{"id":"https://openalex.org/W1978295651","doi":"https://doi.org/10.1109/tasl.2013.2266794","title":"Learning Optimal Features for Polyphonic Audio-to-Score Alignment","display_name":"Learning Optimal Features for Polyphonic Audio-to-Score Alignment","publication_year":2013,"publication_date":"2013-06-06","ids":{"openalex":"https://openalex.org/W1978295651","doi":"https://doi.org/10.1109/tasl.2013.2266794","mag":"1978295651"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2013.2266794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2266794","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5007492310","display_name":"Cyril Joder","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153229","display_name":"European Patent Organisation","ror":"https://ror.org/050pmr719","country_code":"DE","type":"other","lineage":["https://openalex.org/I4210153229"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cyril Joder","raw_affiliation_strings":["European Patent Office, Munich, Germany","Institute for Human-Machine Communication, Technical University Munich, Munich, Germany","Inst. for Human-Machine Commun., Tech. Univ. Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Patent Office, Munich, Germany","institution_ids":["https://openalex.org/I4210153229"]},{"raw_affiliation_string":"Institute for Human-Machine Communication, Technical University Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Inst. for Human-Machine Commun., Tech. Univ. Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Slim Essid","raw_affiliation_strings":["Institut TELECOM, Telecom ParisTech, Paris, France","Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut TELECOM, Telecom ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#","institution_ids":["https://openalex.org/I12356871"]}]},{"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/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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["Institut TELECOM, Telecom ParisTech, Paris, France","Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut TELECOM, Telecom ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#","institution_ids":["https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5091,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.94763279,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"21","issue":"10","first_page":"2118","last_page":"2128"},"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":0.9993000030517578,"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":0.9984999895095825,"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/discriminative-model","display_name":"Discriminative model","score":0.768896222114563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6756182909011841},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5737835764884949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5495488047599792},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5339623093605042},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5249576568603516},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5176737308502197},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.469511479139328},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43982842564582825},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.43981125950813293},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4313039481639862},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.43073374032974243},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4190356135368347},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.4180450439453125},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.32579660415649414},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14651185274124146}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.768896222114563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6756182909011841},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5737835764884949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5495488047599792},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5339623093605042},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5249576568603516},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5176737308502197},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.469511479139328},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43982842564582825},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.43981125950813293},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4313039481639862},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.43073374032974243},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4190356135368347},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4180450439453125},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.32579660415649414},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14651185274124146},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2013.2266794","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2013.2266794","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W40088496","https://openalex.org/W42270375","https://openalex.org/W104137921","https://openalex.org/W170732776","https://openalex.org/W185944909","https://openalex.org/W189514790","https://openalex.org/W1489504608","https://openalex.org/W1519655822","https://openalex.org/W1524784804","https://openalex.org/W1549486140","https://openalex.org/W1994287186","https://openalex.org/W2001562039","https://openalex.org/W2005660297","https://openalex.org/W2024672885","https://openalex.org/W2031787046","https://openalex.org/W2051669046","https://openalex.org/W2089876151","https://openalex.org/W2100816929","https://openalex.org/W2110007838","https://openalex.org/W2120202836","https://openalex.org/W2121232083","https://openalex.org/W2131604793","https://openalex.org/W2139588416","https://openalex.org/W2142927150","https://openalex.org/W2144234122","https://openalex.org/W2146302296","https://openalex.org/W2147880316","https://openalex.org/W2150452896","https://openalex.org/W2152324136","https://openalex.org/W2153331925","https://openalex.org/W2155515618","https://openalex.org/W2160485598","https://openalex.org/W2166209411","https://openalex.org/W2294702833","https://openalex.org/W2295370733","https://openalex.org/W2296201206","https://openalex.org/W2534942261","https://openalex.org/W3090152428","https://openalex.org/W4236796448","https://openalex.org/W6604317416","https://openalex.org/W6607608197","https://openalex.org/W6629134104","https://openalex.org/W6631117800","https://openalex.org/W6631462586","https://openalex.org/W6632893073","https://openalex.org/W6678265817","https://openalex.org/W6681102793","https://openalex.org/W6682082992","https://openalex.org/W6696886382","https://openalex.org/W6697198231","https://openalex.org/W6697237593","https://openalex.org/W6728606992"],"related_works":["https://openalex.org/W4360764600","https://openalex.org/W2289868279","https://openalex.org/W3135448569","https://openalex.org/W2793814466","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W2769884427","https://openalex.org/W2088690926"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,9,16,20,33,41,45,53,56,62,67,89,108,111,142,146,150,157,174,180,198],"design":[4],"of":[5,11,19,110,123,136,156,197,203],"feature":[6,25,63,112],"functions":[7,26,64,113,164],"for":[8],"matching":[10],"a":[12,49,83,93,98,120,183,201],"musical":[13],"recording":[14],"to":[15,40,55,148,188],"symbolic":[17,54],"representation":[18,185],"piece":[21],"(the":[22],"score).":[23],"These":[24],"are":[27,165],"defined":[28],"as":[29,48],"dissimilarity":[30],"measures":[31],"between":[32],"audio":[34,57,158],"observations":[35],"and":[36,125,182],"template":[37,46],"vectors":[38],"corresponding":[39],"score.":[42],"By":[43],"expressing":[44],"construction":[47],"linear":[50,68],"mapping":[51],"from":[52],"representation,":[58],"one":[59,81,91],"can":[60],"learn":[61],"by":[65],"optimizing":[66],"transformation.":[69],"In":[70],"this":[71,168],"paper,":[72],"we":[73],"explore":[74],"two":[75],"different":[76,139],"learning":[77],"strategies.":[78],"The":[79,129],"first":[80],"uses":[82],"best-fit":[84],"criterion":[85],"(minimum":[86],"divergence),":[87],"while":[88],"second":[90],"exploits":[92],"discriminative":[94],"framework":[95],"based":[96],"on":[97,119],"Conditional":[99],"Random":[100],"Fields":[101],"model":[102],"(maximum":[103],"likelihood":[104],"criterion).":[105],"We":[106],"evaluate":[107],"influence":[109],"in":[114,167],"an":[115],"audio-to-score":[116],"alignment":[117,169],"task,":[118],"large":[121],"database":[122],"popular":[124],"classical":[126],"polyphonic":[127],"music.":[128],"results":[130],"show":[131],"that":[132],"with":[133,161,200,206],"several":[134,162],"types":[135],"models,":[137],"using":[138],"temporal":[140],"constraints,":[141],"learned":[143],"mappings":[144],"have":[145],"potential":[147],"outperform":[149],"classic":[151],"heuristic":[152],"mappings.":[153],"Several":[154],"representations":[155],"observations,":[159],"along":[160],"distance":[163],"compared":[166],"task.":[170],"Our":[171],"experiments":[172],"elect":[173],"symmetric":[175],"Kullback-Leibler":[176],"divergence.":[177],"Moreover,":[178],"both":[179],"spectrogram":[181],"CQT-based":[184],"turn":[186],"out":[187],"provide":[189],"very":[190],"accurate":[191],"alignments,":[192],"detecting":[193],"more":[194],"than":[195],"97%":[196],"onsets":[199],"precision":[202],"100":[204],"ms":[205],"our":[207],"most":[208],"complex":[209],"system.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}