{"id":"https://openalex.org/W2100816929","doi":"https://doi.org/10.1109/icassp.2009.4959972","title":"High resolution audio synchronization using chroma onset features","display_name":"High resolution audio synchronization using chroma onset features","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2100816929","doi":"https://doi.org/10.1109/icassp.2009.4959972","mag":"2100816929"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-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/A5001413512","display_name":"Sebastian Ewert","orcid":"https://orcid.org/0000-0002-0718-0476"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sebastian Ewert","raw_affiliation_strings":["Universit\u00e4t Bonn, Informatik III, Bonn, Germany","Universit\u00e4t Bonn, Informatik III, R\u00f6merstr. 164, D-53117, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"Universit\u00e4t Bonn, Informatik III, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Universit\u00e4t Bonn, Informatik III, R\u00f6merstr. 164, D-53117, Germany#TAB#","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard Muller","raw_affiliation_strings":["University of Saarland, Saarbruecken, Germany","Saarland University and MPI Informatik, Campus E1 4, D-66123 Saarbr\u00fccken, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Saarland, Saarbruecken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarland University and MPI Informatik, Campus E1 4, D-66123 Saarbr\u00fccken, Germany#TAB#","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078194825","display_name":"Peter Grosche","orcid":"https://orcid.org/0000-0002-5525-5233"},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Grosche","raw_affiliation_strings":["University of Saarland, Saarbruecken, Germany","Saarland University and MPI Informatik, Campus E1 4, D-66123 Saarbr\u00fccken, Germany#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Saarland, Saarbruecken, Germany","institution_ids":["https://openalex.org/I91712215"]},{"raw_affiliation_string":"Saarland University and MPI Informatik, Campus E1 4, D-66123 Saarbr\u00fccken, Germany#TAB#","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001413512"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":null,"apc_paid":null,"fwci":10.7039,"has_fulltext":false,"cited_by_count":135,"citation_normalized_percentile":{"value":0.98938922,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1869","last_page":"1872"},"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":0.9975000023841858,"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":0.9973999857902527,"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/midi","display_name":"MIDI","score":0.8292700052261353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8278971910476685},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8003379106521606},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.743869423866272},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7106641530990601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5856888294219971},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5089812278747559},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4866712689399719},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.44451603293418884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4226107597351074},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3451962471008301},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.28220295906066895},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.20377838611602783},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07792705297470093}],"concepts":[{"id":"https://openalex.org/C8112396","wikidata":"https://www.wikidata.org/wiki/Q80535","display_name":"MIDI","level":2,"score":0.8292700052261353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278971910476685},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8003379106521606},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.743869423866272},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7106641530990601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5856888294219971},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5089812278747559},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4866712689399719},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.44451603293418884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4226107597351074},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3451962471008301},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.28220295906066895},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20377838611602783},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07792705297470093},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icassp.2009.4959972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.415.1511","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.415.1511","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mpi-inf.mpg.de/resources/MIR/SyncRWC60/2009_EwertMuellerGrosche_HighResAudioSync_ICASSP.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:520463","is_oa":false,"landing_page_url":"http://edoc.mpg.de/520463","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE, 1869-1872 (2009)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1324303","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-000F-19B3-F","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W170732776","https://openalex.org/W1519655822","https://openalex.org/W2139107403","https://openalex.org/W2140304104","https://openalex.org/W2153331925","https://openalex.org/W2398080269","https://openalex.org/W6631117800","https://openalex.org/W6712303689"],"related_works":["https://openalex.org/W2153331925","https://openalex.org/W2369521057","https://openalex.org/W4234749112","https://openalex.org/W1575424942","https://openalex.org/W2398454874","https://openalex.org/W126167045","https://openalex.org/W2105745964","https://openalex.org/W4298140471","https://openalex.org/W2289868279","https://openalex.org/W4231351862"],"abstract_inverted_index":{"The":[0],"general":[1],"goal":[2],"of":[3,60,66,81,97],"music":[4,23,93],"synchronization":[5,73,100],"is":[6],"to":[7,25,37,78],"automatically":[8],"align":[9],"the":[10,56,64,95],"multiple":[11],"information":[12],"sources":[13],"such":[14,32],"as":[15],"audio":[16,52],"recordings,":[17],"MIDI":[18],"files,":[19],"or":[20],"digitized":[21],"sheet":[22],"related":[24],"a":[26,39],"given":[27],"musical":[28],"work.":[29],"In":[30,46],"computing":[31],"alignments,":[33],"one":[34],"typically":[35],"has":[36],"face":[38],"delicate":[40],"tradeoff":[41],"between":[42],"robustness":[43,65],"and":[44],"accuracy.":[45],"this":[47],"paper,":[48],"we":[49],"introduce":[50],"novel":[51],"features":[53,62],"that":[54],"combine":[55],"high":[57],"temporal":[58],"accuracy":[59],"onset":[61],"with":[63],"chroma":[67],"features.":[68,84],"We":[69,85],"show":[70],"how":[71],"previous":[72],"methods":[74],"can":[75],"be":[76],"extended":[77],"make":[79],"use":[80],"these":[82],"new":[83],"report":[86],"on":[87,90],"experiments":[88],"based":[89],"polyphonic":[91],"Western":[92],"demonstrating":[94],"improvements":[96],"our":[98],"proposed":[99],"framework.":[101]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
