{"id":"https://openalex.org/W4221030255","doi":"https://doi.org/10.1186/s13636-022-00239-6","title":"Improved capsule routing for weakly labeled sound event detection","display_name":"Improved capsule routing for weakly labeled sound event detection","publication_year":2022,"publication_date":"2022-03-07","ids":{"openalex":"https://openalex.org/W4221030255","doi":"https://doi.org/10.1186/s13636-022-00239-6"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-022-00239-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00239-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-022-00239-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-022-00239-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100453276","display_name":"Haitao Li","orcid":"https://orcid.org/0000-0001-5322-5375"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haitao Li","raw_affiliation_strings":["College of Mathematics and Physics, Qingdao University of Science and Technology, No.99 Songling Road, Qingdao, 266061, China"],"affiliations":[{"raw_affiliation_string":"College of Mathematics and Physics, Qingdao University of Science and Technology, No.99 Songling Road, Qingdao, 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066428368","display_name":"Shuguo Yang","orcid":"https://orcid.org/0000-0003-3363-0044"},"institutions":[{"id":"https://openalex.org/I143413998","display_name":"Qingdao University of Science and Technology","ror":"https://ror.org/041j8js14","country_code":"CN","type":"education","lineage":["https://openalex.org/I143413998"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuguo Yang","raw_affiliation_strings":["College of Mathematics and Physics, Qingdao University of Science and Technology, No.99 Songling Road, Qingdao, 266061, China"],"affiliations":[{"raw_affiliation_string":"College of Mathematics and Physics, Qingdao University of Science and Technology, No.99 Songling Road, Qingdao, 266061, China","institution_ids":["https://openalex.org/I143413998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100676721","display_name":"Wenwu Wang","orcid":"https://orcid.org/0000-0002-8393-5703"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wenwu Wang","raw_affiliation_strings":["Center for Vision Speech and Signal Processing, Department of Electrical and Electronic Engineering, Faculty of Engineering and Physical Sciences, University of Surrey, Guildford, GU2 7XH, UK"],"affiliations":[{"raw_affiliation_string":"Center for Vision Speech and Signal Processing, Department of Electrical and Electronic Engineering, Faculty of Engineering and Physical Sciences, University of Surrey, Guildford, GU2 7XH, UK","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100453276"],"corresponding_institution_ids":["https://openalex.org/I143413998"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.2977,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.47895926,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2022","issue":"1","first_page":null,"last_page":null},"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":0.9986000061035156,"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":0.9940000176429749,"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":0.7631193399429321},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7381325960159302},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.7277135848999023},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6063511967658997},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5395210981369019},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5237545967102051},{"id":"https://openalex.org/keywords/routing","display_name":"Routing (electronic design automation)","score":0.4444543421268463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41195595264434814},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3219057321548462},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21592125296592712},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09403038024902344},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07487636804580688}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631193399429321},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7381325960159302},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7277135848999023},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6063511967658997},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5395210981369019},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5237545967102051},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.4444543421268463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41195595264434814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3219057321548462},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21592125296592712},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09403038024902344},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07487636804580688},{"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":2,"locations":[{"id":"doi:10.1186/s13636-022-00239-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00239-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-022-00239-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3d2dc19999ea410d9173ab475702c2a5","is_oa":true,"landing_page_url":"https://doaj.org/article/3d2dc19999ea410d9173ab475702c2a5","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":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2022, Iss 1, Pp 1-11 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-022-00239-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-022-00239-6","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-022-00239-6","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221030255.pdf","grobid_xml":"https://content.openalex.org/works/W4221030255.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1972567154","https://openalex.org/W2010792435","https://openalex.org/W2070910811","https://openalex.org/W2083837083","https://openalex.org/W2120340098","https://openalex.org/W2131833400","https://openalex.org/W2164935924","https://openalex.org/W2194775991","https://openalex.org/W2341412280","https://openalex.org/W2408239454","https://openalex.org/W2591013610","https://openalex.org/W2592944988","https://openalex.org/W2593116425","https://openalex.org/W2607308654","https://openalex.org/W2618530766","https://openalex.org/W2793756232","https://openalex.org/W2799258971","https://openalex.org/W2809361304","https://openalex.org/W2883135409","https://openalex.org/W2903099953","https://openalex.org/W2962924597","https://openalex.org/W2963723765","https://openalex.org/W2998830408","https://openalex.org/W3012368684","https://openalex.org/W3101197104","https://openalex.org/W3165390575"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W2411659965","https://openalex.org/W4376166922","https://openalex.org/W2490526372"],"abstract_inverted_index":{"Abstract":[0],"Polyphonic":[1],"sound":[2,11,28,47,78,126],"event":[3,48,79,127],"detection":[4,128],"aims":[5],"to":[6,61,99,114],"detect":[7],"the":[8,66,89,96,109,117,132,145],"types":[9],"of":[10,91,144,159],"events":[12,29,58],"that":[13],"occur":[14,31],"in":[15,25,45,157],"given":[16],"audio":[17],"clips,":[18],"and":[19,22,59,95,149,162],"their":[20],"onset":[21],"offset":[23],"times,":[24],"which":[26],"multiple":[27],"may":[30],"simultaneously.":[32],"Deep":[33],"learning\u2013based":[34],"methods":[35],"such":[36],"as":[37],"convolutional":[38],"neural":[39],"networks":[40,87],"(CNN)":[41],"achieved":[42],"state-of-the-art":[43],"results":[44,156],"polyphonic":[46,77,125],"detection.":[49,80],"However,":[50,102],"two":[51,68],"open":[52],"challenges":[53],"still":[54],"remain:":[55],"overlap":[56],"between":[57],"prone":[60],"overfitting":[62],"problem.":[63],"To":[64],"solve":[65],"above":[67],"problems,":[69],"we":[70,120],"proposed":[71,137],"a":[72,122],"capsule":[73,86,134],"network-based":[74],"method":[75,138],"for":[76],"With":[81],"so-called":[82],"dynamic":[83,103],"routing":[84,104],",":[85],"have":[88],"advantage":[90],"handling":[92],"overlapping":[93],"objects":[94],"generalization":[97],"ability":[98],"reduce":[100],"overfitting.":[101],"also":[105],"greatly":[106],"slows":[107],"down":[108],"training":[110,118],"process.":[111],"In":[112],"order":[113],"speed":[115],"up":[116],"process,":[119],"propose":[121],"weakly":[123],"labeled":[124],"model":[129],"based":[130],"on":[131,141],"improved":[133],"routing.":[135],"Our":[136],"is":[139],"evaluated":[140],"task":[142],"4":[143],"DCASE":[146],"2017":[147],"challenge":[148],"compared":[150],"with":[151],"several":[152],"baselines,":[153],"demonstrating":[154],"competitive":[155],"terms":[158],"F":[160],"-score":[161],"computational":[163],"efficiency.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
