{"id":"https://openalex.org/W4408354058","doi":"https://doi.org/10.1109/icassp49660.2025.10888907","title":"SPSinger: Multi-Singer Singing Voice Synthesis with Short Reference Prompt","display_name":"SPSinger: Multi-Singer Singing Voice Synthesis with Short Reference Prompt","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354058","doi":"https://doi.org/10.1109/icassp49660.2025.10888907"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5104290513","display_name":"Junchuan Zhao","orcid":"https://orcid.org/0009-0008-2616-6590"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Junchuan Zhao","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chetwin Low","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chetwin Low","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423435","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0002-0123-1260"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ye Wang","raw_affiliation_strings":["National University of Singapore,School of Computing,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,School of Computing,Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":1.6508,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85041928,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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":0.9972000122070312,"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":0.9937000274658203,"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/T10860","display_name":"Speech and Audio Processing","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.821167528629303},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6219109892845154},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6144208908081055},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.3429487943649292},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.22574731707572937},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.12931692600250244},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0678967535495758}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.821167528629303},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6219109892845154},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6144208908081055},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.3429487943649292},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.22574731707572937},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.12931692600250244},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0678967535495758}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":32,"referenced_works":["https://openalex.org/W2120605154","https://openalex.org/W2515336442","https://openalex.org/W2963568710","https://openalex.org/W2984106626","https://openalex.org/W3016243847","https://openalex.org/W3016250102","https://openalex.org/W3024869864","https://openalex.org/W3081279708","https://openalex.org/W3097152652","https://openalex.org/W3158762648","https://openalex.org/W3198533616","https://openalex.org/W3209984917","https://openalex.org/W4285345683","https://openalex.org/W4312933868","https://openalex.org/W4319586596","https://openalex.org/W4372190416","https://openalex.org/W4375869411","https://openalex.org/W4385245566","https://openalex.org/W4385571362","https://openalex.org/W4385823074","https://openalex.org/W4390873054","https://openalex.org/W4391021559","https://openalex.org/W4396214748","https://openalex.org/W6631362777","https://openalex.org/W6765987481","https://openalex.org/W6778823374","https://openalex.org/W6783867762","https://openalex.org/W6809623261","https://openalex.org/W6810689344","https://openalex.org/W6847430118","https://openalex.org/W6849109464","https://openalex.org/W6851724922"],"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":{"Current":[0],"singing":[1,24,54,173],"voice":[2,25,55,174],"synthesis":[3,26,175],"systems":[4,27],"often":[5],"struggle":[6],"in":[7,192],"multi-singer":[8,23,53],"scenarios":[9],"due":[10],"to":[11,43,86,100,160],"limited":[12],"training":[13,70],"data":[14],"that":[15,57,133,157,169,176],"only":[16,108,187],"includes":[17],"a":[18,52,83,130,152],"few":[19],"singers.":[20],"Existing":[21],"zero-shot":[22,193],"are":[28],"criticized":[29],"for":[30,145],"their":[31],"reliance":[32],"on":[33,71,77],"global":[34,84,138],"timbre":[35,46,89,135],"embeddings":[36],"from":[37,61,91,104,137],"single":[38],"reference":[39,63,93,147,189],"audio,":[40],"which":[41],"fail":[42],"capture":[44,87,101],"sufficient":[45],"details.":[47],"This":[48,140],"paper":[49],"introduces":[50],"SPSinger,":[51],"synthesizer":[56],"generates":[58],"singer-specific":[59],"voices":[60],"brief":[62],"audio":[64,118,190],"(around":[65],"5":[66],"seconds)":[67],"without":[68],"prior":[69],"the":[72,78,113,124,143,162,178,181],"singer\u2019s":[73],"voice.":[74],"SPSinger":[75,170],"builds":[76],"StableDiffusion":[79],"framework":[80],"by":[81],"adding":[82],"encoder":[85,99],"consistent":[88],"features":[90,136],"short":[92,188],"prompts":[94,119],"and":[95],"an":[96],"attention-based":[97],"local":[98],"detailed":[102],"variations":[103],"long":[105,117,146],"prompts,":[106],"used":[107],"during":[109,120],"training.":[110],"To":[111],"overcome":[112],"challenge":[114],"of":[115,180],"requiring":[116],"inference,":[121],"we":[122,150],"introduce":[123],"Latent":[125],"Prompt":[126],"Adaptation":[127],"Model":[128],"(LPAM),":[129],"Transformer-based":[131],"module":[132],"derives":[134],"embeddings.":[139],"approach":[141],"eliminates":[142],"need":[144],"prompts.":[148],"Additionally,":[149],"propose":[151],"novel":[153],"pitch":[154,163],"shift":[155,164],"algorithm":[156],"uses":[158],"LPAM":[159],"predict":[161],"values.":[165],"Our":[166],"experiments":[167],"show":[168],"achieves":[171],"high-quality":[172],"preserves":[177],"identity":[179],"target":[182],"singer,":[183],"even":[184],"when":[185],"using":[186],"inputs":[191],"scenarios.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}