{"id":"https://openalex.org/W4408356766","doi":"https://doi.org/10.1109/icassp49660.2025.10889751","title":"Everyone-Can-Sing: Zero-Shot Singing Voice Synthesis and Conversion with Speech Reference","display_name":"Everyone-Can-Sing: Zero-Shot Singing Voice Synthesis and Conversion with Speech Reference","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408356766","doi":"https://doi.org/10.1109/icassp49660.2025.10889751"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889751","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":"conference-paper","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/A5003777273","display_name":"Shuqi Dai","orcid":"https://orcid.org/0000-0002-3804-125X"},"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":"Shuqi Dai","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100714799","display_name":"Yunyun Wang","orcid":"https://orcid.org/0000-0002-5884-9408"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunyun Wang","raw_affiliation_strings":["Princeton University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000265897","display_name":"Roger B. Dannenberg","orcid":"https://orcid.org/0000-0003-1823-9856"},"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":"Roger B. Dannenberg","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100702050","display_name":"Zeyu Jin","orcid":"https://orcid.org/0000-0003-0161-5915"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zeyu Jin","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.9927999973297119,"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":0.9927999973297119,"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/T10860","display_name":"Speech and Audio Processing","score":0.9440000057220459,"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":0.7299070358276367},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6517363786697388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6207520365715027},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6067906618118286},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.57762610912323},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.454521119594574},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.27515846490859985},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09901207685470581},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09831154346466064}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7299070358276367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6517363786697388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6207520365715027},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6067906618118286},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.57762610912323},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.454521119594574},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.27515846490859985},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09901207685470581},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09831154346466064},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889751","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889751","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2962788625","https://openalex.org/W3097514409","https://openalex.org/W3215615641","https://openalex.org/W4385571362","https://openalex.org/W4385823191","https://openalex.org/W4391021724","https://openalex.org/W4391021729","https://openalex.org/W4392903036","https://openalex.org/W4392903903","https://openalex.org/W4403791262","https://openalex.org/W6750649333","https://openalex.org/W6771763809","https://openalex.org/W6778823374","https://openalex.org/W6780218876","https://openalex.org/W6783713337","https://openalex.org/W6783867762","https://openalex.org/W6803547063","https://openalex.org/W6838843145","https://openalex.org/W6846936884","https://openalex.org/W6847430118","https://openalex.org/W6848735303","https://openalex.org/W6851724922","https://openalex.org/W6853515095","https://openalex.org/W6892481026"],"related_works":["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","https://openalex.org/W2366077683","https://openalex.org/W1501596003","https://openalex.org/W2368036937"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,47,57,64,86],"unified":[3],"framework":[4,31,91],"for":[5],"Singing":[6],"Voice":[7],"Synthesis":[8],"(SVS)":[9],"and":[10,25,52,59,77,85,101,119],"Conversion":[11],"(SVC),":[12],"addressing":[13],"the":[14],"limitations":[15],"of":[16,27,73],"existing":[17],"approaches":[18],"in":[19,116],"cross-domain":[20],"SVS/SVC,":[21],"poor":[22],"output":[23],"musicality,":[24],"scarcity":[26],"singing":[28,50,100,105],"data.":[29],"Our":[30],"enables":[32],"control":[33],"over":[34,121],"multiple":[35],"aspects,":[36],"including":[37],"language":[38],"content":[39,83],"based":[40,45,55,62,108],"on":[41,46,56,63,95,109],"lyrics,":[42],"performance":[43],"attributes":[44],"musical":[48],"score,":[49],"style":[51,134],"vocal":[53],"techniques":[54],"selector,":[58],"voice":[60,106],"identity":[61],"speech":[65,102,110],"sample.":[66],"The":[67,89],"proposed":[68,90],"zero-shot":[69],"learning":[70],"paradigm":[71],"consists":[72],"one":[74],"SVS":[75],"model":[76],"two":[78],"SVC":[79],"models,":[80],"utilizing":[81],"pre-trained":[82],"embeddings":[84],"diffusion-based":[87],"generator.":[88],"is":[92],"also":[93],"trained":[94],"mixed":[96],"datasets":[97],"comprising":[98],"both":[99],"audio,":[103],"allowing":[104],"cloning":[107],"reference.":[111],"Experiments":[112],"show":[113],"substantial":[114],"improvements":[115],"timbre":[117],"similarity":[118],"musicality":[120],"state-of-the-art":[122],"baselines,":[123],"providing":[124],"insights":[125],"into":[126],"other":[127],"low-data":[128],"music":[129],"tasks":[130],"such":[131],"as":[132],"instrumental":[133],"transfer.":[135],"Examples":[136],"can":[137],"be":[138],"found":[139],"at:":[140],"everyone-can-sing.github.io.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}