{"id":"https://openalex.org/W3016096605","doi":"https://doi.org/10.1109/icassp40776.2020.9053115","title":"Sight to Sound: An End-to-End Approach for Visual Piano Transcription","display_name":"Sight to Sound: An End-to-End Approach for Visual Piano Transcription","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016096605","doi":"https://doi.org/10.1109/icassp40776.2020.9053115","mag":"3016096605"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001366802","display_name":"A. Sophia Koepke","orcid":"https://orcid.org/0000-0002-5807-0576"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"A. Sophia Koepke","raw_affiliation_strings":["VGG, Department of Engineering Science, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VGG, Department of Engineering Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051904433","display_name":"Olivia Wiles","orcid":"https://orcid.org/0009-0001-2539-2878"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Olivia Wiles","raw_affiliation_strings":["VGG, Department of Engineering Science, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VGG, Department of Engineering Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102320227","display_name":"Yael Moses","orcid":null},"institutions":[{"id":"https://openalex.org/I138898306","display_name":"Reichman University","ror":"https://ror.org/01px5cv07","country_code":"IL","type":"education","lineage":["https://openalex.org/I138898306"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Yael Moses","raw_affiliation_strings":["The Interdisciplinary Center, Herzliya"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Interdisciplinary Center, Herzliya","institution_ids":["https://openalex.org/I138898306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057678172","display_name":"Andrew Zisserman","orcid":"https://orcid.org/0000-0002-8945-8573"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Zisserman","raw_affiliation_strings":["VGG, Department of Engineering Science, University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VGG, Department of Engineering Science, University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4507,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9442183,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1838","last_page":"1842"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9972000122070312,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9952999949455261,"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/midi","display_name":"MIDI","score":0.8722093105316162},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.8068485856056213},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7191708087921143},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6864363551139832},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6266289949417114},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4848572015762329},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.4519781470298767},{"id":"https://openalex.org/keywords/sight","display_name":"Sight","score":0.44247981905937195},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.35586410760879517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.277363657951355},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.1578737497329712},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08706757426261902}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.8722093105316162},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.8068485856056213},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7191708087921143},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6864363551139832},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6266289949417114},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4848572015762329},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4519781470298767},{"id":"https://openalex.org/C1517167","wikidata":"https://www.wikidata.org/wiki/Q1134322","display_name":"Sight","level":2,"score":0.44247981905937195},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.35586410760879517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.277363657951355},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.1578737497329712},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08706757426261902},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053115","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053115","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:f8527757-9345-418e-92fd-a71e2046be4a","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:f8527757-9345-418e-92fd-a71e2046be4a","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Conference item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G1277543710","display_name":null,"funder_award_id":"EP/M013774/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W89231944","https://openalex.org/W1522301498","https://openalex.org/W1969199662","https://openalex.org/W2002666695","https://openalex.org/W2054470912","https://openalex.org/W2194775991","https://openalex.org/W2229159429","https://openalex.org/W2550393250","https://openalex.org/W2560997379","https://openalex.org/W2730531294","https://openalex.org/W2768420975","https://openalex.org/W2788575351","https://openalex.org/W2893372777","https://openalex.org/W2899771611","https://openalex.org/W2906214917","https://openalex.org/W2921484047","https://openalex.org/W2964121744","https://openalex.org/W3027779899","https://openalex.org/W4293775315","https://openalex.org/W6603626069","https://openalex.org/W6631190155","https://openalex.org/W6689595412","https://openalex.org/W6729470292","https://openalex.org/W6741152592","https://openalex.org/W6745851314","https://openalex.org/W6754917189","https://openalex.org/W6756040250","https://openalex.org/W6844132935","https://openalex.org/W6930819092"],"related_works":["https://openalex.org/W3133630535","https://openalex.org/W2398084541","https://openalex.org/W4285232104","https://openalex.org/W4242364395","https://openalex.org/W2096042855","https://openalex.org/W2064626218","https://openalex.org/W2153331925","https://openalex.org/W4301398814","https://openalex.org/W2369521057","https://openalex.org/W3093121331"],"abstract_inverted_index":{"Automatic":[0],"music":[1,12,57,95,120],"transcription":[2,121,139],"has":[3],"primarily":[4],"focused":[5],"on":[6],"transcribing":[7,55],"audio":[8,123,132],"to":[9,71,91],"a":[10,35,78,81,111],"symbolic":[11],"representation":[13],"(e.g.":[14,34],"MIDI":[15,100],"or":[16],"sheet":[17],"music).":[18],"However,":[19],"audio-only":[20],"approaches":[21],"often":[22],"struggle":[23],"with":[24],"polyphonic":[25],"instruments":[26],"and":[27,133],"background":[28],"noise.":[29],"In":[30,47],"contrast,":[31],"visual":[32,59],"information":[33],"video":[36,79,134],"of":[37,54,80,99,113],"an":[38,64],"instrument":[39],"being":[40],"played)":[41],"does":[42],"not":[43],"have":[44],"such":[45],"ambiguities.":[46],"this":[48],"work,":[49],"we":[50,88],"address":[51],"the":[52,84,93,97,138],"problem":[53],"piano":[56],"from":[58,122,141],"data":[60,135],"alone.":[61,144],"We":[62,102,127],"propose":[63],"end-to-end":[65],"deep":[66],"learning":[67],"framework":[68],"that":[69,104,130],"learns":[70],"automatically":[72],"predict":[73],"note":[74],"onset":[75],"events":[76],"given":[77],"person":[82],"playing":[83],"piano.":[85],"From":[86],"this,":[87],"are":[89],"able":[90],"transcribe":[92],"played":[94],"in":[96,110,118],"form":[98],"data.":[101],"find":[103],"our":[105],"approach":[106],"is":[107,125],"surprisingly":[108],"effective":[109],"variety":[112],"complex":[114],"situations,":[115],"particularly":[116],"those":[117],"which":[119],"alone":[124],"impossible.":[126],"also":[128],"show":[129],"combining":[131],"can":[136],"improve":[137],"obtained":[140],"each":[142],"modality":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
