{"id":"https://openalex.org/W2939084498","doi":"https://doi.org/10.21437/interspeech.2019-2231","title":"Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events","display_name":"Acoustic Scene Classification by Implicitly Identifying Distinct Sound Events","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2939084498","doi":"https://doi.org/10.21437/interspeech.2019-2231","mag":"2939084498"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2231","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.05204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057908066","display_name":"Hongwei Song","orcid":"https://orcid.org/0000-0003-1928-8182"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Song","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087019132","display_name":"Shiwen Deng","orcid":"https://orcid.org/0000-0001-8964-3165"},"institutions":[{"id":"https://openalex.org/I134052481","display_name":"Harbin Normal University","ror":"https://ror.org/0270y6950","country_code":"CN","type":"education","lineage":["https://openalex.org/I134052481"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiwen Deng","raw_affiliation_strings":["School of Mathematical Science, Harbin Normal University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematical Science, Harbin Normal University, China","institution_ids":["https://openalex.org/I134052481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001133136","display_name":"Zhihao Du","orcid":"https://orcid.org/0000-0003-3509-9322"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Du","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3860","last_page":"3864"},"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":0.9952999949455261,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.982200026512146,"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":0.7553600072860718},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5816702246665955},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5678673386573792},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5452954173088074},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5452320575714111},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.467818945646286},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4514932334423065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41204512119293213},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.23106157779693604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7553600072860718},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5816702246665955},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5678673386573792},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5452954173088074},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5452320575714111},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.467818945646286},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4514932334423065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41204512119293213},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.23106157779693604},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2231","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2231","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.05204","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.05204","pdf_url":"https://arxiv.org/pdf/1904.05204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.05204","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.05204","pdf_url":"https://arxiv.org/pdf/1904.05204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311190","display_name":"Safari Club International Foundation","ror":"https://ror.org/0341wf912"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1496437685","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W2010792435","https://openalex.org/W2011972438","https://openalex.org/W2048174296","https://openalex.org/W2095147901","https://openalex.org/W2103235956","https://openalex.org/W2114777924","https://openalex.org/W2126109423","https://openalex.org/W2137343183","https://openalex.org/W2354870669","https://openalex.org/W2565911560","https://openalex.org/W2566935005","https://openalex.org/W2605021547","https://openalex.org/W2619623002","https://openalex.org/W2629823280","https://openalex.org/W2676925568","https://openalex.org/W2799258971","https://openalex.org/W2883935097","https://openalex.org/W2888784333","https://openalex.org/W2888839755","https://openalex.org/W2889241388","https://openalex.org/W2889309940","https://openalex.org/W2889356375","https://openalex.org/W2889527961","https://openalex.org/W2897435617","https://openalex.org/W2899771611","https://openalex.org/W2913795158","https://openalex.org/W2963610932","https://openalex.org/W2963840672","https://openalex.org/W2964048371","https://openalex.org/W2964121744","https://openalex.org/W4289465850","https://openalex.org/W4295723153"],"related_works":["https://openalex.org/W2909726438","https://openalex.org/W2067046791","https://openalex.org/W2909888262","https://openalex.org/W2012531322","https://openalex.org/W2402761219","https://openalex.org/W2025747832","https://openalex.org/W2785900585","https://openalex.org/W3020957235","https://openalex.org/W2056769785","https://openalex.org/W2353730437"],"abstract_inverted_index":{"In":[0],"this":[1,188],"paper,":[2],"we":[3,62,112],"propose":[4,97,113],"a":[5,66,78,93,98],"new":[6],"strategy":[7,189],"for":[8,59,89,183],"acoustic":[9,16,170],"scene":[10],"classification":[11,163],"(ASC)":[12],",":[13],"namely":[14],"recognizing":[15,169],"scenes":[17,171],"through":[18],"identifying":[19,173],"distinct":[20,56,106,174],"sound":[21,52,57,90,109,128,175],"events.":[22,53],"This":[23,165],"differs":[24],"from":[25],"existing":[26],"strategies,":[27],"which":[28,103],"focus":[29],"on":[30,135],"characterizing":[31],"global":[32],"acoustical":[33],"distributions":[34],"of":[35,41,51,126,140,162],"audio":[36,43,73],"or":[37],"the":[38,49,120,127,136,141,152,181],"temporal":[39],"evolution":[40],"short-term":[42],"features,":[44],"without":[45],"analysis":[46],"down":[47],"to":[48],"level":[50],"To":[54],"identify":[55],"events":[58,91,129,176],"each":[60,72],"scene,":[61],"formulate":[63],"ASC":[64],"in":[65,160],"multi-instance":[67],"learning":[68],"(MIL)":[69],"framework,":[70],"where":[71],"recording":[74],"is":[75,177],"mapped":[76],"into":[77],"bag-of-instances":[79],"representation.":[80],"Here,":[81],"instances":[82,107],"can":[83],"be":[84],"seen":[85],"as":[86],"high-level":[87],"representations":[88],"inside":[92],"scene.":[94],"We":[95],"also":[96],"MIL":[99],"neural":[100],"networks":[101],"model,":[102],"implicitly":[104],"identifies":[105],"(i.e.,":[108],"events).":[110],"Furthermore,":[111],"two":[114],"specially":[115],"designed":[116],"modules":[117],"that":[118,168,186],"model":[119,149],"multi-temporal":[121],"scale":[122],"and":[123,146,179],"multi-modal":[124],"natures":[125],"respectively.":[130],"The":[131],"experiments":[132],"were":[133],"conducted":[134],"official":[137,153],"development":[138],"set":[139],"DCASE2018":[142],"Task1":[143],"Subtask":[144],"B,":[145],"our":[147],"best-performing":[148],"improves":[150],"over":[151],"baseline":[154],"by":[155,172],"9.4%":[156],"(68.3%":[157],"vs":[158],"58.9%)":[159],"terms":[161],"accuracy.":[164],"study":[166],"indicates":[167],"effective":[178],"paves":[180],"way":[182],"future":[184],"studies":[185],"combine":[187],"with":[190],"previous":[191],"ones.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}