{"id":"https://openalex.org/W2077856219","doi":"https://doi.org/10.1109/icassp.2014.6854597","title":"Audio part mixture alignment based on hierarchical nonparametric Bayesian model of musical audio sequence collection","display_name":"Audio part mixture alignment based on hierarchical nonparametric Bayesian model of musical audio sequence collection","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2077856219","doi":"https://doi.org/10.1109/icassp.2014.6854597","mag":"2077856219"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]},{"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":["Kyoto University, Graduate School of Informatics, Kyoto, Japan","R&D Div., Yamaha Corp., Iwata, Japan"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Graduate School of Informatics, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"R&D Div., Yamaha Corp., Iwata, Japan","institution_ids":["https://openalex.org/I1295929820"]}]},{"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/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]},{"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":"Hiroshi G. Okuno","raw_affiliation_strings":["Kyoto University, Graduate School of Informatics, Kyoto, Japan","[Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan]"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Graduate School of Informatics, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]},{"raw_affiliation_string":"[Grad. Sch. of Inf., Kyoto Univ., Kyoto, Japan]","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056563843"],"corresponding_institution_ids":["https://openalex.org/I1295929820","https://openalex.org/I22299242","https://openalex.org/I39012071"],"apc_list":null,"apc_paid":null,"fwci":0.5823,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68259939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"15","issue":null,"first_page":"5212","last_page":"5216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9973999857902527,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9761000275611877,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.709760308265686},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5426223278045654},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5420400500297546},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5212141275405884},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4711681008338928},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.4664105176925659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39915597438812256},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10637229681015015},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07742494344711304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.709760308265686},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5426223278045654},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5420400500297546},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5212141275405884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4711681008338928},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.4664105176925659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39915597438812256},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10637229681015015},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07742494344711304},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854597","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1549486140","https://openalex.org/W2030511115","https://openalex.org/W2072183986","https://openalex.org/W2098101267","https://openalex.org/W2108473831","https://openalex.org/W2108494558","https://openalex.org/W2109958226","https://openalex.org/W2114127405","https://openalex.org/W2115979064","https://openalex.org/W2128064068","https://openalex.org/W2143513973","https://openalex.org/W2149368536","https://openalex.org/W2150452896","https://openalex.org/W2157283201","https://openalex.org/W2187741934","https://openalex.org/W2295370733","https://openalex.org/W6632893073","https://openalex.org/W6681200271","https://openalex.org/W6686958735","https://openalex.org/W6697198231"],"related_works":["https://openalex.org/W4243114048","https://openalex.org/W2529605301","https://openalex.org/W4237896776","https://openalex.org/W4231665652","https://openalex.org/W1837630526","https://openalex.org/W2000242494","https://openalex.org/W2335589441","https://openalex.org/W4296826658","https://openalex.org/W1979697693","https://openalex.org/W2164312800"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"\u201caudio":[3],"part":[4],"mixture":[5],"alignment,\u201d":[6],"a":[7,19,22,26,67,80,105],"method":[8,32,101,117],"for":[9],"temporally":[10],"aligning":[11],"multiple":[12],"audio":[13,35,53,62,128],"signals,":[14],"each":[15,34,44,52],"of":[16,21,25,29,61,124],"which":[17],"is":[18,64,77,89,102,112,118],"rendition":[20],"non-disjoint":[23],"subset":[24],"common":[27],"piece":[28],"music.":[30],"The":[31,99],"decomposes":[33],"signal":[36,54,63],"into":[37],"shared":[38,58],"components":[39,41],"and":[40,74,96,110],"unique":[42],"to":[43,91,121],"rendition.":[45],"At":[46],"the":[47,57,94,115,122],"same":[48],"time,":[49],"it":[50,111],"aligns":[51],"based":[55],"on":[56],"component.":[59],"Decomposition":[60],"modeled":[65,78],"using":[66],"hierarchical":[68],"Dirichlet":[69],"process":[70],"(Hierarchical":[71],"DP,":[72],"HDP),":[73],"sequence":[75],"alignment":[76,95,108],"as":[79],"left-to-right":[81],"hidden":[82],"Markov":[83],"model":[84],"(HMM).":[85],"Variational":[86],"Bayesian":[87],"inference":[88],"used":[90],"jointly":[92],"infer":[93],"component":[97],"decomposition.":[98],"proposed":[100,116],"compared":[103],"with":[104],"classic":[106],"audio-to-audio":[107],"method,":[109],"found":[113],"that":[114],"more":[119],"robust":[120],"discrepancy":[123],"parts":[125],"between":[126],"two":[127],"signals.":[129]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}