{"id":"https://openalex.org/W2146302296","doi":"https://doi.org/10.1109/tasl.2011.2134092","title":"A Conditional Random Field Framework for Robust and Scalable Audio-to-Score Matching","display_name":"A Conditional Random Field Framework for Robust and Scalable Audio-to-Score Matching","publication_year":2011,"publication_date":"2011-04-26","ids":{"openalex":"https://openalex.org/W2146302296","doi":"https://doi.org/10.1109/tasl.2011.2134092","mag":"2146302296"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2011.2134092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2134092","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/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/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":"Cyril Joder","raw_affiliation_strings":["Institut TELECOM, CNRS, LTCI, TELECOM ParisTech, Paris, France","Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut TELECOM, CNRS, LTCI, TELECOM ParisTech, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I1294671590","https://openalex.org/I12356871"]},{"raw_affiliation_string":"Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#","institution_ids":["https://openalex.org/I12356871"]}]},{"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"]},{"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/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":"Slim Essid","raw_affiliation_strings":["Institut TELECOM, CNRS, LTCI, TELECOM ParisTech, Paris, France","Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut TELECOM, CNRS, LTCI, TELECOM ParisTech, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I1294671590","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/A5112054021","display_name":"Ga\u00ebl Richard","orcid":null},"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/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":"Ga\u00ebl Richard","raw_affiliation_strings":["Institut TELECOM, CNRS, LTCI, TELECOM ParisTech, Paris, France","Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut TELECOM, CNRS, LTCI, TELECOM ParisTech, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I1294671590","https://openalex.org/I12356871"]},{"raw_affiliation_string":"Inst. TELECOM, TELECOM ParisTech, Paris, France#TAB#","institution_ids":["https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.2419,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.97251531,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"19","issue":"8","first_page":"2385","last_page":"2397"},"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":0.9991000294685364,"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/conditional-random-field","display_name":"Conditional random field","score":0.8122594356536865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7350749969482422},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.5655092000961304},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5596609115600586},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5325196385383606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5005016326904297},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42788177728652954},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4040258228778839},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3857702910900116},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3526974320411682}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.8122594356536865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7350749969482422},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.5655092000961304},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5596609115600586},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5325196385383606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005016326904297},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42788177728652954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4040258228778839},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3857702910900116},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3526974320411682},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tasl.2011.2134092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2011.2134092","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.412.3822","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.412.3822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://perso.telecom-paristech.fr/~grichard/Publications/Joder_TASLP2011.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02653026v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02653026","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Audio, Speech and Language Processing, 2011","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W12225205","https://openalex.org/W20389641","https://openalex.org/W42270375","https://openalex.org/W67806156","https://openalex.org/W123154089","https://openalex.org/W152645600","https://openalex.org/W189514790","https://openalex.org/W1489504608","https://openalex.org/W1519147456","https://openalex.org/W1519655822","https://openalex.org/W1521585602","https://openalex.org/W1534285095","https://openalex.org/W1537357046","https://openalex.org/W1545600033","https://openalex.org/W1636244751","https://openalex.org/W1994287186","https://openalex.org/W1996135305","https://openalex.org/W2024672885","https://openalex.org/W2031787046","https://openalex.org/W2037234934","https://openalex.org/W2096623359","https://openalex.org/W2100417949","https://openalex.org/W2100816929","https://openalex.org/W2109958226","https://openalex.org/W2110007838","https://openalex.org/W2110575115","https://openalex.org/W2120202836","https://openalex.org/W2121232083","https://openalex.org/W2125838338","https://openalex.org/W2139588416","https://openalex.org/W2142927150","https://openalex.org/W2147880316","https://openalex.org/W2149802835","https://openalex.org/W2150452896","https://openalex.org/W2151159559","https://openalex.org/W2152324136","https://openalex.org/W2153331925","https://openalex.org/W2155295207","https://openalex.org/W2160537075","https://openalex.org/W2275238206","https://openalex.org/W2294938105","https://openalex.org/W2296201206","https://openalex.org/W2314894366","https://openalex.org/W6600519134","https://openalex.org/W6600858156","https://openalex.org/W6605019438","https://openalex.org/W6606247353","https://openalex.org/W6629134104","https://openalex.org/W6631117800","https://openalex.org/W6631159851","https://openalex.org/W6631165815","https://openalex.org/W6632009092","https://openalex.org/W6632355583","https://openalex.org/W6632733265","https://openalex.org/W6678265817","https://openalex.org/W6681102793","https://openalex.org/W6682082992","https://openalex.org/W6682500825","https://openalex.org/W6694178644","https://openalex.org/W6697095839","https://openalex.org/W6697237593"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W50079190","https://openalex.org/W182104056","https://openalex.org/W2111726165","https://openalex.org/W2011251309","https://openalex.org/W2511246383","https://openalex.org/W3108423214","https://openalex.org/W2796133761","https://openalex.org/W3088215229","https://openalex.org/W2184553228"],"abstract_inverted_index":{"In":[0,36],"this":[1],"paper,":[2],"we":[3],"introduce":[4],"the":[5,13,20,27,74,92,100,106,114,141,149,165,181,184],"use":[6],"of":[7,61,69,91,99,129,148],"conditional":[8],"random":[9],"fields":[10],"(CRFs)":[11],"for":[12,31,55,58,95],"audio-to-score":[14],"alignment":[15],"task.":[16],"This":[17,103],"framework":[18,167],"encompasses":[19],"statistical":[21,101],"models":[22,52],"which":[23,88],"are":[24,53,71,152],"used":[25,119],"in":[26,120,171],"literature":[28],"and":[29,65,79,132,183],"allows":[30,39],"more":[32,145],"flexible":[33],"dependency":[34],"structures.":[35],"particular,":[37],"it":[38],"observation":[40],"functions":[41],"to":[42,173,176],"be":[43,169,174],"computed":[44],"from":[45],"several":[46],"analysis":[47],"frames.":[48],"Three":[49,67],"different":[50,59],"CRF":[51],"proposed":[54,166],"our":[56],"task,":[57],"choices":[60],"tradeoff":[62],"between":[63,180],"accuracy":[64],"complexity.":[66],"types":[68],"features":[70],"used,":[72],"characterizing":[73],"local":[75],"harmony,":[76],"note":[77,150],"attacks":[78],"tempo.":[80],"We":[81,161],"also":[82],"propose":[83],"a":[84,109,126,155],"novel":[85],"hierarchical":[86],"approach,":[87],"takes":[89],"advantage":[90],"score":[93,182],"structure":[94],"an":[96],"approximate":[97],"decoding":[98],"model.":[102],"strategy":[104],"reduces":[105],"complexity,":[107],"yielding":[108],"better":[110],"overall":[111],"efficiency":[112],"than":[113,146,158],"classic":[115],"beam":[116],"search":[117],"method":[118],"HMM-based":[121],"models.":[122],"Experiments":[123],"run":[124],"on":[125],"large":[127],"database":[128],"classical":[130],"piano":[131],"popular":[133],"music":[134],"exhibit":[135],"very":[136],"accurate":[137],"alignments.":[138],"Indeed,":[139],"with":[140,154],"best":[142],"performing":[143],"system,":[144],"95%":[147],"onsets":[151],"detected":[153],"precision":[156],"finer":[157],"100":[159],"ms.":[160],"additionally":[162],"show":[163],"how":[164],"can":[168],"modified":[170],"order":[172],"robust":[175],"possible":[177],"structural":[178],"differences":[179],"musical":[185],"performance.":[186]},"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":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
