{"id":"https://openalex.org/W4416251033","doi":"https://doi.org/10.1109/waspaa66052.2025.11230954","title":"Learn from Virtual Guitar: A Comparative Analysis of Automatic Guitar Transcription using Synthetic and Real Audio","display_name":"Learn from Virtual Guitar: A Comparative Analysis of Automatic Guitar Transcription using Synthetic and Real Audio","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416251033","doi":"https://doi.org/10.1109/waspaa66052.2025.11230954"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5049938038","display_name":"Yuta Kusaka","orcid":"https://orcid.org/0009-0004-4921-5253"},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuta Kusaka","raw_affiliation_strings":["Yamaha Corporation,MINA Lab,Japan"],"affiliations":[{"raw_affiliation_string":"Yamaha Corporation,MINA Lab,Japan","institution_ids":["https://openalex.org/I1295929820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056563843","display_name":"Akira Maezawa","orcid":null},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akira Maezawa","raw_affiliation_strings":["Yamaha Corporation,MINA Lab,Japan"],"affiliations":[{"raw_affiliation_string":"Yamaha Corporation,MINA Lab,Japan","institution_ids":["https://openalex.org/I1295929820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5049938038"],"corresponding_institution_ids":["https://openalex.org/I1295929820"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45362935,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.859000027179718,"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":0.859000027179718,"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":0.11659999936819077,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/guitar","display_name":"Guitar","score":0.8378000259399414},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.7343999743461609},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6159999966621399},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44290000200271606},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2827000021934509}],"concepts":[{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.8378000259399414},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.7343999743461609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700999736785889},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6159999966621399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4909000098705292},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33379998803138733},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C2985331491","wikidata":"https://www.wikidata.org/wiki/Q5227298","display_name":"Data format","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230954","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230954","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2906214917","https://openalex.org/W2998490864","https://openalex.org/W3209419355","https://openalex.org/W4221165926","https://openalex.org/W4225281045","https://openalex.org/W4372260308","https://openalex.org/W4372267640","https://openalex.org/W4386696315","https://openalex.org/W4391640266","https://openalex.org/W4392903082","https://openalex.org/W4392904560","https://openalex.org/W4392904621","https://openalex.org/W4404609564","https://openalex.org/W4408353505"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,37,76,153],"effectiveness":[4,77],"of":[5,39,80,155],"using":[6],"synthetic":[7,40,64,81,97,110,124,139,156],"audio,":[8],"generated":[9],"from":[10,27],"musical":[11],"scores":[12],"via":[13],"virtual":[14],"instrument":[15],"software,":[16],"for":[17,45,128,158],"training":[18,159],"automatic":[19,47],"guitar":[20,65,98],"transcription":[21,49,132],"models.":[22,51],"Collecting":[23],"large":[24],"annotated":[25],"datasets":[26,125],"real":[28,72,103,119,142,163],"performances":[29],"is":[30,112,166],"costly":[31],"and":[32,68,78,95,130,141],"labor-intensive.":[33],"To":[34],"overcome":[35],"this,":[36],"use":[38],"data":[41,66,73,82,99,111,140,157,165],"has":[42],"been":[43],"explored":[44],"developing":[46],"music":[48],"(AMT)":[50],"We":[52],"present":[53],"a":[54,58],"systematic":[55],"comparison":[56],"between":[57,135],"high-resolution":[59],"AMT":[60,160],"models":[61,69,91,136,161],"trained":[62,70,92,137],"on":[63,71,93,138],"(SynthTab)":[67],"(GAPS),":[74],"clarifying":[75],"limitations":[79],"in":[83],"AMT.":[84],"Our":[85],"experiments":[86],"yield":[87],"four":[88],"insights:":[89],"1)":[90],"diverse":[94],"well-augmented":[96],"generalize":[100],"well":[101],"to":[102],"recordings,":[104],"2)":[105],"pre-training":[106],"with":[107,116],"target":[108],"instrument\u2019s":[109,118],"more":[113],"effective":[114],"than":[115],"non-target":[117],"data,":[120,143],"3)":[121],"even":[122],"small":[123],"are":[126],"valuable":[127],"pre-training,":[129],"4)":[131],"discrepancies":[133],"arise":[134],"which":[144],"can":[145],"be":[146],"mitigated":[147],"by":[148],"fine-tuning.":[149],"These":[150],"results":[151],"demonstrate":[152],"utility":[154],"when":[162],"aligned":[164],"scarce.":[167]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}