{"id":"https://openalex.org/W6948985863","doi":"https://doi.org/10.5281/zenodo.10265261","title":"Automatic Piano Transcription With Hierarchical Frequency-Time Transformer","display_name":"Automatic Piano Transcription With Hierarchical Frequency-Time Transformer","publication_year":2023,"publication_date":"2023-11-04","ids":{"openalex":"https://openalex.org/W6948985863","doi":"https://doi.org/10.5281/zenodo.10265261"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.10265261","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265261","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":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.10265261","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Keisuke Toyama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keisuke Toyama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Taketo Akama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taketo Akama","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yukara Ikemiya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukara Ikemiya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhta Takida","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhta Takida","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wei-Hsiang Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Hsiang Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yuki Mitsufuji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuki Mitsufuji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"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/T11228","display_name":"Bat Biology and Ecology Studies","score":0.15279999375343323,"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/T11228","display_name":"Bat Biology and Ecology Studies","score":0.15279999375343323,"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/T12640","display_name":"Environmental DNA in Biodiversity Studies","score":0.048500001430511475,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11913","display_name":"Animal Ecology and Behavior Studies","score":0.04670000076293945,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6444000005722046},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.5626999735832214},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5485000014305115},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.414900004863739},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.412200003862381},{"id":"https://openalex.org/keywords/frequency-offset","display_name":"Frequency offset","score":0.3142000138759613}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6444000005722046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5694000124931335},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5626999735832214},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5485000014305115},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4927000105381012},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C49319798","wikidata":"https://www.wikidata.org/wiki/Q5502874","display_name":"Frequency offset","level":4,"score":0.3142000138759613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C133770746","wikidata":"https://www.wikidata.org/wiki/Q856535","display_name":"Current transformer","level":4,"score":0.26649999618530273},{"id":"https://openalex.org/C117323899","wikidata":"https://www.wikidata.org/wiki/Q1907989","display_name":"Distribution transformer","level":4,"score":0.26600000262260437},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.10265261","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265261","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":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.10265261","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.10265261","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":"ConferencePaper"},"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":{"Taking":[0],"long-term":[1,50],"spectral":[2],"and":[3,23,55,97,137,141,159,163],"temporal":[4],"dependencies":[5,51],"into":[6,114],"account":[7],"is":[8,15,65,111],"essential":[9],"for":[10,25],"automatic":[11,67],"piano":[12,31],"transcription.":[13],"This":[14],"especially":[16],"helpful":[17],"when":[18],"determining":[19],"the":[20,29,40,53,87,94,103,106,115,125,133,148,151],"precise":[21],"onset":[22],"offset":[24],"each":[26],"note":[27],"in":[28,45,52,86,93,105,124],"polyphonic":[30],"content.":[32],"In":[33,58],"this":[34,59],"case,":[35],"we":[36,61],"may":[37],"rely":[38],"on":[39,146],"capability":[41],"of":[42,120,150],"self-attention":[43],"mechanism":[44],"Transformers":[46],"to":[47],"capture":[48],"these":[49],"frequency":[54,95,107],"time":[56,88,126],"axes.":[57],"work,":[60],"propose":[62],"hFT-Transformer,":[63],"which":[64,118],"an":[66],"music":[68],"transcription":[69],"method":[70,131],"that":[71,101],"uses":[72],"a":[73,83,90,98],"two-level":[74],"hierarchical":[75],"frequency-time":[76],"Transformer":[77,91,99,122],"architecture.":[78],"The":[79,109],"first":[80],"hierarchy":[81,117],"includes":[82],"convolutional":[84],"block":[85],"axis,":[89,96],"encoder":[92,123],"decoder":[100],"converts":[102],"dimension":[104],"axis.":[108,127],"output":[110],"then":[112],"fed":[113],"second":[116],"consists":[119],"another":[121],"We":[128],"evaluated":[129],"our":[130],"with":[132,157,161],"widely":[134],"used":[135],"MAPS":[136],"MAESTRO":[138],"v3.0.0":[139],"datasets,":[140],"it":[142],"demonstrated":[143],"state-of-the-art":[144],"performance":[145],"all":[147],"F1-scores":[149],"metrics":[152],"among":[153],"Frame,":[154],"Note,":[155],"Note":[156,160],"Offset,":[158],"Offset":[162],"Velocity":[164],"estimations.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}