{"id":"https://openalex.org/W4213209776","doi":"https://doi.org/10.3390/sym14020366","title":"Adaptive Memory-Controlled Self-Attention for Polyphonic Sound Event Detection","display_name":"Adaptive Memory-Controlled Self-Attention for Polyphonic Sound Event Detection","publication_year":2022,"publication_date":"2022-02-12","ids":{"openalex":"https://openalex.org/W4213209776","doi":"https://doi.org/10.3390/sym14020366"},"language":"en","primary_location":{"id":"doi:10.3390/sym14020366","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14020366","pdf_url":"https://www.mdpi.com/2073-8994/14/2/366/pdf?version=1645077022","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/14/2/366/pdf?version=1645077022","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100375197","display_name":"Mei Wang","orcid":"https://orcid.org/0000-0002-2771-3970"},"institutions":[{"id":"https://openalex.org/I38706770","display_name":"Guilin University of Technology","ror":"https://ror.org/03z391397","country_code":"CN","type":"education","lineage":["https://openalex.org/I38706770"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wang","raw_affiliation_strings":["School of Information Science & Engineering, Guilin University of Technology, Guilin 541006, China"],"affiliations":[{"raw_affiliation_string":"School of Information Science & Engineering, Guilin University of Technology, Guilin 541006, China","institution_ids":["https://openalex.org/I38706770"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033082988","display_name":"Yu Yao","orcid":"https://orcid.org/0000-0002-0089-9568"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Yao","raw_affiliation_strings":["Ministry of Education Key Laboratory of Cognitive Radio and Information Processing, Guilin 541006, China","School of Information and Communication, Guilin University of Electronic Technology, Guilin 541006, China"],"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory of Cognitive Radio and Information Processing, Guilin 541006, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Information and Communication, Guilin University of Electronic Technology, Guilin 541006, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101587813","display_name":"Hongbin Qiu","orcid":"https://orcid.org/0000-0001-9530-0775"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongbin Qiu","raw_affiliation_strings":["Ministry of Education Key Laboratory of Cognitive Radio and Information Processing, Guilin 541006, China","School of Information and Communication, Guilin University of Electronic Technology, Guilin 541006, China"],"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory of Cognitive Radio and Information Processing, Guilin 541006, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Information and Communication, Guilin University of Electronic Technology, Guilin 541006, China","institution_ids":["https://openalex.org/I5343935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101683712","display_name":"Xiyu Song","orcid":"https://orcid.org/0000-0003-4053-4528"},"institutions":[{"id":"https://openalex.org/I5343935","display_name":"Guilin University of Electronic Technology","ror":"https://ror.org/05arjae42","country_code":"CN","type":"education","lineage":["https://openalex.org/I5343935"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiyu Song","raw_affiliation_strings":["Ministry of Education Key Laboratory of Cognitive Radio and Information Processing, Guilin 541006, China","School of Information and Communication, Guilin University of Electronic Technology, Guilin 541006, China"],"affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory of Cognitive Radio and Information Processing, Guilin 541006, China","institution_ids":["https://openalex.org/I1327237609"]},{"raw_affiliation_string":"School of Information and Communication, Guilin University of Electronic Technology, Guilin 541006, China","institution_ids":["https://openalex.org/I5343935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101683712"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I5343935"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.8932,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.70852506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"14","issue":"2","first_page":"366","last_page":"366"},"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":0.9977999925613403,"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":0.991599977016449,"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":0.7545939087867737},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5969595909118652},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5104941129684448},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.505959689617157},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4999852180480957},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4782780110836029},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4732433259487152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4668387174606323},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4155041575431824},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41284289956092834},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08331301808357239}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7545939087867737},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5969595909118652},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5104941129684448},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.505959689617157},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4999852180480957},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4782780110836029},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4732433259487152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4668387174606323},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4155041575431824},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41284289956092834},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08331301808357239},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"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/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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":3,"locations":[{"id":"doi:10.3390/sym14020366","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14020366","pdf_url":"https://www.mdpi.com/2073-8994/14/2/366/pdf?version=1645077022","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f36a385ea68b4120b50868edc0cdc72d","is_oa":true,"landing_page_url":"https://doaj.org/article/f36a385ea68b4120b50868edc0cdc72d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 14, Iss 2, p 366 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/14/2/366/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/sym14020366","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym14020366","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym14020366","pdf_url":"https://www.mdpi.com/2073-8994/14/2/366/pdf?version=1645077022","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G398061555","display_name":null,"funder_award_id":"Nos.61771151","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4213209776.pdf","grobid_xml":"https://content.openalex.org/works/W4213209776.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W821549425","https://openalex.org/W1844944916","https://openalex.org/W2133564696","https://openalex.org/W2354870669","https://openalex.org/W2408239454","https://openalex.org/W2529483679","https://openalex.org/W2618269622","https://openalex.org/W2654517624","https://openalex.org/W2759976799","https://openalex.org/W2775505379","https://openalex.org/W2799258971","https://openalex.org/W2809183397","https://openalex.org/W2884011836","https://openalex.org/W2892009249","https://openalex.org/W2911109671","https://openalex.org/W2938440247","https://openalex.org/W2942551338","https://openalex.org/W2959539607","https://openalex.org/W2962910554","https://openalex.org/W2963022469","https://openalex.org/W2963099423","https://openalex.org/W2963128891","https://openalex.org/W2963610932","https://openalex.org/W2963723765","https://openalex.org/W2964891022","https://openalex.org/W2973152780","https://openalex.org/W2987999870","https://openalex.org/W2988928590","https://openalex.org/W2997981428","https://openalex.org/W3015190346","https://openalex.org/W3017521796","https://openalex.org/W3097059024","https://openalex.org/W3098454764","https://openalex.org/W3103314642","https://openalex.org/W3123416659","https://openalex.org/W3124216180","https://openalex.org/W3125993195","https://openalex.org/W3162400960","https://openalex.org/W3162999565","https://openalex.org/W3203468141","https://openalex.org/W6752846909","https://openalex.org/W6763355497","https://openalex.org/W6765705499"],"related_works":["https://openalex.org/W3093895509","https://openalex.org/W3163481960","https://openalex.org/W2323394100","https://openalex.org/W280704926","https://openalex.org/W2476068070","https://openalex.org/W4323971310","https://openalex.org/W2893372175","https://openalex.org/W4283526844","https://openalex.org/W2787003449","https://openalex.org/W4205490113"],"abstract_inverted_index":{"Polyphonic":[0],"sound":[1,17,26,208,232],"event":[2,18,209,233],"detection":[3],"(SED)":[4],"is":[5,67,204,244],"the":[6,10,14,76,89,129,150,170,180,186,200,242],"task":[7],"of":[8,16,73,133,241],"detecting":[9],"time":[11,92],"stamps":[12],"and":[13,31,131,136,149,156],"class":[15],"that":[19,75,179,199,227],"occurred":[20],"during":[21],"a":[22,59,63,101,191],"recording.":[23],"Real":[24,144],"life":[25],"events":[27],"overlap":[28],"in":[29,94,128,143,158,220,228],"recordings,":[30],"their":[32],"durations":[33],"vary":[34],"dramatically,":[35],"making":[36],"them":[37],"even":[38],"harder":[39],"to":[40,52,69,82,86,117,206,252],"recognize.":[41],"In":[42,163,211,223],"this":[43],"paper,":[44],"we":[45,80,99,109,215,225],"propose":[46,81,100],"Convolutional":[47],"Recurrent":[48],"Neural":[49],"Networks":[50],"(CRNNs)":[51],"extract":[53],"hidden":[54],"state":[55],"feature":[56],"representations;":[57],"then,":[58],"self-attention":[60,85,106],"mechanism":[61,203],"using":[62],"symmetric":[64],"score":[65],"function":[66],"introduced":[68],"memorize":[70],"long-range":[71],"dependencies":[72],"features":[74],"CRNNs":[77],"extract.":[78],"Furthermore,":[79],"use":[83],"memory-controlled":[84,105,183],"explicitly":[87],"compute":[88],"relations":[90],"between":[91],"steps":[93],"audio":[95,120],"representation":[96],"embedding.":[97],"Then,":[98],"strategy":[102],"for":[103],"adaptive":[104,182],"mechanisms.":[107],"Moreover,":[108],"applied":[110,251],"semi-supervised":[111,231],"learning,":[112],"namely,":[113],"mean":[114],"teacher\u2013student":[115],"methods,":[116],"exploit":[118],"unlabeled":[119],"data.":[121],"The":[122],"proposed":[123,181,201],"methods":[124],"all":[125],"performed":[126],"well":[127],"Detection":[130,142,155],"Classification":[132],"Acoustic":[134],"Scenes":[135],"Events":[137],"(DCASE)":[138],"2017":[139,165],"Sound":[140,153],"Event":[141,154],"Life":[145],"Audio":[146],"(task3)":[147],"test":[148],"DCASE":[151,164,212],"2021":[152,213],"Separation":[157],"Domestic":[159],"Environments":[160],"(task4)":[161],"test.":[162],"task3,":[166],"our":[167],"model":[168,184],"surpassed":[169],"challenge\u2019s":[171],"winning":[172],"system\u2019s":[173],"F1-score":[174],"by":[175],"6.8%.":[176],"We":[177],"show":[178],"reached":[185],"same":[187],"performance":[188],"level":[189],"as":[190],"fixed":[192],"attention":[193,202,237],"width":[194],"model.":[195],"Experimental":[196],"results":[197],"indicate":[198],"able":[205],"improve":[207],"detection.":[210],"task4,":[214],"investigated":[216],"various":[217],"pooling":[218],"strategies":[219],"two":[221],"scenarios.":[222],"addition,":[224],"found":[226],"weakly":[229],"labeled":[230],"detection,":[234],"building":[235],"an":[236],"layer":[238],"on":[239],"top":[240],"CRNN":[243],"needless":[245],"repetition.":[246],"This":[247],"conclusion":[248],"could":[249],"be":[250],"other":[253],"multi-instance":[254],"learning":[255],"problems.":[256]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
