{"id":"https://openalex.org/W4221153051","doi":"https://doi.org/10.21437/interspeech.2022-960","title":"Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher","display_name":"Learn2Sing 2.0: Diffusion and Mutual Information-Based Target Speaker SVS by Learning from Singing Teacher","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4221153051","doi":"https://doi.org/10.21437/interspeech.2022-960"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-960","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-960","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/A5064426059","display_name":"Heyang Xue","orcid":null},"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":"Heyang Xue","raw_affiliation_strings":["Fuxi AI Lab, NetEase Inc., Hangzhou, China","School of Software,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuxi AI Lab, NetEase Inc., Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"School of Software,","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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinsheng Wang","raw_affiliation_strings":["School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"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":["School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066245750","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-9051-2111"},"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":["School of Software,","School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software,","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science, Northwestern Polytechnical University, Xian, 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/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":["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"]}]},{"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":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9343,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75552611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4267","last_page":"4271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9977999925613403,"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":0.9977999925613403,"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":0.9975000023841858,"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":0.9954000115394592,"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":0.753490686416626},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685979425907135},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5993216037750244},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5726653337478638},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.48530811071395874},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27358466386795044},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2368336021900177},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.052095890045166016}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.753490686416626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685979425907135},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5993216037750244},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5726653337478638},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.48530811071395874},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27358466386795044},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2368336021900177},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.052095890045166016},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-960","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-960","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":[{"score":0.8399999737739563,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1731081199","https://openalex.org/W2118774185","https://openalex.org/W3015645837","https://openalex.org/W3026874504","https://openalex.org/W3036928441","https://openalex.org/W3097152652","https://openalex.org/W3110257065","https://openalex.org/W3133525064","https://openalex.org/W3146962208","https://openalex.org/W3181854487","https://openalex.org/W3196760057","https://openalex.org/W3197659778","https://openalex.org/W3198213150","https://openalex.org/W3204602440","https://openalex.org/W4206397897","https://openalex.org/W4210682690","https://openalex.org/W4226332109","https://openalex.org/W4285345683","https://openalex.org/W4287184558","https://openalex.org/W4296068763","https://openalex.org/W4296068811","https://openalex.org/W4298017177"],"related_works":["https://openalex.org/W3207249698","https://openalex.org/W1528909574","https://openalex.org/W2122830402","https://openalex.org/W2552590214","https://openalex.org/W2921857201","https://openalex.org/W169038075","https://openalex.org/W3207038517","https://openalex.org/W2951961943","https://openalex.org/W4372262998","https://openalex.org/W3133417262"],"abstract_inverted_index":{"Building":[0],"a":[1,6,22,37,117,124],"high-quality":[2],"singing":[3,13,23,34,43,54,68,180,187],"corpus":[4],"for":[5,26,97,108,182],"person":[7],"who":[8],"is":[9,14,29,61,121,132,158,175],"not":[10],"good":[11],"at":[12],"non-trivial,":[15],"thus":[16],"making":[17],"it":[18],"challenging":[19],"to":[20,31,66,134,143,160],"create":[21],"voice":[24,35,181],"synthesizer":[25],"this":[27,95],"person.Learn2Sing":[28],"dedicated":[30],"synthesizing":[32,178],"the":[33,53,57,62,72,78,87,92,109,114,129,137,141,145,149,153,162,172,183],"of":[36,94,148,164,177],"speaker":[38,110,150,165,185],"without":[39,186],"his":[40],"or":[41,102],"her":[42],"data":[44,48,188],"by":[45,50,56,123],"learning":[46,163],"from":[47,69],"recorded":[49],"others,":[51],"i.e.,":[52,100],"teacher.Inspired":[55],"fact":[58],"that":[59,171],"pitch":[60,84],"key":[63],"style":[64,154,168],"factor":[65],"distinguish":[67],"speaking":[70,101],"voice,":[71],"proposed":[73,173],"Learn2Sing":[74],"2.0":[75],"first":[76],"generates":[77],"preliminary":[79],"acoustic":[80,139],"feature":[81],"with":[82,189],"averaged":[83],"value":[85],"in":[86],"phone":[88],"level,":[89],"which":[90,120],"allows":[91],"training":[93],"process":[96],"different":[98],"styles,":[99],"singing,":[103],"share":[104],"same":[105],"conditions":[106],"except":[107],"information.Then,":[111],"conditioned":[112],"on":[113],"specific":[115],"style,":[116],"diffusion":[118],"decoder,":[119],"accelerated":[122],"fast":[125],"sampling":[126],"algorithm":[127],"during":[128],"inference":[130],"stage,":[131],"adopted":[133],"gradually":[135],"restore":[136],"final":[138],"feature.During":[140],"training,":[142],"avoid":[144],"information":[146,157],"confusion":[147],"embedding":[151,166],"and":[152,167],"embedding,":[155],"mutual":[156],"employed":[159],"restrain":[161],"embedding.Experiments":[169],"show":[170],"approach":[174],"capable":[176],"highquality":[179],"target":[184],"10":[190],"decoding":[191],"steps.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}