{"id":"https://openalex.org/W2403172465","doi":"https://doi.org/10.1109/icassp.2016.7472918","title":"Acoustic scene classification with matrix factorization for unsupervised feature learning","display_name":"Acoustic scene classification with matrix factorization for unsupervised feature learning","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2403172465","doi":"https://doi.org/10.1109/icassp.2016.7472918","mag":"2403172465"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5040132672","display_name":"Victor Bisot","orcid":null},"institutions":[{"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/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2802330208","display_name":"Statistics Belgium","ror":"https://ror.org/0246a9012","country_code":"BE","type":"government","lineage":["https://openalex.org/I2802330208","https://openalex.org/I4210095879"]},{"id":"https://openalex.org/I4210105651","display_name":"Laboratoire Traitement du Signal et de l'Image","ror":"https://ror.org/01f1amm71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I154526488","https://openalex.org/I4210105651","https://openalex.org/I4210105774","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":["BE","FR"],"is_corresponding":true,"raw_author_name":"Victor Bisot","raw_affiliation_strings":["LTCI, CNRS, T\u00e9l\u00e9om ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","Signal, Statistique et Apprentissage","D\u00e9partement Traitement du Signal et des Images"],"affiliations":[{"raw_affiliation_string":"LTCI, CNRS, T\u00e9l\u00e9om ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I190752583"]},{"raw_affiliation_string":"Signal, Statistique et Apprentissage","institution_ids":["https://openalex.org/I2802330208"]},{"raw_affiliation_string":"D\u00e9partement Traitement du Signal et des Images","institution_ids":["https://openalex.org/I4210105651"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"institutions":[{"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/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2802330208","display_name":"Statistics Belgium","ror":"https://ror.org/0246a9012","country_code":"BE","type":"government","lineage":["https://openalex.org/I2802330208","https://openalex.org/I4210095879"]},{"id":"https://openalex.org/I4210105651","display_name":"Laboratoire Traitement du Signal et de l'Image","ror":"https://ror.org/01f1amm71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I154526488","https://openalex.org/I4210105651","https://openalex.org/I4210105774","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":["BE","FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["LTCI, CNRS, T\u00e9l\u00e9om ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","Signal, Statistique et Apprentissage","D\u00e9partement Traitement du Signal et des Images"],"affiliations":[{"raw_affiliation_string":"LTCI, CNRS, T\u00e9l\u00e9om ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I190752583"]},{"raw_affiliation_string":"Signal, Statistique et Apprentissage","institution_ids":["https://openalex.org/I2802330208"]},{"raw_affiliation_string":"D\u00e9partement Traitement du Signal et des Images","institution_ids":["https://openalex.org/I4210105651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060031161","display_name":"Slim Essid","orcid":"https://orcid.org/0000-0002-0028-327X"},"institutions":[{"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/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2802330208","display_name":"Statistics Belgium","ror":"https://ror.org/0246a9012","country_code":"BE","type":"government","lineage":["https://openalex.org/I2802330208","https://openalex.org/I4210095879"]},{"id":"https://openalex.org/I4210105651","display_name":"Laboratoire Traitement du Signal et de l'Image","ror":"https://ror.org/01f1amm71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I154526488","https://openalex.org/I4210105651","https://openalex.org/I4210105774","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":["BE","FR"],"is_corresponding":false,"raw_author_name":"Slim Essid","raw_affiliation_strings":["LTCI, CNRS, T\u00e9l\u00e9om ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","Signal, Statistique et Apprentissage","D\u00e9partement Traitement du Signal et des Images"],"affiliations":[{"raw_affiliation_string":"LTCI, CNRS, T\u00e9l\u00e9om ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I190752583"]},{"raw_affiliation_string":"Signal, Statistique et Apprentissage","institution_ids":["https://openalex.org/I2802330208"]},{"raw_affiliation_string":"D\u00e9partement Traitement du Signal et des Images","institution_ids":["https://openalex.org/I4210105651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055423112","display_name":"Ga\u00ebl Richard","orcid":"https://orcid.org/0000-0002-4960-0010"},"institutions":[{"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/I190752583","display_name":"ParisTech","ror":"https://ror.org/05c2qg481","country_code":"FR","type":"education","lineage":["https://openalex.org/I190752583"]},{"id":"https://openalex.org/I277688954","display_name":"Universit\u00e9 Paris-Saclay","ror":"https://ror.org/03xjwb503","country_code":"FR","type":"education","lineage":["https://openalex.org/I277688954"]},{"id":"https://openalex.org/I2802330208","display_name":"Statistics Belgium","ror":"https://ror.org/0246a9012","country_code":"BE","type":"government","lineage":["https://openalex.org/I2802330208","https://openalex.org/I4210095879"]},{"id":"https://openalex.org/I4210105651","display_name":"Laboratoire Traitement du Signal et de l'Image","ror":"https://ror.org/01f1amm71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I154526488","https://openalex.org/I4210105651","https://openalex.org/I4210105774","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":["BE","FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["LTCI, CNRS, T\u00e9l\u00e9om ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","D\u00e9partement Traitement du Signal et des Images","Signal, Statistique et Apprentissage"],"affiliations":[{"raw_affiliation_string":"LTCI, CNRS, T\u00e9l\u00e9om ParisTech, Universit\u00e9 Paris-Saclay, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I277688954","https://openalex.org/I1294671590","https://openalex.org/I190752583"]},{"raw_affiliation_string":"D\u00e9partement Traitement du Signal et des Images","institution_ids":["https://openalex.org/I4210105651"]},{"raw_affiliation_string":"Signal, Statistique et Apprentissage","institution_ids":["https://openalex.org/I2802330208"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040132672"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I190752583","https://openalex.org/I277688954","https://openalex.org/I2802330208","https://openalex.org/I4210105651","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":12.22,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.99011233,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6445","last_page":"6449"},"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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":0.7920185923576355},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.758980393409729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.701196551322937},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.6932324767112732},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.691006064414978},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5830336809158325},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5608726143836975},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5178701877593994},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.516609251499176},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5133680105209351},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5004723072052002},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.47962674498558044},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4548022449016571},{"id":"https://openalex.org/keywords/projection","display_name":"Projection (relational algebra)","score":0.4331516623497009},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21351933479309082},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1276189386844635}],"concepts":[{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7920185923576355},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.758980393409729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.701196551322937},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6932324767112732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.691006064414978},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5830336809158325},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5608726143836975},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5178701877593994},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.516609251499176},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5133680105209351},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5004723072052002},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.47962674498558044},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4548022449016571},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4331516623497009},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21351933479309082},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1276189386844635},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1496704041","https://openalex.org/W1506222585","https://openalex.org/W1902027874","https://openalex.org/W1976258180","https://openalex.org/W1978274651","https://openalex.org/W1979594949","https://openalex.org/W2005876975","https://openalex.org/W2044447850","https://openalex.org/W2048174296","https://openalex.org/W2095147901","https://openalex.org/W2099741732","https://openalex.org/W2103235956","https://openalex.org/W2105622288","https://openalex.org/W2114508388","https://openalex.org/W2130640900","https://openalex.org/W2130789253","https://openalex.org/W2137343183","https://openalex.org/W2137561966","https://openalex.org/W2140095548","https://openalex.org/W2164877274","https://openalex.org/W2200864288","https://openalex.org/W2545232173","https://openalex.org/W3103385400","https://openalex.org/W6675803605"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,27,58],"study":[4,78],"the":[5,42,52,60,111,120],"use":[6,59],"of":[7,37,98],"unsupervised":[8,32],"feature":[9],"learning":[10],"for":[11,65],"acoustic":[12,17],"scene":[13],"classification":[14],"(ASC).":[15],"The":[16,108],"environment":[18],"recordings":[19],"are":[20,44],"represented":[21],"by":[22],"time-frequency":[23],"images":[24,43],"from":[25],"which":[26],"learn":[28],"features":[29,64],"in":[30,123],"an":[31],"manner.":[33],"After":[34],"a":[35,55,73],"set":[36],"preprocessing":[38],"and":[39,89,105],"pooling":[40],"steps,":[41],"decomposed":[45],"using":[46],"matrix":[47,80],"factorization":[48,81],"methods.":[49],"By":[50],"decomposing":[51],"data":[53],"on":[54,72],"learned":[56],"dictionary,":[57],"projection":[61],"coefficients":[62],"as":[63,84,94,96],"classification.":[66],"An":[67],"experimental":[68],"evaluation":[69],"is":[70],"done":[71],"large":[74],"ASC":[75],"dataset":[76],"to":[77,115,119],"popular":[79],"methods":[82],"such":[83],"Principal":[85],"Component":[86],"Analysis":[87],"(PCA)":[88],"Non-negative":[90],"Matrix":[91],"Factorization":[92],"(NMF)":[93],"well":[95],"some":[97],"their":[99],"extensions":[100],"including":[101],"sparse,":[102],"kernel":[103],"based":[104],"convolutive":[106],"variants.":[107],"results":[109,122],"show":[110],"compared":[112,118],"variants":[113],"lead":[114],"significant":[116],"improvement":[117],"state-of-the-art":[121],"ASC.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":5}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}