{"id":"https://openalex.org/W2395731347","doi":"https://doi.org/10.1109/icassp.2016.7471684","title":"Feature adapted convolutional neural networks for downbeat tracking","display_name":"Feature adapted convolutional neural networks for downbeat tracking","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2395731347","doi":"https://doi.org/10.1109/icassp.2016.7471684","mag":"2395731347"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7471684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5108294493","display_name":"Simon Durand","orcid":null},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Durand","raw_affiliation_strings":["LTCI, Universit\u00e9 Paris-Saclay, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031398497","display_name":"Juan Pablo Bello","orcid":"https://orcid.org/0000-0001-8561-5204"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juan P. Bello","raw_affiliation_strings":["Music and Audio Research Laboratory (MARL), New York University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Music and Audio Research Laboratory (MARL), New York University, USA","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010434831","display_name":"Bertrand David","orcid":"https://orcid.org/0000-0002-5520-8613"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bertrand David","raw_affiliation_strings":["LTCI, CNRS, T\u00e9l\u00e9com ParisTech, Universit\u00e9 Paris-Saclay, 75013, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, CNRS, T\u00e9l\u00e9com ParisTech, Universit\u00e9 Paris-Saclay, 75013, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I277688954","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["LTCI, Universit\u00e9 Paris-Saclay, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I277688954","https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5736,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.93649956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"abs 1412 4564","issue":null,"first_page":"296","last_page":"300"},"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":0.9995999932289124,"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":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.7270221710205078},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6446123123168945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6345760226249695},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6147039532661438},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.607587456703186},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5708269476890564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5575093626976013},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.5530404448509216},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45716750621795654},{"id":"https://openalex.org/keywords/rhythm","display_name":"Rhythm","score":0.42672982811927795}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7270221710205078},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6446123123168945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6345760226249695},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6147039532661438},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.607587456703186},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5708269476890564},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5575093626976013},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.5530404448509216},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45716750621795654},{"id":"https://openalex.org/C135343436","wikidata":"https://www.wikidata.org/wiki/Q170406","display_name":"Rhythm","level":2,"score":0.42672982811927795},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7471684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7471684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W89500126","https://openalex.org/W1519655822","https://openalex.org/W1601722049","https://openalex.org/W1607142029","https://openalex.org/W1904365287","https://openalex.org/W2015861736","https://openalex.org/W2019989427","https://openalex.org/W2035424729","https://openalex.org/W2056206818","https://openalex.org/W2058715312","https://openalex.org/W2086186320","https://openalex.org/W2112796928","https://openalex.org/W2146241755","https://openalex.org/W2146516687","https://openalex.org/W2155764689","https://openalex.org/W2156063659","https://openalex.org/W2170277766","https://openalex.org/W2170678332","https://openalex.org/W2403654366","https://openalex.org/W2504108613","https://openalex.org/W2560529159","https://openalex.org/W2953066166","https://openalex.org/W6631117800","https://openalex.org/W6636203886","https://openalex.org/W6640036494","https://openalex.org/W6671833986","https://openalex.org/W6713713142","https://openalex.org/W6729923734","https://openalex.org/W6764750447","https://openalex.org/W6941176339"],"related_works":["https://openalex.org/W2118466154","https://openalex.org/W2118371117","https://openalex.org/W2464878701","https://openalex.org/W4247380401","https://openalex.org/W3013946943","https://openalex.org/W3112683371","https://openalex.org/W3113198510","https://openalex.org/W2157038729","https://openalex.org/W2183667122","https://openalex.org/W2565365725"],"abstract_inverted_index":{"We":[0,105],"define":[1],"a":[2,78,82,99,116],"novel":[3],"system":[4],"for":[5],"the":[6,58,75,88,108],"automatic":[7],"estimation":[8],"of":[9,34,77,112],"downbeat":[10,55,83,93],"positions":[11],"from":[12],"audio":[13],"music":[14],"signals.":[15],"New":[16],"rhythm":[17,69],"and":[18,23,45,70,74,110],"melodic":[19],"features":[20,65],"are":[21,29,72],"introduced":[22],"feature":[24],"adapted":[25],"convolutional":[26],"neural":[27,90],"networks":[28],"used":[30],"to":[31,39,50,53,67],"take":[32],"advantage":[33],"their":[35],"specificity.":[36],"Indeed,":[37],"invariance":[38],"melody":[40],"transposition,":[41],"chroma":[42],"data":[43,59],"augmentation":[44],"length-specific":[46],"rhythmic":[47],"patterns":[48],"prove":[49],"be":[51],"useful":[52],"learn":[54],"likelihood.":[56],"After":[57],"is":[60,85,95],"segmented":[61],"in":[62],"tatums,":[63],"complementary":[64],"related":[66],"melody,":[68],"harmony":[71],"extracted":[73,97],"likelihood":[76],"tatum":[79],"being":[80],"at":[81],"position":[84],"computed":[86],"with":[87,98,115],"aforementioned":[89],"networks.":[91],"The":[92],"sequence":[94],"then":[96,106],"flexible":[100],"temporal":[101],"hidden":[102],"Markov":[103],"model.":[104],"show":[107],"efficiency":[109],"robustness":[111],"our":[113],"approach":[114],"comparative":[117],"evaluation":[118],"conducted":[119],"on":[120],"9":[121],"datasets.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}