{"id":"https://openalex.org/W4388465899","doi":"https://doi.org/10.3233/ida-227077","title":"Note-level singing melody transcription with transformers","display_name":"Note-level singing melody transcription with transformers","publication_year":2023,"publication_date":"2023-11-07","ids":{"openalex":"https://openalex.org/W4388465899","doi":"https://doi.org/10.3233/ida-227077"},"language":"en","primary_location":{"id":"doi:10.3233/ida-227077","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-227077","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis","raw_type":"journal-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/A5045603679","display_name":"Jonggwon Park","orcid":"https://orcid.org/0000-0003-4131-0729"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jonggwon Park","raw_affiliation_strings":["Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011987251","display_name":"Kyoyun Choi","orcid":"https://orcid.org/0000-0002-8240-4716"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kyoyun Choi","raw_affiliation_strings":["Institute of Engineering Research, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Engineering Research, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101264625","display_name":"Seola Oh","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seola Oh","raw_affiliation_strings":["Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013331634","display_name":"Leekyung Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Leekyung Kim","raw_affiliation_strings":["Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102823810","display_name":"Jonghun Park","orcid":"https://orcid.org/0000-0001-7505-110X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jonghun Park","raw_affiliation_strings":["Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Institute for Industrial Systems Innovation, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011987251"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.1843,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45480995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"27","issue":"6","first_page":"1853","last_page":"1871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9991000294685364,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8399325609207153},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.7257815003395081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7218483686447144},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6882857084274292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6843880414962769},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.4274597465991974},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1308130919933319},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06803321838378906}],"concepts":[{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.8399325609207153},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7257815003395081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7218483686447144},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6882857084274292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6843880414962769},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.4274597465991974},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1308130919933319},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06803321838378906},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/ida-227077","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-227077","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Intelligent Data Analysis","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1990908299","https://openalex.org/W2007321142","https://openalex.org/W2091425152","https://openalex.org/W2118774185","https://openalex.org/W2191779130","https://openalex.org/W2896271387","https://openalex.org/W2903105043","https://openalex.org/W2932319787","https://openalex.org/W2954996726","https://openalex.org/W2962866891","https://openalex.org/W2964159205","https://openalex.org/W2964177567","https://openalex.org/W3011176162","https://openalex.org/W3037149862","https://openalex.org/W3160649916","https://openalex.org/W3161758688","https://openalex.org/W4221159539","https://openalex.org/W4288089799","https://openalex.org/W6602863177","https://openalex.org/W6603394118","https://openalex.org/W6675069661","https://openalex.org/W6769627184"],"related_works":["https://openalex.org/W2390529913","https://openalex.org/W2406877384","https://openalex.org/W2372249404","https://openalex.org/W2595839522","https://openalex.org/W2367547137","https://openalex.org/W3016250102","https://openalex.org/W4288088492","https://openalex.org/W2982290989","https://openalex.org/W2028097510","https://openalex.org/W2505877856"],"abstract_inverted_index":{"Recognizing":[0],"a":[1,29,72,88,95,189,215],"singing":[2,22,74,82,148,163],"melody":[3,23,75,83,90,149,164,191],"from":[4],"an":[5],"audio":[6],"signal":[7],"in":[8,32,129,146,161],"terms":[9],"of":[10,35,50,56,60,106,142,180,188,202,214],"the":[11,33,45,54,61,104,107,134,140,143,169,176,181,200,203,212],"music":[12,37],"notes\u2019":[13],"pitch":[14,114],"onset":[15,57],"and":[16,48,53,58,92,116,117,132,153],"offset,":[17],"referred":[18],"to":[19,44,102,126,186],"as":[20,28,87,94,208],"note-level":[21,73,147,162],"transcription,":[24,150],"has":[25],"been":[26],"studied":[27],"critical":[30],"task":[31,40],"field":[34],"automatic":[36],"transcription.":[38],"The":[39,81,155],"is":[41,85,100,184],"challenging":[42],"due":[43],"different":[46],"timbre":[47],"vibrato":[49],"each":[51],"vocal":[52,190],"ambiguity":[55],"offset":[59],"human":[62,196],"voice":[63,177],"compared":[64],"with":[65,121],"other":[66,159],"instrumental":[67],"sounds.":[68],"This":[69],"paper":[70],"proposes":[71],"transcription":[76,165],"model":[77,135,157,183],"using":[78],"sequence-to-sequence":[79],"Transformers.":[80],"annotation":[84],"expressed":[86],"monophonic":[89],"sequence":[91],"used":[93],"decoder":[96],"sequence.":[97],"Overlapping":[98],"decoding":[99],"introduced":[101],"solve":[103],"problem":[105],"context":[108],"between":[109],"segments":[110],"being":[111],"broken.":[112],"Applying":[113],"augmentation":[115],"adding":[118],"noisy":[119],"dataset":[120],"data":[122],"cleansing":[123],"turns":[124],"out":[125],"be":[127],"effective":[128],"preventing":[130],"overfitting":[131],"generalizing":[133],"performance.":[136],"Ablation":[137],"studies":[138],"demonstrate":[139],"effects":[141],"proposed":[144,156,182,204],"techniques":[145],"both":[151],"quantitatively":[152],"qualitatively.":[154],"outperforms":[158],"models":[160,205],"performance":[166,179],"for":[167],"all":[168],"metrics":[170],"considered.":[171],"For":[172],"fundamental":[173],"frequency":[174],"metrics,":[175],"detection":[178],"comparable":[185],"that":[187,199],"extraction":[192],"model.":[193],"Finally,":[194],"subjective":[195],"evaluation":[197],"demonstrates":[198],"results":[201,213],"are":[206],"perceived":[207],"more":[209],"accurate":[210],"than":[211],"previous":[216],"study.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}
