{"id":"https://openalex.org/W6948839688","doi":"https://doi.org/10.5281/zenodo.10265341","title":"Sequence-to-Sequence Network Training Methods for Automatic Guitar Transcription With Tokenized Outputs","display_name":"Sequence-to-Sequence Network Training Methods for Automatic Guitar Transcription With Tokenized Outputs","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6948839688","doi":"https://doi.org/10.5281/zenodo.10265341"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265341","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265341","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sehun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sehun Kim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kazuya Takeda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tomoki Toda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41977153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12568","display_name":"Plant Taxonomy and Phylogenetics","score":0.1143999993801117,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12568","display_name":"Plant Taxonomy and Phylogenetics","score":0.1143999993801117,"subfield":{"id":"https://openalex.org/subfields/1105","display_name":"Ecology, Evolution, Behavior and Systematics"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.06300000101327896,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T14427","display_name":"Environmental Monitoring and Data Management","score":0.05310000106692314,"subfield":{"id":"https://openalex.org/subfields/1907","display_name":"Geology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/guitar","display_name":"Guitar","score":0.8230999708175659},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6115999817848206},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5677000284194946},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5271000266075134},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5019000172615051},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4528000056743622},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.37540000677108765},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.3682999908924103}],"concepts":[{"id":"https://openalex.org/C95543465","wikidata":"https://www.wikidata.org/wiki/Q6607","display_name":"Guitar","level":2,"score":0.8230999708175659},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6115999817848206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6054999828338623},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5019000172615051},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42750000953674316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2596000134944916},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.25440001487731934},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265341","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265341","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265341","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":""},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,121],"propose":[1],"multiple":[2],"methods":[3,47,86,129,150],"for":[4,32,48,106,133],"effectively":[5],"training":[6,49,92,134,180],"a":[7,28,56],"sequence-to-sequence":[8,33],"automatic":[9,34],"guitar":[10,35,153],"transcription":[11,36],"model":[12,31,54,60,147,169],"which":[13],"uses":[14,38],"tokenized":[15,39,140],"music":[16,40],"representation":[17],"as":[18],"an":[19,101,176],"output.":[20],"Our":[21,52,82],"proposed":[22,53,83,126,144,168],"method":[23],"mainly":[24],"consists":[25],"of":[26,91,161,179],"1)":[27,95,124],"hybrid":[29,145],"CTC-Attention":[30,146],"that":[37,123,138,151],"representation,":[41],"and":[42,79,109,157],"2)":[43,110,142],"two":[44],"data":[45,84,93,114,127],"augmentation":[46,85,128],"the":[50,68,76,89,125,159],"model.":[51],"is":[55,170,175],"generic":[57,135],"encoder-decoder":[58],"Transformer":[59,136],"but":[61],"adopts":[62],"multi-task":[63,162],"learning":[64,73,163],"with":[65,155,164],"CTC":[66,165],"from":[67],"encoder":[69],"to":[70,103,115],"speed":[71],"up":[72,88],"alignments":[74],"between":[75],"output":[77],"tokens":[78],"acoustic":[80],"features.":[81],"scale":[87],"amount":[90,178],"by":[94,111],"creating":[96],"bar":[97],"overlap":[98],"when":[99,173],"splitting":[100],"excerpt":[102],"be":[104],"used":[105],"network":[107],"input,":[108],"utilizing":[112],"MIDI-only":[113],"synthetically":[116],"create":[117],"audio-MIDI":[118],"pair":[119],"data.":[120,181],"confirmed":[122],"were":[130],"highly":[131],"effective":[132,172],"models":[137],"generate":[139],"outputs,":[141],"our":[143,167],"outperforms":[148],"conventional":[149],"transcribe":[152],"performance":[154],"tokens,":[156],"3)":[158],"addition":[160],"in":[166],"especially":[171],"there":[174],"insufficient":[177]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}