{"id":"https://openalex.org/W1969721256","doi":"https://doi.org/10.1109/wiamis.2013.6616131","title":"Saliency-based modeling of acoustic scenes using sparse non-negative matrix factorization","display_name":"Saliency-based modeling of acoustic scenes using sparse non-negative matrix factorization","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W1969721256","doi":"https://doi.org/10.1109/wiamis.2013.6616131","mag":"1969721256"},"language":"en","primary_location":{"id":"doi:10.1109/wiamis.2013.6616131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiamis.2013.6616131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)","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/A5014833085","display_name":"Benjamin Cauchi","orcid":"https://orcid.org/0000-0003-0338-492X"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Benjamin Cauchi","raw_affiliation_strings":["Fraunhofer Idmt, Speech and Audio Technology Hearing, Oldenburg, Germany","Hearing, Speech & Audio Technol., FRAUNHOFER IDMT, Oldenburg, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Idmt, Speech and Audio Technology Hearing, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]},{"raw_affiliation_string":"Hearing, Speech & Audio Technol., FRAUNHOFER IDMT, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029522748","display_name":"Mathieu Lagrange","orcid":"https://orcid.org/0000-0002-1253-4427"},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Lagrange","raw_affiliation_strings":["IRCAM, UPMC, Centre National de la Recherche Scientifique, Paris, France","IRCAM, UPMC, Paris, France"],"affiliations":[{"raw_affiliation_string":"IRCAM, UPMC, Centre National de la Recherche Scientifique, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I1294671590","https://openalex.org/I39804081"]},{"raw_affiliation_string":"IRCAM, UPMC, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112603981","display_name":"Nicolas Misdariis","orcid":null},"institutions":[{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE","FR"],"is_corresponding":false,"raw_author_name":"Nicolas Misdariis","raw_affiliation_strings":["Fraunhofer Idmt, Speech and Audio Technology Hearing, Oldenburg, Germany","IRCAM, UPMC, Paris, France"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Idmt, Speech and Audio Technology Hearing, Oldenburg, Germany","institution_ids":["https://openalex.org/I4210138578"]},{"raw_affiliation_string":"IRCAM, UPMC, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010210485","display_name":"Arshia Cont","orcid":"https://orcid.org/0000-0002-7352-7212"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I35345632","display_name":"Institut de Recherche et Coordination Acoustique Musique","ror":"https://ror.org/0121jnt59","country_code":"FR","type":"education","lineage":["https://openalex.org/I35345632"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Arshia Cont","raw_affiliation_strings":["IRCAM, UPMC, Centre National de la Recherche Scientifique, Paris, France","IRCAM, UPMC, Paris, France"],"affiliations":[{"raw_affiliation_string":"IRCAM, UPMC, Centre National de la Recherche Scientifique, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I1294671590","https://openalex.org/I39804081"]},{"raw_affiliation_string":"IRCAM, UPMC, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014833085"],"corresponding_institution_ids":["https://openalex.org/I4210138578"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.04689984,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"401","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7834752202033997},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.7634845972061157},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.7348236441612244},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.6939055919647217},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6711322069168091},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6431646943092346},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5996023416519165},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5418892502784729},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5319856405258179},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.515284538269043},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4831249415874481},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4730127155780792},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46041566133499146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45890727639198303},{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.4545449912548065},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4282670319080353},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25039350986480713},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.12005496025085449},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09841963648796082},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06733837723731995}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7834752202033997},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.7634845972061157},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.7348236441612244},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.6939055919647217},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6711322069168091},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431646943092346},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5996023416519165},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5418892502784729},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5319856405258179},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.515284538269043},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4831249415874481},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4730127155780792},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46041566133499146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45890727639198303},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.4545449912548065},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4282670319080353},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25039350986480713},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.12005496025085449},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09841963648796082},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06733837723731995},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wiamis.2013.6616131","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiamis.2013.6616131","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 14th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS)","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-300562","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-300562.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/383185","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/383185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W952881364","https://openalex.org/W1902027874","https://openalex.org/W1965480374","https://openalex.org/W2048174296","https://openalex.org/W2102381657","https://openalex.org/W2118718620","https://openalex.org/W2545232173","https://openalex.org/W2561557072","https://openalex.org/W2731904613","https://openalex.org/W4233392025","https://openalex.org/W6677759377","https://openalex.org/W6740663318"],"related_works":["https://openalex.org/W2362704157","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/W3199891340","https://openalex.org/W2156699640","https://openalex.org/W2045265907"],"abstract_inverted_index":{"The":[0,69],"modeling":[1],"of":[2,30,52,54],"auditory":[3],"scenes":[4,39],"is":[5,40,46],"a":[6,50,58,87],"challenging":[7],"task":[8],"in":[9,42],"Computational":[10],"Auditory":[11],"Scene":[12],"Analysis.":[13],"A":[14],"method":[15],"based":[16],"on":[17,49,77],"sparse":[18],"Non-negative":[19],"Matrix":[20],"Factorization":[21],"that":[22],"can":[23],"be":[24],"used":[25],"with":[26,65],"no":[27],"prior":[28],"knowledge":[29],"the":[31,36,66,81,94],"audio":[32],"content":[33],"to":[34,75],"establish":[35],"similarity":[37],"between":[38],"proposed":[41,70],"this":[43],"work.":[44],"It":[45],"then":[47],"evaluated":[48],"corpus":[51],"soundscapes":[53],"train":[55],"stations":[56],"from":[57],"perceptual":[59],"study":[60],"and":[61],"results":[62],"are":[63],"compared":[64],"human":[67,95],"perception.":[68],"method,":[71],"by":[72],"being":[73],"able":[74],"focus":[76],"salient":[78],"events":[79],"within":[80],"scene,":[82],"achieves":[83],"better":[84],"performances":[85],"than":[86],"state-of-the-art":[88],"Bag-of-Frames":[89],"approach":[90],"though":[91],"not":[92],"reaching":[93],"performances.":[96]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}
