{"id":"https://openalex.org/W2042390666","doi":"https://doi.org/10.1109/icassp.2014.6854953","title":"Improved musical onset detection with Convolutional Neural Networks","display_name":"Improved musical onset detection with Convolutional Neural Networks","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2042390666","doi":"https://doi.org/10.1109/icassp.2014.6854953","mag":"2042390666"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101525853","display_name":"Jan Schl\u00fcter","orcid":"https://orcid.org/0000-0003-3862-6888"},"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":"Jan Schluter","raw_affiliation_strings":["Austrian Research Institute for Artificial Intelligence, Vienna","Austrian Res. Inst. for Artificial Intell., Vienna, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Research Institute for Artificial Intelligence, Vienna","institution_ids":["https://openalex.org/I161878677"]},{"raw_affiliation_string":"Austrian Res. Inst. for Artificial Intell., Vienna, Austria","institution_ids":["https://openalex.org/I161878677"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089048082","display_name":"Sebastian B\u00f6ck","orcid":"https://orcid.org/0000-0001-6707-5427"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Sebastian Bock","raw_affiliation_strings":["Department of Computational Perception, Johannes Kepler University, Linz, Austria","Dept. of Comput. Perception, Johannes Kepler Univ., Linz, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Dept. of Comput. Perception, Johannes Kepler Univ., Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.0379,"has_fulltext":false,"cited_by_count":197,"citation_normalized_percentile":{"value":0.99366402,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6979","last_page":"6983"},"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/T10788","display_name":"Neuroscience and Music Perception","score":0.9952999949455261,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9951000213623047,"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/spectrogram","display_name":"Spectrogram","score":0.8111739158630371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830585241317749},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.7281395196914673},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7276559472084045},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6480851173400879},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6351507902145386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5667487978935242},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4453493356704712},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4388648271560669},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4352065920829773},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32693108916282654}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8111739158630371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830585241317749},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7281395196914673},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7276559472084045},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6480851173400879},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6351507902145386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5667487978935242},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4453493356704712},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4388648271560669},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4352065920829773},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32693108916282654},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W140394387","https://openalex.org/W159428914","https://openalex.org/W1849277567","https://openalex.org/W1904365287","https://openalex.org/W1979624743","https://openalex.org/W1982446897","https://openalex.org/W2035424729","https://openalex.org/W2107789863","https://openalex.org/W2112796928","https://openalex.org/W2139238328","https://openalex.org/W2140304104","https://openalex.org/W2152429995","https://openalex.org/W2156387975","https://openalex.org/W2240580723","https://openalex.org/W2293202270","https://openalex.org/W2294059674","https://openalex.org/W2336489330","https://openalex.org/W2340134902","https://openalex.org/W2397818963","https://openalex.org/W2406196141","https://openalex.org/W2504108613","https://openalex.org/W2962851944","https://openalex.org/W3113172960","https://openalex.org/W6605716049","https://openalex.org/W6606512206","https://openalex.org/W6676071220","https://openalex.org/W6682889407","https://openalex.org/W6690079499","https://openalex.org/W6696761078","https://openalex.org/W6697171384","https://openalex.org/W6704025895","https://openalex.org/W6713465158"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2530685530","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200"],"abstract_inverted_index":{"Musical":[0],"onset":[1],"detection":[2],"is":[3],"one":[4],"of":[5,43,47,93],"the":[6,58,94],"most":[7],"elementary":[8],"tasks":[9],"in":[10,28],"music":[11,20,48],"analysis,":[12],"but":[13],"still":[14],"only":[15],"solved":[16],"imperfectly":[17],"for":[18,81,102],"polyphonic":[19],"signals.":[21],"Interpreted":[22],"as":[23],"a":[24,41],"computer":[25],"vision":[26],"problem":[27],"spectrograms,":[29],"Convolutional":[30],"Neural":[31],"Networks":[32],"(CNNs)":[33],"seem":[34],"to":[35,112],"be":[36,110],"an":[37],"ideal":[38],"fit.":[39],"On":[40],"dataset":[42],"about":[44],"100":[45],"minutes":[46],"with":[49],"26k":[50],"annotated":[51],"onsets,":[52,85],"we":[53,70],"show":[54],"that":[55,100],"CNNs":[56],"outperform":[57],"previous":[59],"state-of-the-art":[60],"while":[61],"requiring":[62],"less":[63],"manual":[64],"preprocessing.":[65],"Investigating":[66],"their":[67],"inner":[68],"workings,":[69],"find":[71],"two":[72],"key":[73],"advantages":[74],"over":[75],"hand-designed":[76],"methods:":[77],"Using":[78],"separate":[79],"detectors":[80],"percussive":[82],"and":[83,86],"harmonic":[84],"combining":[87],"results":[88,98],"from":[89],"many":[90],"minor":[91],"variations":[92],"same":[95],"scheme.":[96],"The":[97],"suggest":[99],"even":[101],"well-understood":[103],"signal":[104],"processing":[105],"tasks,":[106],"machine":[107],"learning":[108],"can":[109],"superior":[111],"knowledge":[113],"engineering.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":31},{"year":2018,"cited_by_count":30},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}