{"id":"https://openalex.org/W2174411846","doi":"https://doi.org/10.1109/waspaa.2015.7336929","title":"Unified inter- and intra-recording duration model for multiple music audio alignment","display_name":"Unified inter- and intra-recording duration model for multiple music audio alignment","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2174411846","doi":"https://doi.org/10.1109/waspaa.2015.7336929","mag":"2174411846"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2015.7336929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2015.7336929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5056563843","display_name":"Akira Maezawa","orcid":null},"institutions":[{"id":"https://openalex.org/I1295929820","display_name":"Yamaha (Japan)","ror":"https://ror.org/05s7fvh27","country_code":"JP","type":"company","lineage":["https://openalex.org/I1295929820"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Akira Maezawa","raw_affiliation_strings":["Yamaha Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Yamaha Corporation, Japan","institution_ids":["https://openalex.org/I1295929820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003325000","display_name":"Katsutoshi Itoyama","orcid":"https://orcid.org/0000-0002-7098-3896"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsutoshi Itoyama","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067956319","display_name":"Kazuyoshi Yoshii","orcid":"https://orcid.org/0000-0001-8387-8609"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuyoshi Yoshii","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Japan","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005141184","display_name":"Hiroshi G. Okuno","orcid":"https://orcid.org/0000-0002-8704-4318"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroshi G. Okuno","raw_affiliation_strings":["Graduate School of Creative Science and Engineering, Waseda University, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Creative Science and Engineering, Waseda University, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5056563843"],"corresponding_institution_ids":["https://openalex.org/I1295929820"],"apc_list":null,"apc_paid":null,"fwci":0.579,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67878057,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/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":0.9987000226974487,"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/duration","display_name":"Duration (music)","score":0.9418696165084839},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7508994936943054},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.690371572971344},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.6686390042304993},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5640131235122681},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5235944986343384},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4680357277393341},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.46447718143463135},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.42867058515548706},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.343967467546463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31219059228897095},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12727969884872437},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.11756658554077148}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.9418696165084839},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7508994936943054},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.690371572971344},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.6686390042304993},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5640131235122681},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5235944986343384},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4680357277393341},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.46447718143463135},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.42867058515548706},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.343967467546463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31219059228897095},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12727969884872437},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.11756658554077148},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa.2015.7336929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2015.7336929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.7571","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.7571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://winnie.kuis.kyoto-u.ac.jp/%7Eyoshii/papers/waspaa-2015-maezawa.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W106639881","https://openalex.org/W150780440","https://openalex.org/W1513874359","https://openalex.org/W1549486140","https://openalex.org/W1591584603","https://openalex.org/W1968730187","https://openalex.org/W2077856219","https://openalex.org/W2102716594","https://openalex.org/W2115979064","https://openalex.org/W2128064068","https://openalex.org/W2128352481","https://openalex.org/W2139686198","https://openalex.org/W2142927150","https://openalex.org/W2144234122","https://openalex.org/W2146302296","https://openalex.org/W2150308923","https://openalex.org/W2150452896","https://openalex.org/W2160537075","https://openalex.org/W2293056991","https://openalex.org/W2296201206","https://openalex.org/W2386159464","https://openalex.org/W2395462034","https://openalex.org/W2396304210","https://openalex.org/W2404274215","https://openalex.org/W2405017082","https://openalex.org/W2406388223","https://openalex.org/W6604351559","https://openalex.org/W6632893073","https://openalex.org/W6681102793","https://openalex.org/W6697237593","https://openalex.org/W6710527233","https://openalex.org/W6711855267","https://openalex.org/W6712345126","https://openalex.org/W6713534251","https://openalex.org/W6713718600"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W2056234363","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W3004352674","https://openalex.org/W2088690926","https://openalex.org/W1590604789","https://openalex.org/W2155527258"],"abstract_inverted_index":{"This":[0,78],"paper":[1,79,91],"presents":[2],"a":[3,21,60,69,84],"probabilistic":[4,29],"audio-to-audio":[5],"alignment":[6,31,115],"method":[7],"that":[8,109],"focuses":[9],"on":[10,53],"the":[11,14,39,44,54,66,90,93,97,100,110,114],"relationship":[12],"among":[13],"note":[15,71,101],"durations":[16,40],"of":[17,20,23,41,47,56,68,99],"different":[18,73],"performances":[19],"piece":[22,46],"music.":[24,48],"A":[25],"key":[26],"issue":[27],"in":[28,34,43],"audio":[30],"methods":[32],"is":[33],"expressing":[35],"how":[36],"interrelated":[37],"are":[38],"notes":[42,58],"underlying":[45],"Existing":[49],"studies":[50],"focus":[51],"either":[52],"duration":[55,63,67,76,102],"adjacent":[57],"within":[59],"recording":[61],"(intra-recording":[62],"model),":[64],"or":[65],"given":[70],"across":[72],"recordings":[74],"(inter-recording":[75],"model).":[77],"unifies":[80],"these":[81],"approaches":[82],"through":[83],"simple":[85],"modification":[86],"to":[87,103],"them.":[88],"Furthermore,":[89],"extends":[92],"unified":[94],"model,":[95],"allowing":[96],"dynamics":[98],"change":[104],"sporadically.":[105],"Experimental":[106],"evaluation":[107],"demonstrated":[108],"proposed":[111],"models":[112],"decrease":[113],"error.":[116]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}