],"Therefore,":[45],"the":[46,66,115,120,130,133,171],"authors":[47,124],"propose":[48],"novel":[50],"dual-classifier":[51],"guided":[52],"diffusion":[53,63,72,80,163],"framework":[54],"that":[55,151],"employs":[56],"guidance":[57,127],"functions":[58],"for":[59,170],"pretrained,":[61],"unconditional":[62,79],"model,":[64],"reducing":[65],"dependence":[67],"precise":[69],"labels":[70],"during":[71,162],"training.":[73],"approach":[75],"consists":[76],"of":[77,156,173],"an":[78],"model":[81],"two":[83,121],"classifiers":[84],"external":[86],"guidance:":[87],"phoneme":[89],"classifier":[90,98],"ensure":[92],"accurate":[93],"pronunciation":[94],"pitch":[97,101],"adjust":[100],"alignment.":[102],"Techniques":[103],"like":[104],"gradient":[105],"conflict":[106],"projection":[107],"are":[108],"also":[109],"explored":[110],"validated":[112],"harmonize":[114],"potentially":[116],"conflicting":[117],"gradients":[118,140],"classifiers.":[122],"The":[123],"investigate":[125],"different":[126],"strategies,":[128],"including":[129],"noisy-space":[131],"more":[134,167],"general":[135],"clean-space":[136],"guidance,":[137],"which":[138],"estimate":[139],"in":[141],"noisy":[142],"clean":[144],"feature":[145],"spaces,":[146],"respectively.":[147],"Experimental":[148],"results":[149],"demonstrate":[150],"this":[152],"method":[153],"is":[154],"capable":[155],"generating":[157],"voices":[159],"without":[160],"annotations":[161],"training,":[164],"providing":[165],"convenient":[168],"solution":[169],"development":[172],"virtual":[174],"singer":[175],"applications.":[176]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-07T00:00:00"}