{"id":"https://openalex.org/W2008565517","doi":"https://doi.org/10.1109/aspaa.2011.6082324","title":"Bayesian nonparametric spectrogram modeling based on infinite factorial infinite hidden Markov model","display_name":"Bayesian nonparametric spectrogram modeling based on infinite factorial infinite hidden Markov model","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2008565517","doi":"https://doi.org/10.1109/aspaa.2011.6082324","mag":"2008565517"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2011.6082324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5103244481","display_name":"Masahiro Nakano","orcid":"https://orcid.org/0009-0008-9378-0099"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masahiro Nakano","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Graduate School of Information Science and Technology, The University of Tokyo. 7-3-1 Hongo, Bunkyo-ku, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo. 7-3-1 Hongo, Bunkyo-ku, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Atsugi, Kanagawa, Japan","NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Atsugi, Kanagawa, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Corporation, NTT Communication Science Laboratories, Atsugi, Kanagawa, Japan","NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Corporation, NTT Communication Science Laboratories, Atsugi, Kanagawa, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, 3-1 Morinosato Wakamiya, Atsugi, Kanagawa 243-0198, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102941659","display_name":"Tomohiko Nakamura","orcid":"https://orcid.org/0000-0003-4385-7170"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiko Nakamura","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Graduate School of Information Science and Technology, The University of Tokyo. 7-3-1 Hongo, Bunkyo-ku, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo. 7-3-1 Hongo, Bunkyo-ku, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Graduate School of Information Science and Technology, The University of Tokyo. 7-3-1 Hongo, Bunkyo-ku, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo. 7-3-1 Hongo, Bunkyo-ku, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003450550","display_name":"Shigeki Sagayama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Sagayama","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","Graduate School of Information Science and Technology, The University of Tokyo. 7-3-1 Hongo, Bunkyo-ku, 113-8656, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo. 7-3-1 Hongo, Bunkyo-ku, 113-8656, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103244481"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":8.1239,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.97373729,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"101","issue":null,"first_page":"325","last_page":"328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.9984999895095825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8796424865722656},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8305474519729614},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7686560153961182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6388702392578125},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.6205809712409973},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5801646113395691},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5609038472175598},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5001945495605469},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4877929985523224},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4730084240436554},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.45201122760772705},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4496769905090332},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43875208497047424},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.40017077326774597},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3850819766521454},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2983468174934387},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20593160390853882}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8796424865722656},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8305474519729614},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7686560153961182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6388702392578125},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.6205809712409973},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5801646113395691},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5609038472175598},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5001945495605469},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4877929985523224},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4730084240436554},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.45201122760772705},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4496769905090332},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43875208497047424},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.40017077326774597},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3850819766521454},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2983468174934387},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20593160390853882},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aspaa.2011.6082324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W176887922","https://openalex.org/W1504512260","https://openalex.org/W1519655822","https://openalex.org/W1544503773","https://openalex.org/W1902027874","https://openalex.org/W2113526703","https://openalex.org/W2119239801","https://openalex.org/W2135537007","https://openalex.org/W2155531311","https://openalex.org/W2157906684","https://openalex.org/W2158266063","https://openalex.org/W2160697975","https://openalex.org/W2169895393","https://openalex.org/W2187741934","https://openalex.org/W6607207477","https://openalex.org/W6630142929","https://openalex.org/W6683215398","https://openalex.org/W6686958735","https://openalex.org/W6857808910"],"related_works":["https://openalex.org/W2123043102","https://openalex.org/W2577807713","https://openalex.org/W2098101267","https://openalex.org/W2037504162","https://openalex.org/W2774154397","https://openalex.org/W2146544734","https://openalex.org/W2156699640","https://openalex.org/W1979654135","https://openalex.org/W2156181515","https://openalex.org/W2081322759"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,54,146],"Bayesian":[4,147],"nonparametric":[5,148],"latent":[6,44],"source":[7,35],"discovery":[8],"method":[9],"for":[10],"music":[11,24,33,160],"signal":[12,16],"analysis.":[13],"In":[14],"audio":[15],"analysis,":[17],"an":[18,81,163,174],"important":[19,82],"goal":[20],"is":[21,80,180],"to":[22,84,114],"decompose":[23],"signals":[25],"into":[26,136],"individual":[27],"notes,":[28],"with":[29,116],"applications":[30],"such":[31],"as":[32,119],"transcription,":[34],"separation":[36],"or":[37],"note-level":[38],"manipulation.":[39],"Recently,":[40],"the":[41,86,101,123,128,185],"use":[42],"of":[43,58,88,103,125,130,150,167,170,178],"variable":[45],"decompositions,":[46],"especially":[47],"nonnegative":[48],"matrix":[49],"factorization":[50],"(NMF),":[51],"has":[52],"been":[53],"very":[55],"active":[56],"area":[57],"research.":[59],"These":[60],"methods":[61],"are":[62,108],"facing":[63],"two,":[64],"mutually":[65],"dependent,":[66],"problems:":[67],"first,":[68],"instrument":[69],"sounds":[70],"often":[71],"exhibit":[72],"time-varying":[73,78],"spectra,":[74],"and":[75,105,132,152],"grasping":[76],"this":[77],"nature":[79],"factor":[83],"characterize":[85],"diversity":[87],"each":[89,169],"instrument;":[90],"moreover,":[91],"in":[92,99,162,173],"many":[93],"cases":[94],"we":[95],"do":[96],"not":[97],"know":[98],"advance":[100],"number":[102,129,166,177],"sources":[104,131],"which":[106,171],"instruments":[107],"played.":[109],"Conventional":[110],"decompositions":[111],"generally":[112],"fail":[113],"cope":[115],"these":[117,142],"issues":[118],"they":[120],"suffer":[121],"from":[122,184],"difficulties":[124],"automatically":[126,133,164,182],"determining":[127],"grouping":[134],"spectra":[135],"single":[137],"events.":[138],"We":[139],"address":[140],"both":[141],"problems":[143],"by":[144],"developing":[145],"fusion":[149],"NMF":[151],"hidden":[153],"Markov":[154],"model":[155,158],"(HMM).":[156],"Our":[157],"decomposes":[159],"spectrograms":[161],"estimated":[165,183],"components,":[168],"consisting":[172],"HMM":[175],"whose":[176],"states":[179],"also":[181],"data.":[186]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}