{"id":"https://openalex.org/W2512383693","doi":"https://doi.org/10.21437/interspeech.2016-392","title":"Robust Sound Event Detection in Continuous Audio Environments","display_name":"Robust Sound Event Detection in Continuous Audio Environments","publication_year":2016,"publication_date":"2016-08-29","ids":{"openalex":"https://openalex.org/W2512383693","doi":"https://doi.org/10.21437/interspeech.2016-392","mag":"2512383693"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2016-392","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},"type":"conference-paper","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/A5035330165","display_name":"Haomin Zhang","orcid":"https://orcid.org/0000-0002-9439-1625"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haomin Zhang","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing The University of Science and Technology of China, Hefei, PRC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing The University of Science and Technology of China, Hefei, PRC","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]},{"id":"https://openalex.org/I167056439","display_name":"Medway School of Pharmacy","ror":"https://ror.org/00fa9v295","country_code":"GB","type":"education","lineage":["https://openalex.org/I167056439"]},{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing The University of Science and Technology of China, Hefei, PRC","School of Computing@Medway, The University of Kent, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing The University of Science and Technology of China, Hefei, PRC","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"School of Computing@Medway, The University of Kent, UK","institution_ids":["https://openalex.org/I167056439","https://openalex.org/I20581793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory of Speech and Language Information Processing The University of Science and Technology of China, Hefei, PRC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory of Speech and Language Information Processing The University of Science and Technology of China, Hefei, PRC","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100381758"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.6596,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.63840334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2977","last_page":"2981"},"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":0.9998000264167786,"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":0.9904000163078308,"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":0.8050950765609741},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7938894629478455},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6524864435195923},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5208109617233276},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5149236917495728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5047825574874878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4920000731945038},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48827266693115234},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4643773138523102},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44288545846939087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38964587450027466},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20273807644844055},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07709825038909912}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8050950765609741},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7938894629478455},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6524864435195923},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5208109617233276},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5149236917495728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5047825574874878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4920000731945038},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48827266693115234},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4643773138523102},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44288545846939087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38964587450027466},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20273807644844055},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07709825038909912},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2016-392","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2016-392","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2016","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:56309","is_oa":false,"landing_page_url":"https://doi.org/10.21437/Interspeech.2016-392>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Book section"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1530136128","https://openalex.org/W1538131130","https://openalex.org/W1970578576","https://openalex.org/W2005122913","https://openalex.org/W2090431713","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2155273149","https://openalex.org/W2187281534","https://openalex.org/W2283724112"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"Sound":[0],"event":[1,40,70],"detection":[2],"in":[3,17,30,48],"real":[4],"world":[5],"environments":[6],"has":[7],"attracted":[8],"significant":[9],"research":[10],"interest":[11],"recently":[12],"because":[13],"of":[14,51,72,83,103,137],"it's":[15],"applications":[16],"popular":[18],"fields":[19],"such":[20],"as":[21,27,29],"machine":[22],"hearing":[23],"and":[24,79,122],"automated":[25],"surveillance,":[26],"well":[28],"sound":[31,39,46,69,93],"scene":[32],"understanding.":[33],"This":[34,75],"paper":[35,76],"considers":[36],"continuous":[37],"robust":[38],"detection,":[41],"which":[42],"means":[43],"multiple":[44],"overlapped":[45],"events":[47],"different":[49],"types":[50],"interfering":[52],"noise.":[53],"First,":[54],"a":[55,97,104,112],"standard":[56],"evaluation":[57],"task":[58],"is":[59,116,125,134],"outlined":[60],"based":[61],"upon":[62],"existing":[63],"testing":[64],"data":[65],"sets":[66],"for":[67],"the":[68,81,109],"classification":[71],"isolated":[73],"sounds.":[74],"then":[77],"proposes":[78],"evaluates":[80],"use":[82,102],"spectrogram":[84],"image":[85],"features":[86],"employing":[87],"an":[88],"energy":[89],"detector":[90],"to":[91,118,127],"segment":[92],"events,":[94],"before":[95],"developing":[96],"novel":[98],"segmentation":[99],"method":[100,133],"making":[101],"Bayesian":[105],"inference":[106],"criteria.":[107],"At":[108],"back":[110],"end,":[111],"convolutional":[113],"neural":[114],"network":[115],"used":[117],"classify":[119],"detected":[120],"regions,":[121],"this":[123],"combination":[124],"compared":[126,142],"several":[128],"alternative":[129],"approaches.":[130],"The":[131],"proposed":[132],"shown":[135],"capable":[136],"achieving":[138],"very":[139],"good":[140],"performance":[141],"with":[143],"current":[144],"state-of-the-art":[145],"techniques.":[146]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
