{"id":"https://openalex.org/W2120202836","doi":"https://doi.org/10.1109/icassp.2006.1661258","title":"Realtime Audio to Score Alignment for Polyphonic Music Instruments, using Sparse Non-Negative Constraints and Hierarchical HMMS","display_name":"Realtime Audio to Score Alignment for Polyphonic Music Instruments, using Sparse Non-Negative Constraints and Hierarchical HMMS","publication_year":2006,"publication_date":"2006-08-03","ids":{"openalex":"https://openalex.org/W2120202836","doi":"https://doi.org/10.1109/icassp.2006.1661258","mag":"2120202836"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1661258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/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"]},{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"A. Cont","raw_affiliation_strings":["Center for Research in Computing and the Arts, University of California, San Diego, San Diego, CA, USA","Ircam-Realtime Applications Team, Paris, France"],"affiliations":[{"raw_affiliation_string":"Center for Research in Computing and the Arts, University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"Ircam-Realtime Applications Team, Paris, France","institution_ids":["https://openalex.org/I35345632"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5010210485"],"corresponding_institution_ids":["https://openalex.org/I35345632","https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":5.75373419,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.96471219,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"5","issue":null,"first_page":"V","last_page":"245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9993000030517578,"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/polyphony","display_name":"Polyphony","score":0.8161599636077881},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7691100835800171},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.7493020296096802},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7378183603286743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5783449411392212},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.549896240234375},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5270172357559204},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.49540698528289795},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4463808834552765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4247654676437378},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.253792941570282}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8161599636077881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7691100835800171},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.7493020296096802},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7378183603286743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5783449411392212},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.549896240234375},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5270172357559204},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.49540698528289795},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4463808834552765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4247654676437378},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.253792941570282},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1661258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1661258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W106639881","https://openalex.org/W1549486140","https://openalex.org/W1636244751","https://openalex.org/W1916910924","https://openalex.org/W2064480843","https://openalex.org/W2118718620","https://openalex.org/W2135029798","https://openalex.org/W2141684970","https://openalex.org/W2145678789","https://openalex.org/W2155515618","https://openalex.org/W2596136048","https://openalex.org/W3090152428","https://openalex.org/W3143596294","https://openalex.org/W4301521815","https://openalex.org/W6604351559","https://openalex.org/W6632893073","https://openalex.org/W6677759377","https://openalex.org/W6680012447","https://openalex.org/W6681658821","https://openalex.org/W6845795641"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2769570009","https://openalex.org/W2964089573"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,81],"new":[3],"method":[4],"for":[5,12,44,50,64],"realtime":[6,32],"alignment":[7],"of":[8,58,85],"audio":[9],"to":[10,74],"score":[11],"polyphonic":[13],"music":[14],"signals.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19],"will":[20],"be":[21],"focusing":[22],"mostly":[23],"on":[24,31],"the":[25,56,87],"multiple-pitch":[26],"observation":[27],"algorithm":[28,54],"proposed":[29,53],"based":[30],"non-negative":[33],"matrix":[34],"factorization":[35],"with":[36],"sparseness":[37],"constraints":[38],"and":[39],"hierarchical":[40],"hidden":[41],"Markov":[42],"models":[43],"sequential":[45],"modeling":[46,86],"using":[47],"particle":[48],"filtering":[49],"decoding.":[51],"The":[52],"has":[55],"advantage":[57],"having":[59],"an":[60],"explicit":[61],"instrument":[62],"model":[63],"pitch":[65],"obtained":[66],"through":[67],"unsupervised":[68],"learning":[69],"as":[70,72,89],"well":[71],"access":[73],"single":[75],"note":[76],"contribution":[77],"probabilities":[78],"which":[79],"construct":[80],"complex":[82],"chord":[83,88],"instead":[84],"one":[90],"event":[91]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}