{"id":"https://openalex.org/W4388186754","doi":"https://doi.org/10.1145/3625135.3625154","title":"Aligning Incomplete Lyrics of Korean Folk Song Dataset using Whisper","display_name":"Aligning Incomplete Lyrics of Korean Folk Song Dataset using Whisper","publication_year":2023,"publication_date":"2023-10-27","ids":{"openalex":"https://openalex.org/W4388186754","doi":"https://doi.org/10.1145/3625135.3625154"},"language":"en","primary_location":{"id":"doi:10.1145/3625135.3625154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625135.3625154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Digital Libraries for Musicology","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/A5101689108","display_name":"Danbinaerin Han","orcid":"https://orcid.org/0009-0008-1048-5466"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Danbinaerin Han","raw_affiliation_strings":["Department of Art &amp; Technology, Sogang University, South Korea"],"raw_orcid":"https://orcid.org/0009-0008-1048-5466","affiliations":[{"raw_affiliation_string":"Department of Art &amp; Technology, Sogang University, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101767955","display_name":"Daewoong Kim","orcid":"https://orcid.org/0009-0004-0841-2314"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daewoong Kim","raw_affiliation_strings":["Department of Artificial Intelligence, Sogang University, South Korea"],"raw_orcid":"https://orcid.org/0009-0004-0841-2314","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Sogang University, South Korea","institution_ids":["https://openalex.org/I148751991"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055794128","display_name":"Dasaem Jeong","orcid":"https://orcid.org/0009-0002-3655-1181"},"institutions":[{"id":"https://openalex.org/I148751991","display_name":"Sogang University","ror":"https://ror.org/056tn4839","country_code":"KR","type":"education","lineage":["https://openalex.org/I148751991"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dasaem Jeong","raw_affiliation_strings":["Department of Art &amp; Technology, Sogang University, South Korea"],"raw_orcid":"https://orcid.org/0009-0002-3655-1181","affiliations":[{"raw_affiliation_string":"Department of Art &amp; Technology, Sogang University, South Korea","institution_ids":["https://openalex.org/I148751991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101689108"],"corresponding_institution_ids":["https://openalex.org/I148751991"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14688951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9929999709129333,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9624999761581421,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.9642575979232788},{"id":"https://openalex.org/keywords/folk-song","display_name":"Folk song","score":0.5553017258644104},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5368900895118713},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3429664373397827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3270028829574585},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.23412060737609863},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.21785950660705566}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9642575979232788},{"id":"https://openalex.org/C2992446111","wikidata":"https://www.wikidata.org/wiki/Q43343","display_name":"Folk song","level":2,"score":0.5553017258644104},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5368900895118713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3429664373397827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3270028829574585},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.23412060737609863},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.21785950660705566}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625135.3625154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3625135.3625154","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th International Conference on Digital Libraries for Musicology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4451094943","display_name":null,"funder_award_id":"RS-2023-00252944","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W395933519","https://openalex.org/W2107092366","https://openalex.org/W2482558056","https://openalex.org/W2707788252","https://openalex.org/W2766730770","https://openalex.org/W2917340025","https://openalex.org/W4372260429"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2360952181","https://openalex.org/W4310670065","https://openalex.org/W634160686","https://openalex.org/W2597614303","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W437317580","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3,60],"introduce":[4,61],"a":[5,17,65,132],"method":[6],"for":[7,131],"time-alignment":[8],"of":[9,32,57,67,99,134],"lyrics":[10,36,43,85],"in":[11],"Korean":[12,33,136],"folk":[13,34,137],"song":[14,35],"audio":[15,47],"using":[16],"transformer":[18],"encoder-decoder":[19],"model":[20,81],"specifically":[21],"designed":[22],"to":[23,82],"utilize":[24],"incomplete":[25,84],"lyric":[26],"data.":[27],"We":[28,112],"analyzed":[29],"the":[30,42,45,55,80,87,97,100,104,110,115,126],"characteristics":[31],"and":[37,44,53,70,76,118,128],"found":[38],"some":[39],"discrepancies":[40],"between":[41],"corresponding":[46],"recordings.":[48],"To":[49],"address":[50],"these":[51],"challenges":[52],"maximize":[54],"use":[56],"existing":[58],"transcriptions,":[59],"RefWhisper.":[62],"This":[63],"is":[64],"variant":[66],"OpenAI\u2019s":[68],"Whisper":[69],"includes":[71],"an":[72],"extra":[73],"encoder":[74],"module":[75],"cross-attention":[77,92],"layer,":[78],"enabling":[79],"consult":[83],"during":[86],"transcription":[88,106],"process.":[89],"The":[90],"added":[91],"layer":[93],"facilitates":[94],"not":[95],"only":[96],"alignment":[98],"reference":[101],"text":[102],"with":[103,109],"predicted":[105],"but":[107],"also":[108],"audio.":[111],"make":[113],"public":[114],"transcribed":[116],"outcomes":[117],"timestamp":[119],"data,":[120],"which":[121],"are":[122],"aligned":[123],"at":[124],"both":[125],"sentence":[127],"word":[129],"levels,":[130],"corpus":[133],"13,801":[135],"songs.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
