{"id":"https://openalex.org/W2177710760","doi":"https://doi.org/10.1109/waspaa.2015.7336884","title":"Early frame-based detection of acoustic scenes","display_name":"Early frame-based detection of acoustic scenes","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2177710760","doi":"https://doi.org/10.1109/waspaa.2015.7336884","mag":"2177710760"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2015.7336884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2015.7336884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01890049","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043113193","display_name":"Maxime Sangnier","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/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]},{"id":"https://openalex.org/I4210144844","display_name":"Laboratoire d\u2019Analyse et de Math\u00e9matiques Appliqu\u00e9es","ror":"https://ror.org/0581g8849","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I197681013","https://openalex.org/I4210141950","https://openalex.org/I4210144844","https://openalex.org/I4210154111"]},{"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":"Maxime Sangnier","raw_affiliation_strings":["LTCI UMR CNRS 5141, Telecom ParisTech","LS2D (CEA, LIST) - Laboratoire Sciences des Donn\u00e9es et de la D\u00e9cision (CEA, LIST) (anciennement Laboratoire Analyse des Donn\u00e9es et Intelligence des Syst\u00e8mes (LADIS), Laboratoire Outils d'Analyse des Donn\u00e9es (LOAD), Laboratoire des Processus Stochastiques et Stationnaires (LPSS) - France)","LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LTCI UMR CNRS 5141, Telecom ParisTech","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I1294671590","https://openalex.org/I4210165912"]},{"raw_affiliation_string":"LS2D (CEA, LIST) - Laboratoire Sciences des Donn\u00e9es et de la D\u00e9cision (CEA, LIST) (anciennement Laboratoire Analyse des Donn\u00e9es et Intelligence des Syst\u00e8mes (LADIS), Laboratoire Outils d'Analyse des Donn\u00e9es (LOAD), Laboratoire des Processus Stochastiques et Stationnaires (LPSS) - France)","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210085861","https://openalex.org/I4210144844"]},{"raw_affiliation_string":"LTCI - Laboratoire Traitement et Communication de l'Information (46 rue Barrault F-75634 Paris Cedex 13 - France)","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086916160","display_name":"J\u00e9r\u00f4me Gauthier","orcid":"https://orcid.org/0009-0007-9894-9044"},"institutions":[{"id":"https://openalex.org/I2738703131","display_name":"Commissariat \u00e0 l'\u00c9nergie Atomique et aux \u00c9nergies Alternatives","ror":"https://ror.org/00jjx8s55","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131"]},{"id":"https://openalex.org/I4210085861","display_name":"Laboratoire d'Int\u00e9gration des Syst\u00e8mes et des Technologies","ror":"https://ror.org/000dbcc61","country_code":"FR","type":"government","lineage":["https://openalex.org/I2738703131","https://openalex.org/I2738703131","https://openalex.org/I277688954","https://openalex.org/I4210085861","https://openalex.org/I4210117989"]},{"id":"https://openalex.org/I4210144844","display_name":"Laboratoire d\u2019Analyse et de Math\u00e9matiques Appliqu\u00e9es","ror":"https://ror.org/0581g8849","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I197681013","https://openalex.org/I4210141950","https://openalex.org/I4210144844","https://openalex.org/I4210154111"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jerome Gauthier","raw_affiliation_strings":["LADIS, CEA, LIST","LS2D (CEA, LIST) - Laboratoire Sciences des Donn\u00e9es et de la D\u00e9cision (CEA, LIST) (anciennement Laboratoire Analyse des Donn\u00e9es et Intelligence des Syst\u00e8mes (LADIS), Laboratoire Outils d'Analyse des Donn\u00e9es (LOAD), Laboratoire des Processus Stochastiques et Stationnaires (LPSS) - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LADIS, CEA, LIST","institution_ids":["https://openalex.org/I4210085861"]},{"raw_affiliation_string":"LS2D (CEA, LIST) - Laboratoire Sciences des Donn\u00e9es et de la D\u00e9cision (CEA, LIST) (anciennement Laboratoire Analyse des Donn\u00e9es et Intelligence des Syst\u00e8mes (LADIS), Laboratoire Outils d'Analyse des Donn\u00e9es (LOAD), Laboratoire des Processus Stochastiques et Stationnaires (LPSS) - France)","institution_ids":["https://openalex.org/I2738703131","https://openalex.org/I4210085861","https://openalex.org/I4210144844"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031137438","display_name":"Alain Rakotomamonjy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108118","display_name":"Laboratoire d'Informatique, du Traitement de l'Information et des Syst\u00e8mes","ror":"https://ror.org/01f1vfy95","country_code":"FR","type":"facility","lineage":["https://openalex.org/I141576021","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210108118","https://openalex.org/I62396329","https://openalex.org/I88814501"]},{"id":"https://openalex.org/I62396329","display_name":"Universit\u00e9 de Rouen Normandie","ror":"https://ror.org/03nhjew95","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I62396329"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Alain Rakotomamonjy","raw_affiliation_strings":["LITIS EA 4108, University of Rouen","DocApp - LITIS - Equipe Apprentissage (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LITIS EA 4108, University of Rouen","institution_ids":["https://openalex.org/I4210108118","https://openalex.org/I62396329"]},{"raw_affiliation_string":"DocApp - LITIS - Equipe Apprentissage (France)","institution_ids":["https://openalex.org/I4210108118"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4856,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57290171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"14","issue":null,"first_page":"1","last_page":"5"},"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":0.9997000098228455,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8191280364990234},{"id":"https://openalex.org/keywords/soundscape","display_name":"Soundscape","score":0.7065533995628357},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5529537200927734},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5495006442070007},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5414838790893555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4848800599575043},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4683109223842621},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4204002022743225},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.411493718624115},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34618526697158813},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.19088613986968994},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16500109434127808},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08790925145149231}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191280364990234},{"id":"https://openalex.org/C142795923","wikidata":"https://www.wikidata.org/wiki/Q1358257","display_name":"Soundscape","level":3,"score":0.7065533995628357},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5529537200927734},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5495006442070007},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5414838790893555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4848800599575043},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4683109223842621},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4204002022743225},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.411493718624115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34618526697158813},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.19088613986968994},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16500109434127808},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08790925145149231},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/waspaa.2015.7336884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2015.7336884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01890049v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01890049","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) 2015, Oct 2015, New Paltz, United States. pp.7336884, &#x27E8;10.1109/WASPAA.2015.7336884&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01890049v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01890049","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) 2015, Oct 2015, New Paltz, United States. pp.7336884, &#x27E8;10.1109/WASPAA.2015.7336884&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W14817117","https://openalex.org/W1699074795","https://openalex.org/W1987091651","https://openalex.org/W2016776918","https://openalex.org/W2073419240","https://openalex.org/W2078579128","https://openalex.org/W2078765398","https://openalex.org/W2093231248","https://openalex.org/W2095147901","https://openalex.org/W2098166271","https://openalex.org/W2098899567","https://openalex.org/W2103235956","https://openalex.org/W2105842272","https://openalex.org/W2107579427","https://openalex.org/W2110119381","https://openalex.org/W2115240329","https://openalex.org/W2130640900","https://openalex.org/W2130698119","https://openalex.org/W2135046866","https://openalex.org/W2137343183","https://openalex.org/W2143004591","https://openalex.org/W2144635266","https://openalex.org/W2146634731","https://openalex.org/W2167257437","https://openalex.org/W2952715980","https://openalex.org/W3103385400","https://openalex.org/W6637558073","https://openalex.org/W6669992580","https://openalex.org/W6675043963","https://openalex.org/W6675783020","https://openalex.org/W6676275395","https://openalex.org/W6677492792","https://openalex.org/W6684301616"],"related_works":["https://openalex.org/W1254698036","https://openalex.org/W2896201871","https://openalex.org/W2282503792","https://openalex.org/W1988083194","https://openalex.org/W2365709658","https://openalex.org/W1562588264","https://openalex.org/W1593731728","https://openalex.org/W2970126706","https://openalex.org/W2809061312","https://openalex.org/W2770198033"],"abstract_inverted_index":{"Let":[0],"us":[1],"consider":[2],"a":[3,9,16,18,47,64,70,79,93,110,126,139,149,156,168],"specific":[4],"acoustic":[5],"scene":[6,65],"appearing":[7],"in":[8,19,40,82,109],"continuous":[10],"audio":[11],"stream":[12],"recorded":[13],"while":[14],"making":[15,69],"trip":[17],"city.":[20],"In":[21],"this":[22,36,83],"work,":[23],"we":[24],"aim":[25],"at":[26,28],"detecting":[27],"the":[29,32,61,89,98,101,104,113,118,135,151],"earliest":[30],"opportunity":[31],"several":[33],"occurrences":[34],"of":[35,63,115,121],"scene.":[37],"The":[38,128],"objective":[39],"early":[41],"detection":[42],"is":[43,51,131],"then":[44],"to":[45,53,96,124,138,143],"build":[46],"decision":[48,71,90],"function":[49],"that":[50,85],"able":[52],"go":[54],"off":[55],"as":[56,58,100],"soon":[57],"possible":[59],"from":[60,155],"onset":[62],"occurrence.":[66],"This":[67,76],"implies":[68],"with":[72,92,103],"an":[73],"incomplete":[74],"information.":[75],"paper":[77],"proposes":[78],"novel":[80],"framework":[81,153],"area":[84],"i)":[86],"can":[87],"guarantee":[88],"made":[91],"partial":[94],"observation":[95],"be":[97],"same":[99],"one":[102],"full":[105],"observation;":[106],"ii)":[107],"incorporates":[108],"non-confusing":[111],"manner":[112],"lack":[114],"knowledge":[116],"about":[117],"minimal":[119],"amount":[120],"information":[122],"needed":[123],"make":[125],"decision.":[127],"proposed":[129],"detector":[130],"based":[132],"on":[133,167],"mapping":[134],"temporal":[136],"sequences":[137],"landmarking":[140],"space":[141],"thanks":[142],"appropriately":[144],"designed":[145],"similarity":[146],"functions.":[147],"As":[148],"by-product,":[150],"built":[152],"benefits":[154],"scalable":[157],"learning":[158],"problem.":[159],"A":[160],"preliminary":[161],"experimental":[162],"study":[163],"provides":[164],"compelling":[165],"results":[166],"soundscape":[169],"dataset.":[170]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
