{"id":"https://openalex.org/W4283455388","doi":"https://doi.org/10.21437/interspeech.2022-10994","title":"Adversarial Multi-Task Learning for Disentangling Timbre and Pitch in Singing Voice Synthesis","display_name":"Adversarial Multi-Task Learning for Disentangling Timbre and Pitch in Singing Voice Synthesis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283455388","doi":"https://doi.org/10.21437/interspeech.2022-10994"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10994","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10994","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/A5100400949","display_name":"Taewoo Kim","orcid":"https://orcid.org/0000-0002-7750-3736"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Woo Kim","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT Corp., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT Corp., Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042301449","display_name":"Min-Su Kang","orcid":"https://orcid.org/0000-0001-6491-2277"},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Min-Su Kang","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT Corp., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT Corp., Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065639840","display_name":"Gyeong-Hoon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210135449","display_name":"NCSOFT (South Korea)","ror":"https://ror.org/03q4mza74","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210135449"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gyeong-Hoon Lee","raw_affiliation_strings":["Speech AI Lab., AI Center, NCSOFT Corp., Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Speech AI Lab., AI Center, NCSOFT Corp., Republic of Korea","institution_ids":["https://openalex.org/I4210135449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5042301449"],"corresponding_institution_ids":["https://openalex.org/I4210135449"],"apc_list":null,"apc_paid":null,"fwci":0.4162,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5602004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3008","last_page":"3012"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9994000196456909,"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":0.9988999962806702,"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/timbre","display_name":"Timbre","score":0.9217292070388794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7401258945465088},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7263588905334473},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7193341255187988},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7059451937675476},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.47935324907302856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2770787477493286},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15572571754455566},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.09598970413208008},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08634716272354126}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.9217292070388794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401258945465088},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7263588905334473},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7193341255187988},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7059451937675476},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.47935324907302856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2770787477493286},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15572571754455566},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.09598970413208008},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08634716272354126},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10994","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10994","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":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1533861849","https://openalex.org/W2346842942","https://openalex.org/W2471520273","https://openalex.org/W2593414223","https://openalex.org/W2767052532","https://openalex.org/W2903032817","https://openalex.org/W2946200149","https://openalex.org/W2963609956","https://openalex.org/W2964243274","https://openalex.org/W2973046048","https://openalex.org/W3015219411","https://openalex.org/W3015338123","https://openalex.org/W3015516707","https://openalex.org/W3016250102","https://openalex.org/W3033411150","https://openalex.org/W3048768961","https://openalex.org/W3097514409","https://openalex.org/W3097777922","https://openalex.org/W3141797743","https://openalex.org/W3150572638","https://openalex.org/W3159302906","https://openalex.org/W3194338569","https://openalex.org/W3196760057","https://openalex.org/W3212754542","https://openalex.org/W4206319965","https://openalex.org/W4287111234","https://openalex.org/W4287111656","https://openalex.org/W4287672314","https://openalex.org/W4288265053","https://openalex.org/W4320013936"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2390529913","https://openalex.org/W2406877384","https://openalex.org/W2142368101","https://openalex.org/W2372249404","https://openalex.org/W2595839522","https://openalex.org/W2367547137","https://openalex.org/W2354994102","https://openalex.org/W4288088492","https://openalex.org/W2982290989"],"abstract_inverted_index":{"Recently,":[0],"deep":[1],"learning-based":[2],"generative":[3,123],"models":[4],"have":[5,49],"been":[6],"introduced":[7],"to":[8,14,40,60,82,129],"generate":[9,147],"singing":[10,75,134,150],"voices.One":[11],"approach":[12,25,38],"is":[13,35,39,127],"predict":[15,41],"the":[16,27,30,55,63,99,106,114,120,131,153,160],"parametric":[17,47,90,100,162],"vocoder":[18,91,101],"features":[19,57,87,102],"consisting":[20],"of":[21,32,51,119,133],"explicit":[22],"speech":[23],"parameters.This":[24],"has":[26],"advantage":[28],"that":[29,142],"meaning":[31],"each":[33],"feature":[34],"explicitly":[36],"distinguished.Another":[37],"mel-spectrograms":[42,93],"for":[43,88,94],"a":[44,74,89,95,122,137],"neural":[45,96],"vocoder.However,":[46],"vocoders":[48],"limitations":[50],"voice":[52,76],"quality":[53,132],"and":[54,65,92,112,116],"mel-spectrogram":[56],"are":[58,68],"difficult":[59],"model":[61,78,108,145],"because":[62],"timbre":[64,115],"pitch":[66,117],"information":[67],"entangled.In":[69],"this":[70],"study,":[71],"we":[72],"propose":[73],"synthesis":[77],"with":[79],"multi-task":[80],"learning":[81],"use":[83],"both":[84],"approaches":[85],"-acoustic":[86],"vocoder.By":[97],"using":[98],"as":[103],"auxiliary":[104],"features,":[105],"proposed":[107,144],"can":[109,146],"efficiently":[110],"disentangle":[111],"control":[113],"components":[118],"mel-spectrogram.Moreover,":[121],"adversarial":[124],"network":[125],"framework":[126],"applied":[128],"improve":[130],"voices":[135,151],"in":[136],"multi-singer":[138],"model.Experimental":[139],"results":[140],"demonstrate":[141],"our":[143],"more":[148],"natural":[149],"than":[152,159],"single-task":[154],"models,":[155],"while":[156],"performing":[157],"better":[158],"conventional":[161],"vocoder-based":[163],"model.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}