{"id":"https://openalex.org/W3206801991","doi":"https://doi.org/10.1109/icassp43922.2022.9747441","title":"KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE Using Mel-Spectrograms","display_name":"KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE Using Mel-Spectrograms","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3206801991","doi":"https://doi.org/10.1109/icassp43922.2022.9747441","mag":"3206801991"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747441","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5034891715","display_name":"Chien-Feng Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143126","display_name":"Acer (Taiwan)","ror":"https://ror.org/03xajsx66","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210143126"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Feng Liao","raw_affiliation_strings":["Taiwan AI Labs,Taiwan","Taiwan AI Labs, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs,Taiwan","institution_ids":["https://openalex.org/I4210143126"]},{"raw_affiliation_string":"Taiwan AI Labs, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101719938","display_name":"Jen-Yu Liu","orcid":"https://orcid.org/0000-0003-1299-6688"},"institutions":[{"id":"https://openalex.org/I4210143126","display_name":"Acer (Taiwan)","ror":"https://ror.org/03xajsx66","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210143126"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jen-Yu Liu","raw_affiliation_strings":["Taiwan AI Labs,Taiwan","Taiwan AI Labs, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs,Taiwan","institution_ids":["https://openalex.org/I4210143126"]},{"raw_affiliation_string":"Taiwan AI Labs, Taiwan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210143126","display_name":"Acer (Taiwan)","ror":"https://ror.org/03xajsx66","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210143126"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yi-Hsuan Yang","raw_affiliation_strings":["Taiwan AI Labs,Taiwan","Taiwan AI Labs, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs,Taiwan","institution_ids":["https://openalex.org/I4210143126"]},{"raw_affiliation_string":"Taiwan AI Labs, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210143126"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"956","last_page":"960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8195801973342896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7256630659103394},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7076045870780945},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7016974687576294},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.5276126861572266},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4125269055366516},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41227084398269653},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3752659261226654}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8195801973342896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7256630659103394},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7076045870780945},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7016974687576294},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5276126861572266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4125269055366516},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41227084398269653},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3752659261226654},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747441","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W29794711","https://openalex.org/W854541894","https://openalex.org/W2030149476","https://openalex.org/W2124097505","https://openalex.org/W2127141656","https://openalex.org/W2408435475","https://openalex.org/W2516406502","https://openalex.org/W2752796333","https://openalex.org/W2789543585","https://openalex.org/W2889244839","https://openalex.org/W2921576841","https://openalex.org/W2938704169","https://openalex.org/W2953022181","https://openalex.org/W2963403868","https://openalex.org/W2963609956","https://openalex.org/W2963799213","https://openalex.org/W2964026424","https://openalex.org/W2964243274","https://openalex.org/W2970006822","https://openalex.org/W2971074500","https://openalex.org/W2972867623","https://openalex.org/W2973046048","https://openalex.org/W2996287690","https://openalex.org/W3015315843","https://openalex.org/W3015437531","https://openalex.org/W3015499232","https://openalex.org/W3021164770","https://openalex.org/W3024605872","https://openalex.org/W3024973272","https://openalex.org/W3034573343","https://openalex.org/W3037798801","https://openalex.org/W3081279708","https://openalex.org/W3082910224","https://openalex.org/W3096437652","https://openalex.org/W3097514409","https://openalex.org/W3114301328","https://openalex.org/W3133405188","https://openalex.org/W3133525064","https://openalex.org/W3140429000","https://openalex.org/W3174758275","https://openalex.org/W3197103763","https://openalex.org/W3204116061","https://openalex.org/W4287802874","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6678318511","https://openalex.org/W6739901393","https://openalex.org/W6748381668","https://openalex.org/W6761551260","https://openalex.org/W6762931180","https://openalex.org/W6767111847","https://openalex.org/W6771665576","https://openalex.org/W6776218486","https://openalex.org/W6777028661","https://openalex.org/W6779709467","https://openalex.org/W6783382068","https://openalex.org/W6790720088","https://openalex.org/W6796730497"],"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/W2566616303","https://openalex.org/W4402568167","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,73,94],"propose":[4],"a":[5,13,36,54,75,100,140,156],"novel":[6],"neural":[7],"network":[8],"model":[9,56],"called":[10],"KaraSinger":[11,34,161],"for":[12,98,124],"less-studied":[14],"singing":[15,46],"voice":[16],"synthesis":[17],"(SVS)":[18],"task":[19],"named":[20],"score-free":[21],"SVS,":[22],"in":[23,165],"which":[24],"the":[25,43,62,66,70,83,91,104,109,115,119,132,135,169],"prosody":[26],"and":[27,53,108,121,127,168],"melody":[28],"are":[29],"spontaneously":[30],"decided":[31],"by":[32,149],"machine.":[33],"comprises":[35],"vector-quantized":[37],"variational":[38],"autoencoder":[39],"(VQ-VAE)":[40],"that":[41,58,160],"compresses":[42],"Mel-spectrograms":[44],"of":[45,50,117,134,143,155],"audio":[47],"to":[48,60,81,86],"sequences":[49],"discrete":[51,63,84,111],"codes,":[52],"language":[55],"(LM)":[57],"learns":[59],"predict":[61],"codes":[64,85],"given":[65],"corresponding":[67],"lyrics.":[68],"For":[69,90],"VQ-VAE":[71,120],"part,":[72,93],"employ":[74],"Connectionist":[76],"Temporal":[77],"Classification":[78],"(CTC)":[79],"loss":[80],"encourage":[82],"carry":[87],"phoneme-related":[88],"information.":[89],"LM":[92,122],"use":[95],"location-sensitive":[96],"attention":[97],"learning":[99],"robust":[101],"alignment":[102],"between":[103],"input":[105],"phoneme":[106],"sequence":[107],"output":[110],"code.":[112],"We":[113,130],"keep":[114],"architecture":[116],"both":[118],"light-weight":[123],"fast":[125],"training":[126],"inference":[128],"speed.":[129],"validate":[131],"effectiveness":[133],"proposed":[136],"design":[137],"choices":[138],"using":[139],"proprietary":[141],"collection":[142],"550":[144],"English":[145],"pop":[146],"songs":[147],"sung":[148],"multiple":[150],"amateur":[151],"singers.":[152],"The":[153],"result":[154],"listening":[157],"test":[158],"shows":[159],"achieves":[162],"high":[163],"scores":[164],"intelligibility,":[166],"musicality,":[167],"overall":[170],"quality.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}