{"id":"https://openalex.org/W4221165926","doi":"https://doi.org/10.1109/icassp43922.2022.9747697","title":"Towards Automatic Transcription of Polyphonic Electric Guitar Music: A New Dataset and a Multi-Loss Transformer Model","display_name":"Towards Automatic Transcription of Polyphonic Electric Guitar Music: A New Dataset and a Multi-Loss Transformer Model","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221165926","doi":"https://doi.org/10.1109/icassp43922.2022.9747697"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747697","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100384510","display_name":"Yu\u2010Hua Chen","orcid":"https://orcid.org/0000-0001-6925-148X"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210143126","display_name":"Acer (Taiwan)","ror":"https://ror.org/03xajsx66","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210143126"]},{"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":"Yu-Hua Chen","raw_affiliation_strings":["Taiwan AI Labs,Taiwan","Academia Sinica, Taiwan","National Taiwan University, Taiwan","Taiwan AI Labs, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs,Taiwan","institution_ids":["https://openalex.org/I4210143126"]},{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Taiwan AI Labs, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086833741","display_name":"Wen-Yi Hsiao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143126","display_name":"Acer (Taiwan)","ror":"https://ror.org/03xajsx66","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210143126"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Yi Hsiao","raw_affiliation_strings":["Taiwan AI Labs,Taiwan","Taiwan AI Labs, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs,Taiwan","institution_ids":["https://openalex.org/I4210143126"]},{"raw_affiliation_string":"Taiwan AI Labs, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085825855","display_name":"Tsu-Kuang Hsieh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210143126","display_name":"Acer (Taiwan)","ror":"https://ror.org/03xajsx66","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210143126"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tsu-Kuang Hsieh","raw_affiliation_strings":["Taiwan AI Labs,Taiwan","Taiwan AI Labs, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs,Taiwan","institution_ids":["https://openalex.org/I4210143126"]},{"raw_affiliation_string":"Taiwan AI Labs, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["National Taiwan University,Taiwan","National Taiwan University, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061291906","display_name":"Yi\u2010Hsuan Yang","orcid":"https://orcid.org/0000-0002-2724-6161"},"institutions":[{"id":"https://openalex.org/I4210143126","display_name":"Acer (Taiwan)","ror":"https://ror.org/03xajsx66","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210143126"]},{"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":"Yi-Hsuan Yang","raw_affiliation_strings":["Taiwan AI Labs,Taiwan","Academia Sinica, Taiwan","Taiwan AI Labs, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Taiwan AI Labs,Taiwan","institution_ids":["https://openalex.org/I4210143126"]},{"raw_affiliation_string":"Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I84653119"]},{"raw_affiliation_string":"Taiwan AI Labs, Taiwan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8421,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.87309226,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"786","last_page":"790"},"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":0.9994000196456909,"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":0.9975000023841858,"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":0.9142745733261108},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7628320455551147},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.713473916053772},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.670958936214447},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6483604311943054},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.6398910284042358},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5822933912277222},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.5819693207740784},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.48267653584480286},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4265424907207489},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3873080611228943},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1714455783367157},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.17108756303787231},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.1093626320362091},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.10452550649642944}],"concepts":[{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.9142745733261108},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7628320455551147},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713473916053772},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.670958936214447},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6483604311943054},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.6398910284042358},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5822933912277222},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5819693207740784},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.48267653584480286},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4265424907207489},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3873080611228943},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1714455783367157},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.17108756303787231},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.1093626320362091},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.10452550649642944},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747697","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":52,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1526676615","https://openalex.org/W2001426554","https://openalex.org/W2023973629","https://openalex.org/W2036197063","https://openalex.org/W2055356414","https://openalex.org/W2096482524","https://openalex.org/W2097732069","https://openalex.org/W2105143211","https://openalex.org/W2110007838","https://openalex.org/W2118774185","https://openalex.org/W2198584637","https://openalex.org/W2296230291","https://openalex.org/W2394782790","https://openalex.org/W2397818963","https://openalex.org/W2523056285","https://openalex.org/W2577545569","https://openalex.org/W2902076983","https://openalex.org/W2906214917","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2952823162","https://openalex.org/W2958623036","https://openalex.org/W2963045359","https://openalex.org/W2963408210","https://openalex.org/W2991248973","https://openalex.org/W3047571292","https://openalex.org/W3165908916","https://openalex.org/W4206488305","https://openalex.org/W4287072584","https://openalex.org/W4293775315","https://openalex.org/W4320013936","https://openalex.org/W4385245566","https://openalex.org/W4394645529","https://openalex.org/W6631190155","https://openalex.org/W6697326221","https://openalex.org/W6712094209","https://openalex.org/W6727368055","https://openalex.org/W6732146819","https://openalex.org/W6733936739","https://openalex.org/W6739901393","https://openalex.org/W6745851314","https://openalex.org/W6753894231","https://openalex.org/W6755182157","https://openalex.org/W6756341328","https://openalex.org/W6764408361","https://openalex.org/W6771364782","https://openalex.org/W6781484447","https://openalex.org/W6798855526","https://openalex.org/W6799000596","https://openalex.org/W6806461207","https://openalex.org/W6949711019"],"related_works":["https://openalex.org/W4220911637","https://openalex.org/W4385984930","https://openalex.org/W4247286973","https://openalex.org/W1990291079","https://openalex.org/W3089777375","https://openalex.org/W2380085135","https://openalex.org/W2558300772","https://openalex.org/W4375868955","https://openalex.org/W2385208723","https://openalex.org/W2355890546"],"abstract_inverted_index":{"In":[0],"this":[1,41,56,94],"paper,":[2],"we":[3,26,50],"propose":[4],"a":[5,45,59],"new":[6],"dataset":[7,57],"named":[8],"EGDB,":[9],"that":[10,49],"contains":[11],"transcriptions":[12],"of":[13,18,30,62,68,73,79],"the":[14,28,38,66,71,77,88],"electric":[15],"guitar":[16,74],"performance":[17,29],"240":[19],"tablatures":[20],"rendered":[21],"with":[22,44],"different":[23],"tones.":[24],"Moreover,":[25],"benchmark":[27],"two":[31],"well-known":[32],"transcription":[33],"models":[34],"proposed":[35],"originally":[36],"for":[37,83,90,93],"piano":[39],"on":[40,55,70],"dataset,":[42],"along":[43],"multi-loss":[46],"Transformer":[47],"model":[48],"newly":[51],"propose.":[52],"Our":[53],"evaluation":[54],"and":[58],"separate":[60],"set":[61],"real-world":[63],"recordings":[64],"demonstrate":[65],"influence":[67],"timbre":[69],"accuracy":[72],"sheet":[75],"transcription,":[76],"potential":[78],"using":[80],"multiple":[81],"losses":[82],"Transformers,":[84],"as":[85,87],"well":[86],"room":[89],"further":[91],"improvement":[92],"task.":[95]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-08-14T07:06:38.338062","created_date":"2025-10-10T00:00:00"}
