{"id":"https://openalex.org/W2119036123","doi":"https://doi.org/10.1109/icassp.2011.5946424","title":"Hidden Discrete Tempo Model: A tempo-aware timing model for audio-to-score alignment","display_name":"Hidden Discrete Tempo Model: A tempo-aware timing model for audio-to-score alignment","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2119036123","doi":"https://doi.org/10.1109/icassp.2011.5946424","mag":"2119036123"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/1269631","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007492310","display_name":"Cyril Joder","orcid":null},"institutions":[{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":["LTCI, Institut T\u00e9l\u00e9com-T\u00e9l\u00e9com SudParis, Paris, France","AAO (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Institut T\u00e9l\u00e9com-T\u00e9l\u00e9com SudParis, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"AAO (France)","institution_ids":[]}]},{"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/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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":["LTCI, Institut T\u00e9l\u00e9com-T\u00e9l\u00e9com SudParis, Paris, France","LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Institut T\u00e9l\u00e9com-T\u00e9l\u00e9com SudParis, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)","institution_ids":["https://openalex.org/I4210165912"]}]},{"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"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210145102","display_name":"Institut Polytechnique de Paris","ror":"https://ror.org/042tfbd02","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210145102"]},{"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, Institut T\u00e9l\u00e9com-T\u00e9l\u00e9com SudParis, Paris, France","IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI, Institut T\u00e9l\u00e9com-T\u00e9l\u00e9com SudParis, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"raw_affiliation_string":"IDS - D\u00e9partement Images, Donn\u00e9es, Signal (46, rue Barrault 75013 Paris ; 15 Place Marguerite Perey 91120 Palaiseau (depuis oct 2019) - France)","institution_ids":[]},{"raw_affiliation_string":"S2A - Signal, Statistique et Apprentissage (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","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":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.16106552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"397","last_page":"400"},"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":0.9958999752998352,"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":0.9937999844551086,"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/computer-science","display_name":"Computer science","score":0.7464028000831604},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.6208286285400391},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5660660862922668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5539966225624084},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5190609097480774},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49657779932022095},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.458956778049469},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42195606231689453},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4147314727306366},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.40230175852775574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3978463411331177},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27827614545822144},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11903378367424011}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464028000831604},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.6208286285400391},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5660660862922668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5539966225624084},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5190609097480774},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49657779932022095},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.458956778049469},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42195606231689453},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4147314727306366},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.40230175852775574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3978463411331177},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27827614545822144},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11903378367424011},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":3,"locations":[{"id":"doi:10.1109/icassp.2011.5946424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-02714059v1","is_oa":false,"landing_page_url":"https://inria.hal.science/hal-02714059","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":"ICASSP 2011 - 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2011, Prague, France. pp.397-400, &#x27E8;10.1109/ICASSP.2011.5946424&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:zenodo.org:1269631","is_oa":true,"landing_page_url":"https://zenodo.org/record/1269631","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:1269631","is_oa":true,"landing_page_url":"https://zenodo.org/record/1269631","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W42270375","https://openalex.org/W1519655822","https://openalex.org/W1994287186","https://openalex.org/W2024672885","https://openalex.org/W2096623359","https://openalex.org/W2100417949","https://openalex.org/W2110007838","https://openalex.org/W2110575115","https://openalex.org/W2130887255","https://openalex.org/W2139588416","https://openalex.org/W2150452896","https://openalex.org/W2160537075","https://openalex.org/W2275238206","https://openalex.org/W2294938105","https://openalex.org/W6631117800","https://openalex.org/W6674259615","https://openalex.org/W6683762051","https://openalex.org/W6694178644","https://openalex.org/W6697095839"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2102309991","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2133857928"],"abstract_inverted_index":{"In":[0],"this":[1,75,107],"paper,":[2],"we":[3],"present":[4],"the":[5,33,37,45,55,60,68,79,102,117],"Hidden":[6],"Discrete":[7],"Tempo":[8],"Model,":[9],"an":[10,24,51],"effective":[11],"Dynamic":[12],"Bayesian":[13],"Network":[14],"for":[15,50,109],"audio":[16,110],"to":[17,41,85,111],"score":[18,112],"matching.":[19],"Its":[20],"main":[21],"feature":[22,122],"is":[23],"explicit":[25],"modeling":[26],"of":[27,36,44,62,74,106,119],"tempo,":[28],"which":[29,64],"directly":[30,65],"in":[31,83],"fluences":[32],"timing":[34],"model":[35,108],"musical":[38],"performance.":[39],"Thanks":[40],"a":[42],"discretization":[43],"tempo":[46,121],"set,":[47],"it":[48],"allows":[49],"efficient":[52],"decoding":[53],"by":[54,77],"Viterbi":[56],"algorithm,":[57],"and":[58,88,98],"facilitates":[59],"introduction":[61],"features":[63],"depend":[66],"on":[67,94],"local":[69],"tempo.":[70],"We":[71],"take":[72],"advantage":[73],"property":[76],"using":[78],"cyclic":[80],"tempogram":[81],"descriptor":[82],"addition":[84],"chroma":[86],"vectors":[87],"onset":[89],"detection":[90],"features.":[91],"Experiment":[92],"run":[93],"both":[95],"classical":[96],"piano":[97],"pop":[99],"music":[100],"show":[101],"very":[103],"high":[104],"accuracy":[105],"alignment,":[113],"as":[114,116],"well":[115],"usefulness":[118],"die":[120],"used.":[123]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
