{"id":"https://openalex.org/W4221167708","doi":"https://doi.org/10.21437/interspeech.2022-454","title":"WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses","display_name":"WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221167708","doi":"https://doi.org/10.21437/interspeech.2022-454"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-454","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-454","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":"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/A5048848376","display_name":"Zewang Zhang","orcid":"https://orcid.org/0009-0001-3620-8706"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zewang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101398585","display_name":"Yibin Zheng","orcid":"https://orcid.org/0000-0001-9158-1813"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibin Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100701664","display_name":"Xinhui Li","orcid":"https://orcid.org/0000-0003-0164-3422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhui Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658678","display_name":"Li L\u00fc","orcid":"https://orcid.org/0000-0001-5230-3749"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9531,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92765782,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4252","last_page":"4256"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9957000017166138,"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":0.9842000007629395,"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/naturalness","display_name":"Naturalness","score":0.9717649221420288},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.8604691028594971},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7909450531005859},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7486976385116577},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7342559695243835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6978169083595276},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5325110554695129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38038554787635803},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1818680465221405},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.14090391993522644},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0721401572227478}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9717649221420288},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8604691028594971},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7909450531005859},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7486976385116577},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7342559695243835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6978169083595276},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5325110554695129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38038554787635803},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1818680465221405},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.14090391993522644},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0721401572227478},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-454","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-454","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":0.6600000262260437,"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/W4391272374","https://openalex.org/W1914543332","https://openalex.org/W2946856121","https://openalex.org/W40885451","https://openalex.org/W2108985546","https://openalex.org/W2081919107","https://openalex.org/W2433276473","https://openalex.org/W2535215250","https://openalex.org/W1813881148","https://openalex.org/W1537411440"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,27],"develop":[4],"a":[5,59],"new":[6],"multi-singer":[7,78,100],"Chinese":[8,129],"neural":[9,64],"singing":[10,25,69,130,135],"voice":[11],"synthesis":[12],"(SVS)":[13],"system":[14,93],"named":[15],"WeSinger.":[16],"To":[17,85],"improve":[18],"the":[19,90,110,126],"accuracy":[20,117],"and":[21,32,45,83,99,105,118,120],"naturalness":[22],"of":[23,112,116],"synthesized":[24,134],"voice,":[26],"design":[28],"several":[29],"specifical":[30],"modules":[31],"techniques:":[33],"1)":[34],"A":[35,49,72],"deep":[36],"bi-directional":[37],"LSTM-based":[38],"duration":[39],"model":[40,52],"with":[41,53,77],"multi-scale":[42],"rhythm":[43],"loss":[44],"post-processing":[46],"step;":[47],"2)":[48],"Transformer-alike":[50],"acoustic":[51],"progressive":[54],"pitch-weighted":[55],"decoder":[56],"loss;":[57],"3)":[58],"24":[60,96],"kHz":[61,97],"pitch-aware":[62],"LPCNet":[63,98],"vocoder":[65],"to":[66,94],"produce":[67],"high-quality":[68],"waveforms;":[70],"4)":[71],"novel":[73],"data":[74],"augmentation":[75],"method":[76],"pre-training":[79,101],"for":[80],"stronger":[81],"robustness":[82],"naturalness.":[84],"our":[86],"knowledge,":[87],"WeSinger":[88,113,121],"is":[89],"first":[91],"SVS":[92],"adopt":[95],"simultaneously.":[102],"Both":[103],"quantitative":[104],"qualitative":[106],"evaluation":[107],"results":[108],"demonstrate":[109],"effectiveness":[111],"in":[114],"terms":[115],"naturalness,":[119],"achieves":[122],"state-of-the-art":[123],"performance":[124],"on":[125],"recent":[127],"public":[128],"corpus":[131],"Opencpop\\footnote{https://wenet.org.cn/opencpop/}.":[132],"Some":[133],"samples":[136],"are":[137],"available":[138],"online\\footnote{https://zzw922cn.github.io/wesinger/}.":[139]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}