{"id":"https://openalex.org/W2883135409","doi":"https://doi.org/10.23919/apsipa.2018.8659533","title":"A Capsule based Approach for Polyphonic Sound Event Detection","display_name":"A Capsule based Approach for Polyphonic Sound Event Detection","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2883135409","doi":"https://doi.org/10.23919/apsipa.2018.8659533","mag":"2883135409"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659533","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},"type":"article","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/A5101553467","display_name":"Yaming Liu","orcid":"https://orcid.org/0000-0002-3982-001X"},"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":"Yaming Liu","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077231313","display_name":"Jian Tang","orcid":"https://orcid.org/0000-0002-6819-4185"},"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":"Jian Tang","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"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":"Lirong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101553467"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.6514,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85056023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1853","last_page":"1857"},"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":0.9976999759674072,"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":0.9923999905586243,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8670035600662231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8115249276161194},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7205246090888977},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5965713262557983},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5905472040176392},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5791347622871399},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5510337352752686},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5487349033355713},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5255759358406067},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5163939595222473},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47233620285987854},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4607385993003845},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4549503028392792},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36178985238075256},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.06795215606689453}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8670035600662231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8115249276161194},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7205246090888977},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5965713262557983},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5905472040176392},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5791347622871399},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5510337352752686},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5487349033355713},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5255759358406067},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5163939595222473},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47233620285987854},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4607385993003845},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4549503028392792},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36178985238075256},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.06795215606689453},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659533","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659533","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W85726508","https://openalex.org/W1501987291","https://openalex.org/W1568645074","https://openalex.org/W1650531274","https://openalex.org/W1970578576","https://openalex.org/W2042081239","https://openalex.org/W2123843894","https://openalex.org/W2135131618","https://openalex.org/W2331166300","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2553581788","https://openalex.org/W2591013610","https://openalex.org/W2592944988","https://openalex.org/W2604490051","https://openalex.org/W2963703618","https://openalex.org/W2963723765","https://openalex.org/W2964121744","https://openalex.org/W6636898527","https://openalex.org/W6702387769","https://openalex.org/W6743446608"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"Polyphonic":[0],"sound":[1,18,74,121],"event":[2,75],"detection":[3],"(polyphonic":[4],"SED)":[5],"is":[6,63,129,140],"an":[7,164,169],"interesting":[8],"but":[9],"challenging":[10],"task":[11],"due":[12,80],"to":[13,50,71,81,112],"the":[14,52,82,89,144,153,160,175],"concurrence":[15],"of":[16,85,91,126,166,172,179],"multiple":[17],"events.":[19],"Recently,":[20],"SED":[21],"methods":[22],"based":[23,101,147],"on":[24,148,152],"convolutional":[25],"neural":[26,31],"networks":[27,32],"(CNN)":[28],"and":[29,168,181],"recurrent":[30],"(RNN)":[33],"have":[34],"shown":[35],"promising":[36],"performance.":[37],"Generally,":[38],"CNN":[39],"are":[40,48,110],"designed":[41,111],"for":[42,66,103,118,142],"local":[43,57],"feature":[44],"extraction":[45],"while":[46],"RNN":[47,149],"used":[49],"model":[51],"temporal":[53,124],"dependency":[54,125],"among":[55],"these":[56],"features.":[58,86],"Despite":[59],"their":[60,77],"success,":[61],"it":[62],"still":[64],"insufficient":[65],"existing":[67],"deep":[68],"learning":[69],"techniques":[70],"separate":[72],"individual":[73,120],"from":[76],"mixture,":[78],"largely":[79],"overlapping":[83],"characteristic":[84],"Motivated":[87],"by":[88,132],"success":[90],"Capsule":[92],"Networks":[93],"(CapsNet),":[94],"we":[95],"propose":[96],"a":[97,133,136],"more":[98],"suitable":[99],"capsule":[100,108],"approach":[102,162],"polyphonic":[104],"SED.":[105],"Specifically,":[106],"several":[107],"layers":[109],"effectively":[113],"select":[114],"representative":[115],"frequency":[116],"bands":[117],"each":[119],"event.":[122],"The":[123],"capsule's":[127],"outputs":[128],"then":[130],"modeled":[131],"RNN.":[134],"And":[135],"dynamic":[137],"threshold":[138],"method":[139,178],"proposed":[141,161],"making":[143],"final":[145],"decision":[146],"outputs.":[150],"Experiments":[151],"TUT-SED":[154],"Synthetic":[155],"2016":[156],"dataset":[157],"show":[158],"that":[159],"obtains":[163],"F1-score":[165],"68.8%":[167],"error":[170],"rate":[171],"0.45,":[173],"outperforming":[174],"previous":[176],"state-of-the-art":[177],"66.4%":[180],"0.48,":[182],"respectively.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}