{"id":"https://openalex.org/W4392904560","doi":"https://doi.org/10.1109/icassp48485.2024.10447902","title":"SynthTab: Leveraging Synthesized Data for Guitar Tablature Transcription","display_name":"SynthTab: Leveraging Synthesized Data for Guitar Tablature Transcription","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904560","doi":"https://doi.org/10.1109/icassp48485.2024.10447902"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5104268516","display_name":"Yongyi Zang","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yongyi Zang","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667719","display_name":"Yi Zhong","orcid":"https://orcid.org/0000-0001-5584-0988"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zhong","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074979798","display_name":"Frank Cwitkowitz","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank Cwitkowitz","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102749436","display_name":"Zhiyao Duan","orcid":"https://orcid.org/0000-0002-8334-9974"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyao Duan","raw_affiliation_strings":["University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester,Department of Electrical and Computer Engineering,Rochester,NY,USA","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104268516"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":2.3908,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88835312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1286","last_page":"1290"},"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":0.9991000294685364,"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/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/guitar","display_name":"Guitar","score":0.88532555103302},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8201771974563599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8078803420066833},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.5609191060066223},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5413574576377869},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.5187475681304932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4169454872608185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4110056161880493},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3899228572845459},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.11622866988182068},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09327682852745056}],"concepts":[{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.88532555103302},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8201771974563599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8078803420066833},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5609191060066223},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5413574576377869},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.5187475681304932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4169454872608185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4110056161880493},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3899228572845459},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.11622866988182068},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09327682852745056},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4392250869","display_name":"Collaborative Research: FW-HTF-R: Toward an Ecosystem of Artificial Intelligence-Powered Music Production (TEAMuP)","funder_award_id":"2222129","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4863407681","display_name":null,"funder_award_id":"1922591","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8327703227","display_name":null,"funder_award_id":"DGE-1922591","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2076608692","https://openalex.org/W2091425152","https://openalex.org/W2906214917","https://openalex.org/W2938817334","https://openalex.org/W2998490864","https://openalex.org/W3014809999","https://openalex.org/W3092879656","https://openalex.org/W3095303521","https://openalex.org/W4221165926","https://openalex.org/W4286857148","https://openalex.org/W4312831741","https://openalex.org/W4360612734","https://openalex.org/W4362563993","https://openalex.org/W4372267640","https://openalex.org/W6697040288","https://openalex.org/W6697229037","https://openalex.org/W6697326221","https://openalex.org/W6755182157","https://openalex.org/W6756341328","https://openalex.org/W6771364782","https://openalex.org/W6781484447","https://openalex.org/W6799000596","https://openalex.org/W6804324758","https://openalex.org/W6809958796"],"related_works":["https://openalex.org/W4220911637","https://openalex.org/W4362597605","https://openalex.org/W4385984930","https://openalex.org/W1574414179","https://openalex.org/W1990291079","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W3118230952","https://openalex.org/W2898671791","https://openalex.org/W2404247810"],"abstract_inverted_index":{"Guitar":[0,31],"tablature":[1],"is":[2,35,104],"a":[3,20,81,98,105,129,150],"form":[4],"of":[5,19,68,110,131],"music":[6,43],"notation":[7],"widely":[8],"used":[9],"among":[10],"guitarists.":[11],"It":[12],"captures":[13],"not":[14],"only":[15],"the":[16,29,125,135],"musical":[17],"content":[18],"piece,":[21],"but":[22],"also":[23],"its":[24],"implementation":[25],"and":[26,46,56,66,91,107,128,137,141,162],"ornamentation":[27],"on":[28,61,154,164],"instrument.":[30],"Tablature":[32],"Transcription":[33],"(GTT)":[34],"an":[36,165],"important":[37],"task":[38],"with":[39,178],"broad":[40],"applications":[41],"in":[42,54,134],"education,":[44],"composition,":[45],"entertainment.":[47],"Existing":[48],"GTT":[49,86,152],"datasets":[50],"are":[51],"quite":[52],"limited":[53],"size":[55],"scope,":[57],"rendering":[58],"models":[59],"trained":[60],"them":[62],"prone":[63],"to":[64,70,75,124],"overfitting":[65],"incapable":[67],"generalizing":[69],"out-of-domain":[71],"data.":[72],"In":[73],"order":[74],"address":[76],"this":[77],"issue,":[78],"we":[79],"present":[80],"methodology":[82],"for":[83,143],"synthesizing":[84],"large-scale":[85],"audio":[87,120],"using":[88],"commercial":[89],"acoustic":[90],"electric":[92],"guitar":[93],"plugins.":[94],"We":[95],"procure":[96],"SynthTab,":[97],"dataset":[99],"derived":[100],"from":[101],"DadaGP,":[102],"which":[103,121],"vast":[106],"diverse":[108],"collection":[109],"richly":[111],"annotated":[112],"symbolic":[113],"tablature.":[114],"The":[115],"proposed":[116],"synthesis":[117],"pipeline":[118],"produces":[119],"faithfully":[122],"adheres":[123],"original":[126],"fingerings":[127],"subset":[130],"techniques":[132],"specified":[133],"tablature,":[136],"covers":[138],"multiple":[139],"guitars":[140],"styles":[142],"each":[144],"track.":[145],"Experiments":[146],"show":[147,172],"that":[148,173],"pre-training":[149,174],"baseline":[151],"model":[153],"SynthTab":[155],"can":[156],"improve":[157],"transcription":[158],"performance":[159],"when":[160],"fine-tuning":[161],"testing":[163],"individual":[166],"dataset.":[167],"More":[168],"importantly,":[169],"cross-dataset":[170],"experiments":[171],"significantly":[175],"mitigates":[176],"issues":[177],"overfitting.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}