{"id":"https://openalex.org/W7108622238","doi":"https://doi.org/10.5281/zenodo.17811550","title":"Exploring System Adaptations for Minimum Latency Real-Time Piano Transcription","display_name":"Exploring System Adaptations for Minimum Latency Real-Time Piano Transcription","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108622238","doi":"https://doi.org/10.5281/zenodo.17811550"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811550","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811550","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.17811550","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Patricia Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patricia Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Silvan Peter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Silvan Peter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jan Schl\u00fcter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Schl\u00fcter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Gerhard Widmer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","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":0,"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":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5286999940872192,"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":0.5286999940872192,"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":0.31279999017715454,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.022700000554323196,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.6668999791145325},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6664000153541565},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5199999809265137},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4765999913215637},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4544999897480011},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.4447999894618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7254999876022339},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.6668999791145325},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6664000153541565},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5199999809265137},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43880000710487366},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35839998722076416},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31859999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811550","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811550","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.17811550","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811550","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":{"Advances":[0],"in":[1,16,87,121,151],"neural":[2],"network":[3],"design":[4],"and":[5,53,74,85,95,98,103,138],"the":[6,55,111,114,135],"availability":[7],"of":[8,36],"large-scale":[9],"labeled":[10],"datasets":[11],"have":[12],"driven":[13],"major":[14],"improvements":[15],"piano":[17,66],"transcription.":[18,67,109,158],"Existing":[19],"approaches":[20],"target":[21],"either":[22],"offline":[23],"applications,":[24],"with":[25,34],"no":[26],"restrictions":[27],"on":[28,113],"computational":[29,76],"demands,":[30],"or":[31],"online":[32,58],"transcription,":[33],"delays":[35],"160--320ms.":[37],"However,":[38],"most":[39],"real-time":[40,65,108,157],"musical":[41],"applications":[42],"require":[43],"latencies":[44],"below":[45],"30ms.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,69,91,117],"investigate":[51],"whether":[52],"how":[54],"current":[56],"state-of-the-art":[57],"transcription":[59,122],"model":[60,83,88],"can":[61],"be":[62],"adapted":[63],"for":[64,107],"Specifically,":[68],"eliminate":[70],"all":[71],"non-causal":[72],"processing,":[73],"reduce":[75],"load":[77],"through":[78],"shared":[79],"computations":[80],"across":[81],"core":[82],"components":[84],"variations":[86],"size.":[89],"Additionally,":[90],"explore":[92],"different":[93],"pre-":[94],"postprocessing":[96],"strategies,":[97],"related":[99],"label":[100],"encoding":[101],"schemes,":[102],"discuss":[104],"their":[105],"suitability":[106],"Evaluating":[110],"adaptions":[112],"MAESTRO":[115],"dataset,":[116],"find":[118],"a":[119,132,146],"drop":[120],"accuracy":[123],"due":[124],"to":[125,148],"strictly":[126],"causal":[127],"processing":[128],"as":[129,131,145],"well":[130],"tradeoff":[133],"between":[134],"preprocessing":[136],"latency":[137,156],"prediction":[139],"accuracy.":[140],"We":[141],"release":[142],"our":[143],"system":[144],"baseline":[147],"support":[149],"researchers":[150],"designing":[152],"models":[153],"towards":[154],"minimum":[155]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-12-05T00:00:00"}