{"id":"https://openalex.org/W4280572880","doi":"https://doi.org/10.21437/interspeech.2022-10039","title":"Muskits: an End-to-end Music Processing Toolkit for Singing Voice Synthesis","display_name":"Muskits: an End-to-end Music Processing Toolkit for Singing Voice Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4280572880","doi":"https://doi.org/10.21437/interspeech.2022-10039"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10039","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10039","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","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/A5008336983","display_name":"Jiatong Shi","orcid":"https://orcid.org/0000-0002-9050-8304"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075939587","display_name":"Shuai Guo","orcid":"https://orcid.org/0000-0002-2022-8948"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai Guo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054269959","display_name":"Tao Qian","orcid":"https://orcid.org/0000-0002-8969-906X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Qian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109294914","display_name":"Tomoki Hayashi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101671924","display_name":"Yuning Wu","orcid":"https://orcid.org/0000-0003-1715-2361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuning Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097901318","display_name":"Fangzheng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fangzheng Xu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053606195","display_name":"Huazhe Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huazhe Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112896504","display_name":"Peter Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102462376","display_name":"Qin Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin Jin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5008336983"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6701,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.85869508,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4277","last_page":"4281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9983999729156494,"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":0.989300012588501,"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":0.8322430849075317},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7163195610046387},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.635353684425354},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6148995161056519},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48294371366500854},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3206954002380371},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3049149513244629},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10244596004486084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322430849075317},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7163195610046387},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.635353684425354},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6148995161056519},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48294371366500854},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3206954002380371},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3049149513244629},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10244596004486084},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10039","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10039","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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":{"This":[0,100],"paper":[1,101],"introduces":[2],"a":[3,70],"new":[4],"open-source":[5],"platform":[6,67],"named":[7],"Muskits":[8,22,37],"for":[9,49],"end-to-end":[10,17],"music":[11],"processing,":[12],"which":[13],"mainly":[14],"focuses":[15],"on":[16,90],"singing":[18],"voice":[19],"synthesis":[20],"(E2E-SVS).":[21],"supports":[23],"state-of-the-art":[24],"SVS":[25],"models,":[26],"including":[27,94],"RNN":[28],"SVS,":[29,31],"transformer":[30],"and":[32,47,53,72,97,110,117],"XiaoiceSing.":[33],"The":[34,121],"design":[35],"of":[36,41,59,106],"follows":[38],"the":[39,57,65,91,103],"style":[40],"widely-used":[42],"speech":[43],"processing":[44],"toolkits,":[45],"ESPnet":[46],"Kaldi,":[48],"data":[50],"prepossessing,":[51],"training,":[52],"recipe":[54],"pipelines.":[55],"To":[56],"best":[58],"our":[60],"knowledge,":[61],"this":[62],"toolkit":[63,92,122],"is":[64,123],"first":[66],"that":[68],"allows":[69],"fair":[71],"highly-reproducible":[73],"comparison":[74],"between":[75],"several":[76,86],"published":[77],"works":[78],"in":[79,113],"SVS.":[80],"In":[81],"addition,":[82],"we":[83],"also":[84],"demonstrate":[85],"advanced":[87],"usages":[88],"based":[89],"functionalities,":[93,109],"multilingual":[95],"training":[96],"transfer":[98,118],"learning.":[99],"describes":[102],"major":[104],"framework":[105],"Muskits,":[107],"its":[108],"experimental":[111],"results":[112],"single-singer,":[114],"multi-singer,":[115],"multilingual,":[116],"learning":[119],"scenarios.":[120],"publicly":[124],"available":[125],"at":[126],"https://github.com/SJTMusicTeam/Muskits.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
