{"id":"https://openalex.org/W7108648202","doi":"https://doi.org/10.5281/zenodo.17811552","title":"TOWARDS ROBUST MUSIC TRANSCRIPTION BY MEASURING CROSS-VERSION CONSISTENCY IN WESTERN CLASSICAL MUSIC","display_name":"TOWARDS ROBUST MUSIC TRANSCRIPTION BY MEASURING CROSS-VERSION CONSISTENCY IN WESTERN CLASSICAL MUSIC","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108648202","doi":"https://doi.org/10.5281/zenodo.17811552"},"language":null,"primary_location":{"id":"pmh:doi:10.5281/zenodo.17706388","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yannik Venohr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yannik Venohr","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yiwei Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiwei Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Christof Weiss","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christof Weiss","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.50927328,"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":0.9319000244140625,"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":0.9319000244140625,"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":0.05090000107884407,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.006399999838322401,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.7239999771118164},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7006999850273132},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.5439000129699707},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5299000144004822},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43160000443458557},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.41929998993873596},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41019999980926514}],"concepts":[{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.7239999771118164},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7006999850273132},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5870000123977661},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.5439000129699707},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5299000144004822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46939998865127563},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43160000443458557},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41019999980926514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33649998903274536},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C37279795","wikidata":"https://www.wikidata.org/wiki/Q2492305","display_name":"Consistency model","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C558987187","wikidata":"https://www.wikidata.org/wiki/Q1544924","display_name":"Musical analysis","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C143857728","wikidata":"https://www.wikidata.org/wiki/Q193544","display_name":"Music theory","level":3,"score":0.2554999887943268},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.5281/zenodo.17706388","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},{"id":"doi:10.5281/zenodo.17811552","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811552","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":"pmh:doi:10.5281/zenodo.17706388","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.40696972608566284}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Music":[1],"Transcription":[2],"(AMT)":[3],"is":[4,41,69,143],"a":[5,63,88,169],"central":[6],"task":[7],"within":[8],"MIR,":[9],"enabling":[10],"various":[11],"subsequent":[12],"applications.":[13],"Despite":[14],"advancements":[15],"thanks":[16],"to":[17,25,47,52,60,71,74,150,176,178],"deep":[18],"learning,":[19],"improving":[20],"AMT":[21,57,115],"remains":[22],"challenging":[23],"due":[24,51],"the":[26,96,114],"scarcity":[27],"of":[28,95,117],"large,":[29],"high-quality":[30],"annotated":[31,141],"datasets.":[32],"Recognizing":[33],"pitches":[34],"in":[35,138],"multi-instrument":[36],"settings":[37],"beyond":[38],"solo":[39],"piano":[40],"particularly":[42,136],"difficult,":[43],"as":[44,153],"models":[45],"struggle":[46],"generalize":[48,177],"across":[49,92],"domains":[50,139],"dataset":[53],"biases":[54],"and":[55,73,104],"overfitting.":[56],"research":[58],"appears":[59],"have":[61],"hit":[62],"glass":[64],"ceiling,":[65],"where":[66,140],"further":[67],"progress":[68],"difficult":[70],"achieve":[72],"measure.":[75],"To":[76],"address":[77],"this,":[78,157],"we":[79],"propose":[80],"cross-version":[81,124,162],"consistency---an":[82],"annotation-free":[83],"evaluation":[84,111],"framework":[85],"that":[86,123,161],"assesses":[87],"model's":[89,170],"transcription":[90],"consistency":[91,125,163],"different":[93],"recordings":[94,147],"same":[97],"musical":[98],"work.":[99],"We":[100],"formalize":[101],"this":[102],"concept":[103],"systematically":[105],"analyze":[106],"its":[107,174],"relationship":[108],"with":[109],"standard":[110],"metrics":[112],"on":[113],"subtask":[116],"multi-pitch":[118],"estimation.":[119],"Our":[120],"results":[121,159],"show":[122],"enables":[126],"model":[127],"assessment":[128],"using":[129],"only":[130],"unlabeled":[131],"multi-version":[132,146],"datasets,":[133],"making":[134],"it":[135],"valuable":[137],"data":[142],"scarce":[144],"but":[145],"are":[148],"easy":[149],"obtain,":[151],"such":[152],"orchestral":[154],"music.":[155],"Beyond":[156],"our":[158],"indicate":[160],"can":[164],"also":[165],"provide":[166],"insights":[167],"into":[168],"robustness,":[171],"i.":[172],"e.,":[173],"ability":[175],"out-of-domain":[179],"data.":[180]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-12-05T00:00:00"}