{"id":"https://openalex.org/W2155531311","doi":"https://doi.org/10.1109/aspaa.2009.5346527","title":"Factorial Scaled Hidden Markov Model for polyphonic audio representation and source separation","display_name":"Factorial Scaled Hidden Markov Model for polyphonic audio representation and source separation","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2155531311","doi":"https://doi.org/10.1109/aspaa.2009.5346527","mag":"2155531311"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2009.5346527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2009.5346527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00553336","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073788938","display_name":"Alexey Ozerov","orcid":"https://orcid.org/0000-0003-4834-5166"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alexey Ozerov","raw_affiliation_strings":["Institut Telecom, CNRS LTCI, Telecom ParisTech, Paris, France","Metiss Group, IRISA, Rennes, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Telecom, CNRS LTCI, Telecom ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Metiss Group, IRISA, Rennes, France","institution_ids":["https://openalex.org/I2802519937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022368934","display_name":"C\u00e9dric F\u00e9votte","orcid":"https://orcid.org/0000-0003-3801-5534"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Cedric Fevotte","raw_affiliation_strings":["CNRS LTCI, Telecom ParisTech, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CNRS LTCI, Telecom ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109941579","display_name":"Maurice Charbit","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I205703379","display_name":"Institut Mines-T\u00e9l\u00e9com","ror":"https://ror.org/025vp2923","country_code":"FR","type":"facility","lineage":["https://openalex.org/I205703379"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maurice Charbit","raw_affiliation_strings":["Institut Telecom, CNRS LTCI, Telecom ParisTech, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Telecom, CNRS LTCI, Telecom ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I205703379","https://openalex.org/I4210165912"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.4207,"has_fulltext":false,"cited_by_count":90,"citation_normalized_percentile":{"value":0.98301105,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9987999796867371,"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/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8904725313186646},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8275197744369507},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6102026104927063},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5748600363731384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5596069097518921},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.5389045476913452},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4910905361175537},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48394468426704407},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.48298659920692444},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.44893065094947815},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4354918897151947},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4226207733154297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4057005047798157},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3586500287055969},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3476945757865906},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.31686824560165405},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.23051604628562927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16290724277496338},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13713553547859192}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8904725313186646},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8275197744369507},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6102026104927063},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5748600363731384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5596069097518921},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.5389045476913452},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4910905361175537},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48394468426704407},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.48298659920692444},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.44893065094947815},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4354918897151947},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4226207733154297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4057005047798157},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3586500287055969},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3476945757865906},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.31686824560165405},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.23051604628562927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16290724277496338},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13713553547859192},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/aspaa.2009.5346527","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2009.5346527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:inria-00553336v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00553336","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA'09), Oct 2009, Mohonk, NY, United States","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00553336v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00553336","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA'09), Oct 2009, Mohonk, NY, United States","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1528056001","https://openalex.org/W2039844283","https://openalex.org/W2049633694","https://openalex.org/W2078887028","https://openalex.org/W2099904336","https://openalex.org/W2103031592","https://openalex.org/W2115283881","https://openalex.org/W2117042571","https://openalex.org/W2118292600","https://openalex.org/W2125838338","https://openalex.org/W2134807719","https://openalex.org/W2394955069","https://openalex.org/W6712099778"],"related_works":["https://openalex.org/W2037504162","https://openalex.org/W2774154397","https://openalex.org/W2921513691","https://openalex.org/W1979654135","https://openalex.org/W2156699640","https://openalex.org/W2098101267","https://openalex.org/W2081322759","https://openalex.org/W2156181515","https://openalex.org/W2146544734","https://openalex.org/W2158112352"],"abstract_inverted_index":{"We":[0,35,76],"present":[1],"a":[2,60,91],"new":[3],"probabilistic":[4],"model":[5,14,26],"for":[6,41,83],"polyphonic":[7],"audio":[8],"termed":[9],"factorial":[10],"scaled":[11,24],"hidden":[12],"Markov":[13],"(FS-HMM),":[15],"which":[16,45],"generalizes":[17],"several":[18],"existing":[19],"models,":[20],"notably":[21],"the":[22,28,48,78,84],"Gaussian":[23],"mixture":[25],"and":[27,65,94],"Itakura-Saito":[29],"nonnegative":[30],"matrix":[31],"factorization":[32],"(NMF)":[33],"model.":[34],"describe":[36],"two":[37],"expectation-maximization":[38],"(EM)":[39],"algorithms":[40],"maximum":[42],"likelihood":[43],"estimation,":[44],"differ":[46],"by":[47],"choice":[49],"of":[50,87],"complete":[51,62],"data":[52,63],"set.":[53],"The":[54],"second":[55],"EM":[56],"algorithm,":[57],"based":[58],"on":[59],"reduced":[61],"set":[64],"multiplicative":[66],"updates":[67],"inspired":[68],"from":[69,90],"NMF":[70],"methodology,":[71],"exhibits":[72],"much":[73],"faster":[74],"convergence.":[75],"consider":[77],"FS-HMM":[79],"in":[80],"different":[81],"configurations":[82],"difficult":[85],"problem":[86],"speech/music":[88],"separation":[89],"single":[92],"channel":[93],"report":[95],"satisfying":[96],"results.":[97]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":14},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":12}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}