{"id":"https://openalex.org/W4200561598","doi":"https://doi.org/10.1145/3461615.3491115","title":"Noise Robust Singing Voice Synthesis Using Gaussian Mixture Variational Autoencoder","display_name":"Noise Robust Singing Voice Synthesis Using Gaussian Mixture Variational Autoencoder","publication_year":2021,"publication_date":"2021-10-18","ids":{"openalex":"https://openalex.org/W4200561598","doi":"https://doi.org/10.1145/3461615.3491115"},"language":"en","primary_location":{"id":"doi:10.1145/3461615.3491115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3491115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","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/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":true,"raw_author_name":"Heyang Xue","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061062034","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0002-7435-1511"},"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":"Xiao Zhang","raw_affiliation_strings":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014705936","display_name":"Jie Wu","orcid":"https://orcid.org/0000-0002-2864-1606"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Wu","raw_affiliation_strings":["Xiaomi AI Lab, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054843960","display_name":"Jian Luan","orcid":"https://orcid.org/0000-0002-2383-226X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Luan","raw_affiliation_strings":["Xiaomi AI Lab, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362600","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0002-2165-2599"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi AI Lab, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi AI Lab, China","institution_ids":[]}]},{"author_position":"last","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":["Northwestern Polytechnical University, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5064426059"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47822853,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9994999766349792,"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":0.9994999766349792,"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":0.7826904058456421},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7405582666397095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7198358178138733},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6345117092132568},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6170266270637512},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5094922184944153},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.47575730085372925},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4652819037437439},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4314522445201874},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.4253031015396118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36127036809921265},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3053668737411499},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.1661091148853302},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10014820098876953}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7826904058456421},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7405582666397095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7198358178138733},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6345117092132568},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6170266270637512},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5094922184944153},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.47575730085372925},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4652819037437439},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4314522445201874},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.4253031015396118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36127036809921265},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3053668737411499},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.1661091148853302},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10014820098876953},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461615.3491115","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461615.3491115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Publication of the 2021 International Conference on Multimodal Interaction","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":15,"referenced_works":["https://openalex.org/W2159300614","https://openalex.org/W2595002104","https://openalex.org/W2603567530","https://openalex.org/W2626699878","https://openalex.org/W2730106296","https://openalex.org/W2907262790","https://openalex.org/W2990621560","https://openalex.org/W3015499232","https://openalex.org/W3027916066","https://openalex.org/W3037149862","https://openalex.org/W3081279708","https://openalex.org/W3133525064","https://openalex.org/W3160427568","https://openalex.org/W3161691227","https://openalex.org/W3163906773"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W3013693939","https://openalex.org/W2088854863","https://openalex.org/W2159052453","https://openalex.org/W1975881626","https://openalex.org/W4252208810","https://openalex.org/W1982429998","https://openalex.org/W2052981742"],"abstract_inverted_index":{"Generating":[0],"high-quality":[1,138],"singing":[2,10,25,38,62,83,139,149],"voice":[3,26,63,84,140,150],"usually":[4],"depends":[5],"on":[6,32],"a":[7,59,95,105],"sizable":[8],"studio-level":[9],"corpus":[11],"which":[12,65],"is":[13,22],"difficult":[14],"and":[15,137],"expensive":[16],"to":[17,51,76,147],"collect.":[18],"In":[19,54],"contrast,":[20],"there":[21],"plenty":[23],"of":[24,100,111,163],"data":[27,39],"that":[28,130],"can":[29,134],"be":[30,41],"found":[31,37],"the":[33,36,73,91,109,125,131,161],"Internet.":[34],"However,":[35],"may":[40],"mixed":[42],"by":[43,47],"accompaniments":[44],"or":[45,120],"contaminated":[46],"environmental":[48],"noises":[49],"due":[50],"recording":[52],"conditions.":[53,169],"this":[55],"paper,":[56],"we":[57],"propose":[58],"noise":[60,74,79,98,102,114,117,168],"robust":[61],"synthesizer":[64,93,133],"incorporates":[66],"Gaussian":[67],"Mixture":[68],"Variational":[69],"Autoencoder":[70],"(GMVAE)":[71],"as":[72],"encoder":[75],"handle":[77],"different":[78],"conditions,":[80],"generating":[81],"clean":[82,121,136],"from":[85,151],"lyrics":[86],"for":[87,116,141],"target":[88,142],"speaker.":[89],"Specifically,":[90],"proposed":[92,132],"learns":[94],"multi-modal":[96],"latent":[97],"representation":[99,118],"various":[101],"conditions":[103],"in":[104],"continuous":[106],"space":[107],"without":[108],"use":[110],"an":[112],"auxiliary":[113],"classifier":[115],"learning":[119],"reference":[122],"audio":[123],"during":[124],"inference":[126],"stage.":[127],"Experiments":[128,158],"show":[129,160],"generate":[135],"speaker":[143],"with":[144,155],"MOS":[145],"close":[146],"reconstructed":[148],"ground":[152],"truth":[153],"mel-spectrogram":[154],"Griffin-Lim":[156],"vocoder.":[157],"also":[159],"robustness":[162],"our":[164],"approach":[165],"under":[166],"complex":[167]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}