{"id":"https://openalex.org/W2771644120","doi":"https://doi.org/10.1109/waspaa.2017.8170013","title":"Towards end-to-end polyphonic music transcription: Transforming music audio directly to a score","display_name":"Towards end-to-end polyphonic music transcription: Transforming music audio directly to a score","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2771644120","doi":"https://doi.org/10.1109/waspaa.2017.8170013","mag":"2771644120"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2017.8170013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"article","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/A5057345246","display_name":"Ralf Gunter Correa Carvalho","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ralf Gunter Correa Carvalho","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, US"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, US","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038903729","display_name":"Paris Smaragdis","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paris Smaragdis","raw_affiliation_strings":["Adobe Research","University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]},{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057345246"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":1.6643,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.8586904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"151","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994000196456909,"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/polyphony","display_name":"Polyphony","score":0.8768244385719299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6984148025512695},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6953232884407043},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6794207096099854},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6651911735534668},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5349363684654236},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5345508456230164},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5101218819618225},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3520749509334564},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.16452300548553467},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1204211413860321}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8768244385719299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984148025512695},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6953232884407043},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6794207096099854},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6651911735534668},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5349363684654236},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5345508456230164},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5101218819618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3520749509334564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.16452300548553467},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1204211413860321},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa.2017.8170013","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2017.8170013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W129413713","https://openalex.org/W1538131130","https://openalex.org/W1556662957","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1974548373","https://openalex.org/W2017578549","https://openalex.org/W2095705004","https://openalex.org/W2105343238","https://openalex.org/W2120809168","https://openalex.org/W2130942839","https://openalex.org/W2136848157","https://openalex.org/W2142464052","https://openalex.org/W2152937398","https://openalex.org/W2161632835","https://openalex.org/W2162931300","https://openalex.org/W2949117887","https://openalex.org/W6632100814","https://openalex.org/W6637242042","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6679436768","https://openalex.org/W6683965311"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2132597408","https://openalex.org/W2340483794","https://openalex.org/W2593532750","https://openalex.org/W3207232378","https://openalex.org/W2642467014","https://openalex.org/W2889523925","https://openalex.org/W3080080512"],"abstract_inverted_index":{"We":[0,55],"present":[1],"a":[2,38,59],"neural":[3,39],"network":[4,40,60],"model":[5],"that":[6,37],"learns":[7],"to":[8,75],"produce":[9],"music":[10],"scores":[11],"directly":[12],"from":[13],"audio":[14],"signals.":[15],"Instead":[16],"of":[17],"employing":[18],"commonplace":[19],"processing":[20],"steps,":[21],"such":[22,43,58],"as":[23],"frequency":[24],"transform":[25],"front-ends,":[26],"harmonicity":[27],"and":[28,69],"scale":[29],"priors,":[30],"or":[31],"temporal":[32],"pitch":[33],"smoothing,":[34],"we":[35],"show":[36,56],"can":[41,61],"learn":[42],"steps":[44],"on":[45],"its":[46],"own":[47],"when":[48],"presented":[49],"with":[50,65],"the":[51],"appropriate":[52],"training":[53],"data.":[54],"how":[57,70],"perform":[62],"monophonic":[63],"transcription":[64],"very":[66],"high":[67],"accuracy,":[68],"it":[71],"also":[72],"generalizes":[73],"well":[74],"transcribing":[76],"polyphonic":[77],"music.":[78]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}