{"id":"https://openalex.org/W2058326762","doi":"https://doi.org/10.1109/wiamis.2013.6616160","title":"A generic classification system for multi-channel audio indexing: Application to speech and music detection","display_name":"A generic classification system for multi-channel audio indexing: Application to speech and music detection","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2058326762","doi":"https://doi.org/10.1109/wiamis.2013.6616160","mag":"2058326762"},"language":"en","primary_location":{"id":"doi:10.1109/wiamis.2013.6616160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiamis.2013.6616160","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/A5003116633","display_name":"Elie-Laurent Benaroya","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/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/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/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Elie-Laurent Benaroya","raw_affiliation_strings":["STMS IRCAM-CNRS Sound Analysis, Synthesis Team, UPMC, Paris, France","STMS IRCAM, Sound Anal./Synthesis Team, UPMC, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STMS IRCAM-CNRS Sound Analysis, Synthesis Team, UPMC, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"STMS IRCAM, Sound Anal./Synthesis Team, UPMC, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"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/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/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/I4389425508","display_name":"Sciences et Technologies de la Musique et du Son","ror":"https://ror.org/025xvn046","country_code":null,"type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I2802818602","https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4210102700","https://openalex.org/I4389425508"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["STMS IRCAM-CNRS Sound Analysis, Synthesis Team, UPMC, Paris, France","STMS IRCAM, Sound Anal./Synthesis Team, UPMC, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STMS IRCAM-CNRS Sound Analysis, Synthesis Team, UPMC, Paris, France","institution_ids":["https://openalex.org/I35345632","https://openalex.org/I39804081","https://openalex.org/I4389425508","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"STMS IRCAM, Sound Anal./Synthesis Team, UPMC, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4389425508"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.12627021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9937000274658203,"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":0.8421374559402466},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.7533085942268372},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6881831884384155},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6001865267753601},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5722351670265198},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5543175339698792},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.49099281430244446},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.48812589049339294},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.42783159017562866},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41810885071754456},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.41805967688560486},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.38286834955215454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3693701922893524},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3269036114215851}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8421374559402466},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.7533085942268372},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6881831884384155},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6001865267753601},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5722351670265198},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5543175339698792},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.49099281430244446},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.48812589049339294},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.42783159017562866},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41810885071754456},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.41805967688560486},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.38286834955215454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693701922893524},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3269036114215851},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wiamis.2013.6616160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wiamis.2013.6616160","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:HAL:hal-01106842v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01106842","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE WIAMIS, Jul 2013, Paris, France","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1618905105","https://openalex.org/W1989085630","https://openalex.org/W2001014535","https://openalex.org/W2124864596","https://openalex.org/W2128838222","https://openalex.org/W2158275940","https://openalex.org/W2331166300","https://openalex.org/W2621560750","https://openalex.org/W6636501900","https://openalex.org/W6702387769","https://openalex.org/W6738928127"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1984921740","https://openalex.org/W1911859126","https://openalex.org/W642007152","https://openalex.org/W2064012922","https://openalex.org/W1620668332","https://openalex.org/W2033602688","https://openalex.org/W2156141367"],"abstract_inverted_index":{"There":[0],"is":[1,26,39,71],"a":[2,14,27,55,74,113],"rise":[3],"in":[4,120],"the":[5,81,88,106,121],"number":[6],"3D":[7,19,37,84],"audio-visual":[8],"productions":[9],"and":[10,46,63,76,99],"archives":[11],"that":[12],"creates":[13],"need":[15],"for":[16,58,96,101],"indexation":[17],"of":[18,83,115],"contents.":[20],"Event":[21],"detection":[22,62,78],"using":[23],"audio":[24,38,45,60,82],"modality":[25],"difficult":[28],"task.":[29],"The":[30],"standard":[31,107],"way":[32],"to":[33,40,43,105],"do":[34],"classification":[35,89],"on":[36,48,73,80,91],"first":[41],"down-mix":[42],"mono":[44],"classify":[47],"that.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"describe":[54],"generic":[56],"classifier":[57],"multi-channel":[59],"event":[61],"propose":[64],"several":[65,116],"information":[66,117],"fusion":[67,118],"strategies.":[68],"Our":[69],"system":[70],"evaluated":[72],"speech":[75,97],"music":[77,102],"task":[79],"movies.":[85],"We":[86,110],"improve":[87],"performances":[90],"our":[92],"database":[93],"by":[94],"1.5%":[95],"detection,":[98,103],"8%":[100],"compared":[104],"downmixing":[108],"method.":[109],"also":[111],"provide":[112],"comparison":[114],"methods":[119],"experiments.":[122]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}