{"id":"https://openalex.org/W4297678710","doi":"https://doi.org/10.1145/3549737.3549754","title":"Transformer-Based Music Language Modelling and Transcription","display_name":"Transformer-Based Music Language Modelling and Transcription","publication_year":2022,"publication_date":"2022-09-07","ids":{"openalex":"https://openalex.org/W4297678710","doi":"https://doi.org/10.1145/3549737.3549754"},"language":"en","primary_location":{"id":"doi:10.1145/3549737.3549754","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3549737.3549754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Hellenic Conference on Artificial Intelligence","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/A5073436351","display_name":"Christos Zonios","orcid":"https://orcid.org/0000-0003-4072-5842"},"institutions":[{"id":"https://openalex.org/I194019607","display_name":"University of Ioannina","ror":"https://ror.org/01qg3j183","country_code":"GR","type":"education","lineage":["https://openalex.org/I194019607"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Christos Zonios","raw_affiliation_strings":["University of Ioannina, Greece"],"affiliations":[{"raw_affiliation_string":"University of Ioannina, Greece","institution_ids":["https://openalex.org/I194019607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033894687","display_name":"John Pavlopoulos","orcid":"https://orcid.org/0000-0001-9188-7425"},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]},{"id":"https://openalex.org/I149461666","display_name":"Ca' Foscari University of Venice","ror":"https://ror.org/04yzxz566","country_code":"IT","type":"education","lineage":["https://openalex.org/I149461666"]}],"countries":["GR","IT"],"is_corresponding":false,"raw_author_name":"John Pavlopoulos","raw_affiliation_strings":["Ca' Foscari, University of Venice, Italy and Athens University of Economics and Business, Greece"],"affiliations":[{"raw_affiliation_string":"Ca' Foscari, University of Venice, Italy and Athens University of Economics and Business, Greece","institution_ids":["https://openalex.org/I73142707","https://openalex.org/I149461666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007939716","display_name":"Aristidis Likas","orcid":"https://orcid.org/0000-0003-3170-5428"},"institutions":[{"id":"https://openalex.org/I194019607","display_name":"University of Ioannina","ror":"https://ror.org/01qg3j183","country_code":"GR","type":"education","lineage":["https://openalex.org/I194019607"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Aristidis Likas","raw_affiliation_strings":["University of Ioannina, Greece"],"affiliations":[{"raw_affiliation_string":"University of Ioannina, Greece","institution_ids":["https://openalex.org/I194019607"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073436351"],"corresponding_institution_ids":["https://openalex.org/I194019607"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10921962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T13996","display_name":"Diverse Musicological Studies","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7899099588394165},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598795890808105},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6850805878639221},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.6286118030548096},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5340589284896851},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5233832597732544},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5013256072998047},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.45136570930480957},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4507009983062744},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.41926127672195435},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.41619449853897095},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4053075909614563},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4040790796279907},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2395598590373993},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17078876495361328},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10930448770523071},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10323753952980042},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07764649391174316}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7899099588394165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598795890808105},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6850805878639221},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.6286118030548096},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5340589284896851},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5233832597732544},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5013256072998047},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.45136570930480957},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4507009983062744},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.41926127672195435},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.41619449853897095},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4053075909614563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4040790796279907},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2395598590373993},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17078876495361328},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10930448770523071},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10323753952980042},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07764649391174316},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3549737.3549754","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3549737.3549754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th Hellenic Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8399999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2105143211","https://openalex.org/W2131774270","https://openalex.org/W2198584637","https://openalex.org/W2317919972","https://openalex.org/W2892181857","https://openalex.org/W2906214917","https://openalex.org/W2927431361","https://openalex.org/W2950784811","https://openalex.org/W3021934057"],"related_works":["https://openalex.org/W2156218549","https://openalex.org/W2014970400","https://openalex.org/W1896852351","https://openalex.org/W4320485815","https://openalex.org/W4361757600","https://openalex.org/W1978173276","https://openalex.org/W2765714965","https://openalex.org/W2048023951","https://openalex.org/W1490654608","https://openalex.org/W2396258569"],"abstract_inverted_index":{"Automatic":[0],"Music":[1,52],"Transcription":[2],"(AMT)":[3],"is":[4,61,84],"the":[5,93,97,109,124],"process":[6],"of":[7,15,27,99],"extracting":[8],"information":[9],"from":[10,102],"audio":[11],"into":[12],"some":[13],"form":[14],"music":[16,28,45],"notation.":[17],"This":[18],"challenging":[19],"task":[20],"requires":[21],"significant":[22],"prior":[23],"knowledge":[24],"and":[25,70,116],"understanding":[26],"language.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"examine":[34],"Transformer-based":[35],"approaches":[36],"for":[37,58,74,82,92],"performing":[38],"AMT":[39,83,129],"on":[40,63,111],"piano":[41],"recordings":[42],"by":[43],"learning":[44,73,101],"language":[46],"representations.":[47],"We":[48,107,121],"propose":[49],"a":[50,79,89,112],"new":[51],"Language":[53,104],"Modelling":[54],"(MusicLM)":[55],"pre-training":[56],"approach":[57],"Transformers.":[59],"It":[60],"based":[62],"an":[64],"appropriately":[65,87],"defined":[66],"transcription":[67],"error-correction":[68],"task,":[69,115],"enables":[71],"transfer":[72,100],"various":[75],"musical":[76],"tasks.":[77],"Furthermore,":[78],"novel":[80],"model":[81],"proposed":[85],"that":[86],"exploits":[88],"BERT":[90],"Transformer":[91,110],"MusicLM":[94,114],"problem,":[95],"showing":[96],"potential":[98],"Natural":[103],"to":[105],"MusicLM.":[106],"apply":[108],"Masked":[113],"achieve":[117],"musically":[118],"coherent":[119],"results.":[120],"also":[122],"replace":[123],"RNNs":[125],"used":[126],"in":[127,137],"current":[128],"models":[130],"with":[131],"pre-trained":[132],"BERT-based":[133],"Transformers,":[134],"achieving":[135],"improvements":[136],"AUC.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
