{"id":"https://openalex.org/W2786629437","doi":"https://doi.org/10.1109/ijcnn.2018.8489542","title":"Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features","display_name":"Multichannel Sound Event Detection Using 3D Convolutional Neural Networks for Learning Inter-channel Features","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2786629437","doi":"https://doi.org/10.1109/ijcnn.2018.8489542","mag":"2786629437"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1801.09522","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054490307","display_name":"Sharath Adavanne","orcid":"https://orcid.org/0000-0002-5001-6911"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Sharath Adavanne","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010846139","display_name":"Archontis Politis","orcid":"https://orcid.org/0000-0002-0595-2356"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Archontis Politis","raw_affiliation_strings":["Department of Signal Processing and Acoustics, Aalto University, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Signal Processing and Acoustics, Aalto University, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology, Finland"],"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology, Finland","institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054490307"],"corresponding_institution_ids":["https://openalex.org/I166825849","https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":0.499,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.61591042,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9991999864578247,"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":0.9916999936103821,"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/ambisonics","display_name":"Ambisonics","score":0.9371888041496277},{"id":"https://openalex.org/keywords/binaural-recording","display_name":"Binaural recording","score":0.8620234131813049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7933918237686157},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6994354724884033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6109180450439453},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5822098851203918},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4619837701320648},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.454620897769928},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4468940198421478},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44273531436920166},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4157823324203491},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4117692708969116},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.1606968343257904},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1179332435131073},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08610028028488159}],"concepts":[{"id":"https://openalex.org/C47726159","wikidata":"https://www.wikidata.org/wiki/Q457547","display_name":"Ambisonics","level":3,"score":0.9371888041496277},{"id":"https://openalex.org/C201247586","wikidata":"https://www.wikidata.org/wiki/Q5612967","display_name":"Binaural recording","level":2,"score":0.8620234131813049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933918237686157},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6994354724884033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6109180450439453},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5822098851203918},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4619837701320648},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.454620897769928},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4468940198421478},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44273531436920166},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4157823324203491},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117692708969116},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.1606968343257904},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1179332435131073},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08610028028488159},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":5,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489542","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1801.09522","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1801.09522","pdf_url":"https://arxiv.org/pdf/1801.09522","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"},{"id":"mag:2786629437","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1801.09522.pdf","pdf_url":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/35235","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/b8ef8b3b-74b4-4623-9231-30fdc6266b79","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":null,"raw_type":"acceptedVersion"},{"id":"doi:10.48550/arxiv.1801.09522","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1801.09522","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1801.09522","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1801.09522","pdf_url":"https://arxiv.org/pdf/1801.09522","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1484823238","https://openalex.org/W1501987291","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1529830495","https://openalex.org/W1533561824","https://openalex.org/W1587644769","https://openalex.org/W1650531274","https://openalex.org/W1822987211","https://openalex.org/W1844944916","https://openalex.org/W2046317813","https://openalex.org/W2095705004","https://openalex.org/W2097998348","https://openalex.org/W2130640900","https://openalex.org/W2163344649","https://openalex.org/W2171680721","https://openalex.org/W2292996718","https://openalex.org/W2341393370","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2594627932","https://openalex.org/W2622742434","https://openalex.org/W2746554716","https://openalex.org/W2748560825","https://openalex.org/W2763761345","https://openalex.org/W2899771611","https://openalex.org/W2949117887","https://openalex.org/W2963099423","https://openalex.org/W2963158330","https://openalex.org/W2964342924","https://openalex.org/W6631190155","https://openalex.org/W6631847504","https://openalex.org/W6632323398","https://openalex.org/W6638667902","https://openalex.org/W6674330103","https://openalex.org/W6696777030","https://openalex.org/W6739564277","https://openalex.org/W6744964450","https://openalex.org/W6747331233","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W2801612492","https://openalex.org/W2767299893","https://openalex.org/W3213096249","https://openalex.org/W2966587287","https://openalex.org/W2891644395","https://openalex.org/W3015395742","https://openalex.org/W2783358616","https://openalex.org/W2957061055","https://openalex.org/W3186318461","https://openalex.org/W3185499768","https://openalex.org/W3167318608","https://openalex.org/W3015894695","https://openalex.org/W3095737053","https://openalex.org/W2919883917","https://openalex.org/W3119066640","https://openalex.org/W3145387657","https://openalex.org/W2764338498","https://openalex.org/W2291372403","https://openalex.org/W3016257794","https://openalex.org/W2890489755"],"abstract_inverted_index":{"In":[0,50],"this":[1,71],"paper,":[2],"we":[3,161],"propose":[4],"a":[5,14,74,141],"stacked":[6],"convolutional":[7,16],"and":[8,79,112,136,173],"recurrent":[9],"neural":[10,17],"network":[11,18,37],"(CRNN)":[12],"with":[13,60,109,140,182],"3D":[15,33],"(CNN)":[19],"in":[20,156,179],"the":[21,25,36,41,46,54,84,89,96,110,116,163],"first":[22],"layer":[23],"for":[24],"multichannel":[26,48,57,101,133,153],"sound":[27,65,130,177,185],"event":[28],"detection":[29],"(SED)":[30],"task.":[31],"The":[32,123,147],"CNN":[34],"enables":[35],"to":[38,52,94,127],"simultaneously":[39],"learn":[40],"inter-and":[42],"intra-channel":[43],"features":[44,134],"from":[45,132],"input":[47],"audio.":[49,102],"order":[51],"evaluate":[53],"proposed":[55,90,124],"method,":[56],"audio":[58,155,160],"datasets":[59],"different":[61],"number":[62,143],"of":[63,70,86,98,115,144,158],"overlapping":[64,129,184],"sources":[66],"are":[67,92],"synthesized.":[68],"Each":[69],"dataset":[72],"has":[73],"four-channel":[75],"first-order":[76],"Ambisonic,":[77],"binaural,":[78],"single-channel":[80,113,159],"versions,":[81],"on":[82,151],"which":[83],"performance":[85],"SED":[87,99,139],"using":[88,100,152],"method":[91,125],"compared":[93],"study":[95,105],"potential":[97],"A":[103],"similar":[104],"is":[106],"also":[107],"done":[108],"binaural":[111],"versions":[114],"real-life":[117],"recording":[118],"TUT-SED":[119],"2017":[120],"development":[121],"dataset.":[122],"learns":[126],"recognize":[128,174],"events":[131,178],"faster":[135],"performs":[137],"better":[138],"fewer":[142],"training":[145],"epochs.":[146],"results":[148],"show":[149],"that":[150],"Ambisonic":[154],"place":[157],"improve":[162],"overall":[164,168],"F-score":[165],"by":[166,171],"7.5%,":[167],"error":[169],"rate":[170],"10%":[172],"15.6%":[175],"more":[176],"time":[180],"frames":[181],"four":[183],"sources.":[186]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}