{"id":"https://openalex.org/W2144234122","doi":"https://doi.org/10.1109/icassp.2011.5946373","title":"A unified approach to real time audio-to-score and audio-to-audio alignment using sequential Montecarlo inference techniques","display_name":"A unified approach to real time audio-to-score and audio-to-audio alignment using sequential Montecarlo inference techniques","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2144234122","doi":"https://doi.org/10.1109/icassp.2011.5946373","mag":"2144234122"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946373","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://inria.hal.science/hal-00692579","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088496136","display_name":"Nicola Montecchio","orcid":"https://orcid.org/0000-0002-7496-9557"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Nicola Montecchio","raw_affiliation_strings":["Department of Information Engineering, University of Padova, Padova, Italy","University of Padova, Dept. of Information Engineering, via Gradenigo 6/B, 35131 Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, University of Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"University of Padova, Dept. of Information Engineering, via Gradenigo 6/B, 35131 Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010210485","display_name":"Arshia Cont","orcid":"https://orcid.org/0000-0002-7352-7212"},"institutions":[{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Arshia Cont","raw_affiliation_strings":["Institut de Recherche et Coordination Acoustique Musique, Paris, France","Institut de Recherche et Coordination, Acoustique/Musique (IRCAM), 1, place Igor-Stravinsky, 75004 Paris - France"],"affiliations":[{"raw_affiliation_string":"Institut de Recherche et Coordination Acoustique Musique, Paris, France","institution_ids":["https://openalex.org/I35345632"]},{"raw_affiliation_string":"Institut de Recherche et Coordination, Acoustique/Musique (IRCAM), 1, place Igor-Stravinsky, 75004 Paris - France","institution_ids":["https://openalex.org/I35345632"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088496136"],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":null,"apc_paid":null,"fwci":6.2391,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.97247706,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"50","issue":null,"first_page":"193","last_page":"196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9853000044822693,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7782517671585083},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7716909646987915},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6581590175628662},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5819013714790344},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5792948603630066},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.519784152507782},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.495519757270813},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.4394875168800354},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.41925036907196045},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.417349636554718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.357349157333374},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22916504740715027},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09384623169898987}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7782517671585083},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716909646987915},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6581590175628662},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5819013714790344},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5792948603630066},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.519784152507782},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.495519757270813},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4394875168800354},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.41925036907196045},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.417349636554718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.357349157333374},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22916504740715027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09384623169898987},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5946373","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946373","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-00692579v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00692579","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2011 : Proceedings of International Conference on Acoustics, Speech and Signal Processing, May 2011, Prague, Czech Republic. pp.193-196, ⟨10.1109/ICASSP.2011.5946373⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00692579v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00692579","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ICASSP 2011 : Proceedings of International Conference on Acoustics, Speech and Signal Processing, May 2011, Prague, Czech Republic. pp.193-196, ⟨10.1109/ICASSP.2011.5946373⟩","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W87329255","https://openalex.org/W1515617868","https://openalex.org/W1994287186","https://openalex.org/W2121232083","https://openalex.org/W2130363011","https://openalex.org/W2142927150","https://openalex.org/W2150452896","https://openalex.org/W2160337655","https://openalex.org/W2951896087","https://openalex.org/W6631015562","https://openalex.org/W6678265817","https://openalex.org/W6681102793"],"related_works":["https://openalex.org/W2419138286","https://openalex.org/W2507549656","https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W1967853457","https://openalex.org/W1975359510","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,28,73],"methodology":[3,81],"for":[4],"the":[5,24,45,69,79],"real":[6,74],"time":[7,75],"alignment":[8,19,67],"of":[9,27,56,63,78],"music":[10],"signals":[11],"using":[12],"sequential":[13],"Monte":[14],"Carlo":[15],"inference":[16],"techniques.":[17],"The":[18,53],"problem":[20],"is":[21,48,59],"formulated":[22],"as":[23],"state":[25,47],"tracking":[26],"dynamical":[29],"system,":[30],"and":[31,65,88],"differs":[32],"from":[33],"traditional":[34],"Hidden":[35],"Markov":[36],"Model":[37],"Dynamic":[38],"Time":[39],"Warping":[40],"based":[41],"systems":[42],"in":[43,72],"that":[44],"hidden":[46],"continuous":[49],"rather":[50],"than":[51],"discrete.":[52],"major":[54],"contribution":[55],"this":[57],"paper":[58],"addressing":[60],"both":[61,83],"problems":[62,84],"audio-to-score":[64],"audio-to-audio":[66],"within":[68],"same":[70],"framework":[71],"setting.":[76],"Performances":[77],"proposed":[80],"on":[82],"are":[85],"then":[86],"evaluated":[87],"discussed.":[89]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}