{"id":"https://openalex.org/W2938774173","doi":"https://doi.org/10.1109/icassp.2019.8683582","title":"Deep Polyphonic ADSR Piano Note Transcription","display_name":"Deep Polyphonic ADSR Piano Note Transcription","publication_year":2019,"publication_date":"2019-04-16","ids":{"openalex":"https://openalex.org/W2938774173","doi":"https://doi.org/10.1109/icassp.2019.8683582","mag":"2938774173"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.09165","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080859330","display_name":"Rainer Kelz","orcid":null},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Rainer Kelz","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence, Vienna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence, Vienna","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089048082","display_name":"Sebastian B\u00f6ck","orcid":"https://orcid.org/0000-0001-6707-5427"},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sebastian Bock","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence, Vienna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence, Vienna","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I161878677","display_name":"Austrian Research Institute for Artificial Intelligence","ror":"https://ror.org/04j47vk14","country_code":"AT","type":"facility","lineage":["https://openalex.org/I161878677","https://openalex.org/I4210107880"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence, Vienna"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence, Vienna","institution_ids":["https://openalex.org/I161878677"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6731,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.95696634,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"246","last_page":"250"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9997000098228455,"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":0.9965999722480774,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7712939977645874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.684502124786377},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.6061604022979736},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5600968599319458},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.5422267913818359},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5230725407600403},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5186973810195923},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47800886631011963},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.42527398467063904},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41222602128982544},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21561866998672485},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20062431693077087}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7712939977645874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.684502124786377},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.6061604022979736},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5600968599319458},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5422267913818359},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5230725407600403},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5186973810195923},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47800886631011963},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.42527398467063904},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41222602128982544},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21561866998672485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20062431693077087},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/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/icassp.2019.8683582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.09165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.09165","pdf_url":"https://arxiv.org/pdf/1906.09165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.09165","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.09165","pdf_url":"https://arxiv.org/pdf/1906.09165","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1530968569","https://openalex.org/W1574263887","https://openalex.org/W1822807512","https://openalex.org/W1846203979","https://openalex.org/W2055356414","https://openalex.org/W2095705004","https://openalex.org/W2104112890","https://openalex.org/W2110007838","https://openalex.org/W2144414181","https://openalex.org/W2147962362","https://openalex.org/W2152937398","https://openalex.org/W2155531311","https://openalex.org/W2198584637","https://openalex.org/W2294404390","https://openalex.org/W2396376630","https://openalex.org/W2405656250","https://openalex.org/W2407685581","https://openalex.org/W2437181147","https://openalex.org/W2593836007","https://openalex.org/W2771231137","https://openalex.org/W2805763736","https://openalex.org/W2950335938","https://openalex.org/W2963285578","https://openalex.org/W2963551352","https://openalex.org/W3046154609","https://openalex.org/W4226286871","https://openalex.org/W4293775315","https://openalex.org/W4301387266","https://openalex.org/W6638777396","https://openalex.org/W6674330103","https://openalex.org/W6681236507","https://openalex.org/W6681841984","https://openalex.org/W6685562342","https://openalex.org/W6697316635","https://openalex.org/W6711863477","https://openalex.org/W6714030504","https://openalex.org/W6733936739","https://openalex.org/W6745851314","https://openalex.org/W6746269311","https://openalex.org/W6750261095","https://openalex.org/W6751873103"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W2316271602","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2357375963","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W4389072957"],"abstract_inverted_index":{"We":[0,103],"investigate":[1],"a":[2,10,18,70,91,119],"late-fusion":[3],"approach":[4],"to":[5,40,56,90,96,114,129],"piano":[6],"transcription,":[7],"combined":[8],"with":[9,42,60],"strong":[11],"temporal":[12],"prior":[13],"in":[14,31,52],"the":[15,53,108],"form":[16],"of":[17,33,36,72],"handcrafted":[19],"Hidden":[20],"Markov":[21],"Model":[22],"(HMM).":[23],"The":[24,45,84],"network":[25,46],"architecture":[26],"under":[27],"consideration":[28],"is":[29],"compact":[30],"terms":[32],"its":[34],"number":[35],"parameters":[37],"and":[38,111],"easy":[39],"train":[41],"gradient":[43],"descent.":[44],"outputs":[47],"are":[48,66,87,112],"fused":[49],"over":[50],"time":[51],"final":[54,92],"stage":[55],"obtain":[57,104],"note":[58,85,100,125],"segmentations,":[59],"an":[61],"HMM":[62],"whose":[63],"transition":[64],"probabilities":[65],"chosen":[67],"based":[68],"on":[69,107],"model":[71],"attack,":[73],"decay,":[74],"sustain,":[75],"release":[76],"(ADSR)":[77],"envelopes,":[78],"commonly":[79],"used":[80],"for":[81],"sound":[82],"synthesis.":[83],"segments":[86],"then":[88],"subject":[89],"binary":[93],"decision":[94],"rule":[95],"reject":[97],"too":[98],"weak":[99],"segment":[101],"hypotheses.":[102],"state-of-the-art":[105],"results":[106],"MAPS":[109],"dataset,":[110],"able":[113],"outperform":[115],"other":[116],"approaches":[117],"by":[118],"large":[120],"margin,":[121],"when":[122],"predicting":[123],"complete":[124],"regions":[126],"from":[127],"onsets":[128],"offsets.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}