{"id":"https://openalex.org/W4403780508","doi":"https://doi.org/10.1145/3664647.3685000","title":"Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm","display_name":"Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780508","doi":"https://doi.org/10.1145/3664647.3685000"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3685000","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3685000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5101011479","display_name":"Yuning Wu","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":true,"raw_author_name":"Yuning Wu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"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, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yifeng Yu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"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, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074650189","display_name":"Tao Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155796","display_name":"Shanghai Jinyuan Senior High School","ror":"https://ror.org/05g2egb88","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210155796"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qian","raw_affiliation_strings":["Shanghai High School, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai High School, Shanghai, China","institution_ids":["https://openalex.org/I4210155796"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768194","display_name":"Yueqian Lin","orcid":"https://orcid.org/0000-0003-1473-8981"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yueqian Lin","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113242994","display_name":"Jionghao Han","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":"Jionghao Han","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102613754","display_name":"Xue Bai","orcid":"https://orcid.org/0009-0005-5479-9692"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyi Bai","raw_affiliation_strings":["Cornell University &amp; Multimodal Art Projection, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University &amp; Multimodal Art Projection, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","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, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009985839","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0001-6486-6020"},"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":"Qin Jin","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5101011479"],"corresponding_institution_ids":["https://openalex.org/I78988378"],"apc_list":null,"apc_paid":null,"fwci":0.6891,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76352233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"11279","last_page":"11281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9990000128746033,"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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/computer-science","display_name":"Computer science","score":0.6818908452987671},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6484706997871399},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49088460206985474},{"id":"https://openalex.org/keywords/paradigm-shift","display_name":"Paradigm shift","score":0.4190950393676758},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3611829876899719},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10697212815284729}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6818908452987671},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6484706997871399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49088460206985474},{"id":"https://openalex.org/C43540301","wikidata":"https://www.wikidata.org/wiki/Q689971","display_name":"Paradigm shift","level":2,"score":0.4190950393676758},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3611829876899719},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10697212815284729},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3685000","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3685000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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":16,"referenced_works":["https://openalex.org/W2962780374","https://openalex.org/W2979476256","https://openalex.org/W3140429000","https://openalex.org/W3169320628","https://openalex.org/W3180374548","https://openalex.org/W3207340675","https://openalex.org/W4225463329","https://openalex.org/W4287119707","https://openalex.org/W4298397573","https://openalex.org/W4385565440","https://openalex.org/W4385822683","https://openalex.org/W4385823416","https://openalex.org/W4392909068","https://openalex.org/W4392909760","https://openalex.org/W4402111669","https://openalex.org/W4402111789"],"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":{"This":[0],"research":[1],"presents":[2],"Muskits-ESPnet,":[3],"a":[4,74],"versatile":[5],"toolkit":[6,62],"that":[7],"introduces":[8],"new":[9],"paradigms":[10],"to":[11,78],"Singing":[12],"Voice":[13],"Synthesis":[14],"(SVS)":[15],"through":[16],"the":[17],"application":[18],"of":[19],"pretrained":[20],"audio":[21,39],"models":[22,37],"in":[23,45],"both":[24],"continuous":[25],"and":[26,38,41,47,52,69],"discrete":[27,32],"approaches.":[28],"Specifically,":[29],"we":[30],"explore":[31],"representations":[33],"derived":[34],"from":[35],"SSL":[36],"codecs":[40],"offer":[42],"significant":[43],"advantages":[44],"versatility":[46],"intelligence,":[48],"supporting":[49],"multi-format":[50],"inputs":[51],"adaptable":[53],"data":[54],"processing":[55],"workflows":[56],"for":[57],"various":[58],"SVS":[59],"models.":[60],"The":[61],"features":[63],"automatic":[64],"music":[65],"score":[66],"error":[67],"detection":[68],"correction,":[70],"as":[71,73],"well":[72],"perception":[75],"auto-evaluation":[76],"module":[77],"imitate":[79],"human":[80],"subjective":[81],"evaluating":[82],"scores.":[83],"Muskits-ESPnet":[84],"is":[85],"available":[86],"at":[87],"https://github.com/espnet/espnet.":[88]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
