{"id":"https://openalex.org/W4416798429","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249391","title":"Singing MIDI Transcription with Music Language Models: Formulation and Comparison","display_name":"Singing MIDI Transcription with Music Language Models: Formulation and Comparison","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798429","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249391"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5110389632","display_name":"Yoriatsu Sugimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yu Sugimoto","raw_affiliation_strings":["Kyushu University,Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University,Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016862479","display_name":"Jun-You Wang","orcid":"https://orcid.org/0000-0002-9119-9259"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jun-You Wang","raw_affiliation_strings":["National Taiwan Normal University,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan Normal University,Taiwan","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038264558","display_name":"Li Su","orcid":"https://orcid.org/0000-0003-4275-8832"},"institutions":[{"id":"https://openalex.org/I84653119","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784","country_code":"TW","type":"facility","lineage":["https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Li Su","raw_affiliation_strings":["Academia Sinica,Taiwan"],"affiliations":[{"raw_affiliation_string":"Academia Sinica,Taiwan","institution_ids":["https://openalex.org/I84653119"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043140898","display_name":"Eita Nakamura","orcid":"https://orcid.org/0000-0003-4097-6027"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eita Nakamura","raw_affiliation_strings":["Kyushu University,Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University,Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110389632"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47761507,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"310","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9602000117301941,"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":0.9602000117301941,"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":0.012299999594688416,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.007799999788403511,"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/midi","display_name":"MIDI","score":0.8266000151634216},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7049999833106995},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.6657000184059143},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.48500001430511475},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.45190000534057617},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4235000014305115},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.37279999256134033}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.8266000151634216},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7049999833106995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6956999897956848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754000186920166},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.6657000184059143},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.45190000534057617},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.322299987077713},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.28450000286102295},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.27250000834465027},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249391","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249391","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2104112890","https://openalex.org/W2160815625","https://openalex.org/W2198584637","https://openalex.org/W2799373499","https://openalex.org/W2962760690","https://openalex.org/W2986673441","https://openalex.org/W3152594694","https://openalex.org/W3160649916","https://openalex.org/W4311187172","https://openalex.org/W4388017359","https://openalex.org/W4403199175","https://openalex.org/W4407784140"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"investigates":[2],"the":[3,14,18,29,84,101,126],"use":[4],"of":[5,16,25,125],"music":[6],"language":[7],"models":[8,43],"(LMs)":[9],"in":[10,28,67],"singing":[11],"MIDI":[12],"transcription,":[13],"task":[15],"estimating":[17],"pitch,":[19],"onset":[20],"time,":[21],"and":[22,63,76,87,100,123,129],"offset":[23],"time":[24],"each":[26],"note":[27,65,85],"vocal":[30],"part":[31],"from":[32],"a":[33,91,116],"musical":[34],"audio":[35],"signal.":[36],"While":[37],"recent":[38],"studies":[39],"have":[40],"investigated":[41],"acoustic":[42,93,118],"that":[44,79,107],"predict":[45],"pitch":[46,61,81],"frame":[47,49],"by":[48],"using":[50,95],"deep":[51],"neural":[52],"networks":[53],"(DNNs),":[54],"transcription":[55,113],"errors":[56],"remain":[57],"due":[58],"to":[59],"large":[60],"fluctuations":[62],"ambiguous":[64],"boundaries":[66],"singing.":[68],"To":[69],"address":[70],"this":[71],"issue,":[72],"we":[73],"formulate":[74],"Markov-":[75],"DNN-based":[77,92],"LMs":[78,128],"estimate":[80],"probabilities":[82],"at":[83],"level,":[86],"integrate":[88],"them":[89],"with":[90],"model":[94],"two":[96],"methods:":[97],"generative":[98],"modeling":[99],"sequential":[102],"transducer.":[103],"Experimental":[104],"results":[105],"show":[106],"both":[108],"integration":[109,130],"methods":[110,131],"significantly":[111],"improve":[112],"accuracy":[114],"over":[115],"baseline":[117],"model.":[119],"Moreover,":[120],"different":[121],"strengths":[122],"characteristics":[124],"compared":[127],"are":[132],"discussed.":[133]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}