{"id":"https://openalex.org/W4296068763","doi":"https://doi.org/10.21437/interspeech.2022-48","title":"Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis","display_name":"Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068763","doi":"https://doi.org/10.21437/interspeech.2022-48"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-48","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-48","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/A5100445125","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-9500-081X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["College of Design and Innovation, Tongji University, China","School of Pop Music & Dance, Shanghai Institute of Visual Arts, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Design and Innovation, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"School of Pop Music & Dance, Shanghai Institute of Visual Arts, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115547209","display_name":"Xinsheng Wang","orcid":"https://orcid.org/0000-0002-7528-4621"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["Fuxi AI Lab, NetEase Inc., Hangzhou, China","Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050166453","display_name":"Pengcheng Zhu","orcid":"https://orcid.org/0000-0001-9867-7041"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Zhu","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600528","display_name":"Jie Wu","orcid":"https://orcid.org/0000-0002-3472-1717"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["College of Design and Innovation, Tongji University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Design and Innovation, Tongji University, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016567570","display_name":"Hanzhao Li","orcid":"https://orcid.org/0009-0005-3215-7517"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanzhao Li","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064426059","display_name":"Heyang Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heyang Xue","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060467975","display_name":"Yongmao Zhang","orcid":"https://orcid.org/0009-0000-0526-5778"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongmao Zhang","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036369578","display_name":"Mengxiao Bi","orcid":"https://orcid.org/0009-0007-6680-481X"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengxiao Bi","raw_affiliation_strings":["Fuxi AI Lab, NetEase Inc., Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.4365,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.97471508,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4242","last_page":"4246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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":0.9973999857902527,"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/lyrics","display_name":"Lyrics","score":0.8970550894737244},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.875917375087738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7520376443862915},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7463616132736206},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.688224732875824},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5478498935699463},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5349007844924927},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5109878778457642},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47012102603912354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44172993302345276},{"id":"https://openalex.org/keywords/mean-opinion-score","display_name":"Mean opinion score","score":0.4251210689544678},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.420979380607605},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4174373149871826},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.414571076631546},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12663984298706055},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07937309145927429},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07678499817848206}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.8970550894737244},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.875917375087738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7520376443862915},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7463616132736206},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.688224732875824},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5478498935699463},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5349007844924927},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5109878778457642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47012102603912354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44172993302345276},{"id":"https://openalex.org/C62897895","wikidata":"https://www.wikidata.org/wiki/Q1915482","display_name":"Mean opinion score","level":3,"score":0.4251210689544678},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.420979380607605},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4174373149871826},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.414571076631546},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12663984298706055},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07937309145927429},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07678499817848206},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-48","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-48","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","display_name":"Quality Education","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1875231349","https://openalex.org/W2067709094","https://openalex.org/W2519091744","https://openalex.org/W2527729766","https://openalex.org/W2770743791","https://openalex.org/W2794490148","https://openalex.org/W2901997113","https://openalex.org/W2903739847","https://openalex.org/W2950374865","https://openalex.org/W2963300588","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2971753973","https://openalex.org/W3008691130","https://openalex.org/W3015841875","https://openalex.org/W3033411150","https://openalex.org/W3041870963","https://openalex.org/W3092028330","https://openalex.org/W3094002217","https://openalex.org/W3097514409","https://openalex.org/W3146962208","https://openalex.org/W3160329778","https://openalex.org/W3163132306","https://openalex.org/W3163793923","https://openalex.org/W3166714886","https://openalex.org/W3181854487","https://openalex.org/W3197481261","https://openalex.org/W3201011692","https://openalex.org/W4285345683","https://openalex.org/W4287121924","https://openalex.org/W4287184558","https://openalex.org/W4287672314","https://openalex.org/W4287761884","https://openalex.org/W4289305009"],"related_works":["https://openalex.org/W3109498233","https://openalex.org/W3164858600","https://openalex.org/W2031768607","https://openalex.org/W2902064555","https://openalex.org/W231741463","https://openalex.org/W2772686614","https://openalex.org/W2152945827","https://openalex.org/W4205278983","https://openalex.org/W114226241","https://openalex.org/W4200068392"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"Opencpop,":[3],"a":[4,26,37,75],"publicly":[5],"available":[6],"highquality":[7],"Mandarin":[8,22],"singing":[9,13,52],"corpus":[10,17],"designed":[11],"for":[12,77],"voice":[14],"synthesis":[15],"(SVS).The":[16],"consists":[18],"of":[19,40,68,119],"100":[20],"popular":[21],"songs":[23],"performed":[24],"by":[25],"female":[27],"professional":[28],"singer.Audio":[29],"files":[30],"are":[31,50],"recorded":[32],"with":[33,58,91],"studio":[34],"quality":[35],"at":[36],"sampling":[38],"rate":[39],"44,100":[41],"Hz":[42],"and":[43,47,61,72,88,95,132],"the":[44,66,69,105,117,120,126,133,144],"corresponding":[45],"lyrics":[46],"musical":[48],"scores":[49],"provided.All":[51],"recordings":[53],"have":[54],"been":[55],"phonetically":[56],"annotated":[57],"phoneme":[59],"boundaries":[60],"syllable":[62],"(note)":[63],"boundaries.To":[64],"demonstrate":[65],"reliability":[67,118],"released":[70,124],"data":[71],"to":[73,125],"provide":[74],"baseline":[76,82],"future":[78],"research,":[79],"we":[80],"built":[81],"deep":[83],"neural":[84],"network-based":[85],"SVS":[86,107],"models":[87],"evaluated":[89],"them":[90],"both":[92],"objective":[93],"metrics":[94],"subjective":[96],"mean":[97],"opinion":[98],"score":[99],"(MOS)":[100],"measure.Experimental":[101],"results":[102],"show":[103],"that":[104],"best":[106],"model":[108],"trained":[109],"on":[110,143],"our":[111],"database":[112],"achieves":[113],"3.70":[114],"MOS,":[115],"indicating":[116],"provided":[121],"corpus.Opencpop":[122],"is":[123],"open-source":[127],"community":[128],"WeNet":[129],"1":[130],",":[131],"corpus,":[134],"as":[135,137],"well":[136],"synthesized":[138],"demos,":[139],"can":[140],"be":[141],"found":[142],"project":[145],"homepage":[146],"2":[147],".":[148]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
