{"id":"https://openalex.org/W4406461759","doi":"https://doi.org/10.1109/slt61566.2024.10832313","title":"Visinger2+: End-to-End Singing Voice Synthesis Augmented by Self-Supervised Learning Representation","display_name":"Visinger2+: End-to-End Singing Voice Synthesis Augmented by Self-Supervised Learning Representation","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461759","doi":"https://doi.org/10.1109/slt61566.2024.10832313"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/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":true,"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/A5101063912","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/A5040175121","display_name":"Yuning Wu","orcid":"https://orcid.org/0000-0002-2699-4790"},"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":"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/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":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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/A5102256715"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7777021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"719","last_page":"726"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991999864578247,"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":0.998199999332428,"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":0.7897856831550598},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7674444913864136},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6752241849899292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5973618030548096},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47156187891960144},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.42273083329200745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3005368411540985},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09631520509719849}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7897856831550598},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7674444913864136},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6752241849899292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5973618030548096},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47156187891960144},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.42273083329200745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3005368411540985},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09631520509719849},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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":42,"referenced_works":["https://openalex.org/W2891314207","https://openalex.org/W3082910224","https://openalex.org/W3096084197","https://openalex.org/W3097514409","https://openalex.org/W3158762648","https://openalex.org/W3160427568","https://openalex.org/W3197273793","https://openalex.org/W3197580070","https://openalex.org/W3207340675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225463329","https://openalex.org/W4226380987","https://openalex.org/W4280572880","https://openalex.org/W4296068763","https://openalex.org/W4379251869","https://openalex.org/W4385823074","https://openalex.org/W4385823416","https://openalex.org/W4385895691","https://openalex.org/W4385993862","https://openalex.org/W4391021724","https://openalex.org/W4392909760","https://openalex.org/W4392910802","https://openalex.org/W4399794707","https://openalex.org/W4401597614","https://openalex.org/W4402111799","https://openalex.org/W4402112388","https://openalex.org/W4402301063","https://openalex.org/W4403780508","https://openalex.org/W4405710101","https://openalex.org/W6630833833","https://openalex.org/W6636756989","https://openalex.org/W6678318511","https://openalex.org/W6783382068","https://openalex.org/W6783867762","https://openalex.org/W6810007534","https://openalex.org/W6852985890","https://openalex.org/W6853004994","https://openalex.org/W6857589352","https://openalex.org/W6860417749","https://openalex.org/W6861764568","https://openalex.org/W6869945801"],"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/W4404782863"],"abstract_inverted_index":{"Singing":[0],"Voice":[1],"Synthesis":[2],"(SVS)":[3],"has":[4],"witnessed":[5],"significant":[6,17],"advancements":[7],"with":[8],"the":[9,22,31,50,65,77,88,93,98,115,122],"advent":[10],"of":[11,24,33,52,117,125],"deep":[12],"learning":[13,35,61],"techniques.":[14],"However,":[15],"a":[16,45,102],"challenge":[18],"in":[19,111,120,129],"SVS":[20,53],"is":[21],"scarcity":[23],"labeled":[25],"singing":[26,107,127],"voice":[27],"data,":[28],"which":[29],"limits":[30],"effectiveness":[32],"supervised":[34],"methods.":[36],"In":[37],"response":[38],"to":[39,48,79,86],"this":[40,42,69,118],"challenge,":[41],"paper":[43],"introduces":[44],"novel":[46],"approach":[47,119],"enhance":[49,80],"quality":[51,124],"by":[54],"leveraging":[55],"unlabeled":[56],"data":[57],"from":[58,92],"pre-trained":[59,94],"self-supervised":[60],"models.":[62],"Building":[63],"upon":[64],"existing":[66],"VISinger2":[67],"framework,":[68],"study":[70],"integrates":[71],"additional":[72],"spectral":[73],"feature":[74],"information":[75],"into":[76],"system":[78],"its":[81],"performance.":[82],"The":[83],"integration":[84],"aims":[85],"harness":[87],"rich":[89],"acoustic":[90],"features":[91],"models,":[95],"thereby":[96],"enriching":[97],"synthesis":[99],"and":[100,105,132],"yielding":[101],"more":[103],"natural":[104],"expressive":[106],"voice.":[108],"Experimental":[109],"results":[110],"various":[112],"corpora":[113],"demonstrate":[114],"efficacy":[116],"improving":[121],"overall":[123],"synthesized":[126],"voices":[128],"both":[130],"objective":[131],"subjective":[133],"metrics.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}