{"id":"https://openalex.org/W7108686439","doi":"https://doi.org/10.5281/zenodo.17811439","title":"High-Resolution Sustain Pedal Depth Estimation from Piano Audio across Room Acoustics","display_name":"High-Resolution Sustain Pedal Depth Estimation from Piano Audio across Room Acoustics","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108686439","doi":"https://doi.org/10.5281/zenodo.17811439"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811439","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811439","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.17811439","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hanwen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hanwen Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Fang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ziyu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyu Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Ichiro Fujinaga","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ichiro Fujinaga","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.62680856,"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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.3984000086784363,"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":0.3984000086784363,"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":0.3239000141620636,"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":0.20759999752044678,"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/piano","display_name":"Piano","score":0.8277999758720398},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6262999773025513},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.5260999798774719},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4740999937057495},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45559999346733093},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.45080000162124634},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4092999994754791}],"concepts":[{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8277999758720398},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6262999773025513},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6001999974250793},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4887000024318695},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.4207000136375427},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C178432105","wikidata":"https://www.wikidata.org/wiki/Q2182127","display_name":"Room acoustics","level":3,"score":0.39980000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3779999911785126},{"id":"https://openalex.org/C2776009117","wikidata":"https://www.wikidata.org/wiki/Q2305951","display_name":"Architectural acoustics","level":3,"score":0.34940001368522644},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.30000001192092896},{"id":"https://openalex.org/C2983311337","wikidata":"https://www.wikidata.org/wiki/Q34379","display_name":"Musical instrument","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C34951282","wikidata":"https://www.wikidata.org/wiki/Q864191","display_name":"Bioacoustics","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2703999876976013}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811439","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811439","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.17811439","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811439","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":{"Piano":[0],"sustain":[1,83,110],"pedal":[2,23,41,68,84,111],"detection":[3,98],"has":[4],"previously":[5],"been":[6],"approached":[7],"as":[8],"a":[9,32,46,114,141],"binary":[10,58,97],"on/off":[11],"classification":[12,59],"task,":[13],"limiting":[14],"its":[15],"application":[16],"in":[17,66,135],"real-world":[18],"piano":[19],"performance":[20,54],"scenarios":[21],"where":[22],"depth":[24,42,69],"significantly":[25],"influences":[26,167],"musical":[27],"expression.":[28],"This":[29],"paper":[30,102],"presents":[31],"novel":[33],"approach":[34],"for":[35,82],"high-resolution":[36],"estimation":[37,112],"that":[38,49,117,147,165],"predicts":[39],"continuous":[40,67,74],"values.":[43],"We":[44,122],"introduce":[45],"Transformer-based":[47],"architecture":[48],"not":[50,155],"only":[51],"matches":[52],"state-of-the-art":[53],"on":[55,109],"the":[56,104,148],"traditional":[57],"task":[60],"but":[61],"also":[62],"achieves":[63],"high":[64],"accuracy":[65],"estimation.":[70],"Furthermore,":[71],"by":[72],"estimating":[73],"values,":[75],"our":[76,124],"model":[77,125,168],"provides":[78],"musically":[79],"meaningful":[80],"predictions":[81,169],"usage,":[85],"whereas":[86],"baseline":[87,150],"models":[88,151],"struggle":[89],"to":[90,157],"capture":[91],"such":[92],"nuanced":[93],"expressions":[94],"with":[95,126],"their":[96],"approach.":[99,143],"Additionally,":[100],"this":[101],"investigates":[103],"influence":[105],"of":[106,129],"room":[107,130,159],"acoustics":[108],"using":[113,140],"synthetic":[115],"dataset":[116],"includes":[118],"varied":[119],"acoustic":[120],"conditions.":[121,160],"train":[123],"different":[127],"combinations":[128],"settings":[131],"and":[132,152,170],"test":[133],"it":[134],"an":[136,172],"unseen":[137,158],"new":[138],"environment":[139],"\"leave-one-out\"":[142],"Our":[144],"findings":[145],"show":[146],"two":[149],"ours":[153],"are":[154],"robust":[156],"Statistical":[161],"analysis":[162],"further":[163],"confirms":[164],"reverberation":[166],"introduces":[171],"overestimation":[173],"bias.":[174]},"counts_by_year":[],"updated_date":"2025-12-05T23:25:22.460635","created_date":"2025-12-05T00:00:00"}