{"id":"https://openalex.org/W2981942095","doi":"https://doi.org/10.1145/3343031.3351086","title":"On Learning Disentangled Representation for Acoustic Event Detection","display_name":"On Learning Disentangled Representation for Acoustic Event Detection","publication_year":2019,"publication_date":"2019-10-15","ids":{"openalex":"https://openalex.org/W2981942095","doi":"https://doi.org/10.1145/3343031.3351086","mag":"2981942095"},"language":"en","primary_location":{"id":"doi:10.1145/3343031.3351086","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3343031.3351086","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3343031.3351086","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3343031.3351086","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008699574","display_name":"Lijian Gao","orcid":"https://orcid.org/0000-0002-6458-0660"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijian Gao","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068470372","display_name":"Qirong Mao","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qirong Mao","raw_affiliation_strings":["Jiangsu University, Zhenjiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu University, Zhenjiang, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112047383","display_name":"Ming Dong","orcid":"https://orcid.org/0000-0002-0616-4431"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Dong","raw_affiliation_strings":["Wayne State University, Detroit, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI, USA","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088934264","display_name":"Jing Yu","orcid":"https://orcid.org/0000-0001-8792-7201"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Jing","raw_affiliation_strings":["Wayne State University, Detroit, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI, USA","institution_ids":["https://openalex.org/I185443292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058494512","display_name":"Ratna Babu Chinnam","orcid":"https://orcid.org/0000-0003-0980-1544"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ratna Chinnam","raw_affiliation_strings":["Wayne State University, Detroit, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wayne State University, Detroit, MI, USA","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2006","last_page":"2014"},"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":0.9970999956130981,"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":0.9825999736785889,"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/discriminative-model","display_name":"Discriminative model","score":0.8538742065429688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.756859302520752},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.645784854888916},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6384631395339966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6012725830078125},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5497385859489441},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47938302159309387},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4578917920589447},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45642396807670593},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45553067326545715},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.42441806197166443},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4230876564979553},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37917497754096985}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8538742065429688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.756859302520752},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.645784854888916},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6384631395339966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6012725830078125},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5497385859489441},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47938302159309387},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4578917920589447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45642396807670593},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45553067326545715},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.42441806197166443},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4230876564979553},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37917497754096985},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3343031.3351086","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3343031.3351086","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3343031.3351086","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3343031.3351086","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3343031.3351086","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3343031.3351086","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G4915889223","display_name":null,"funder_award_id":"61672267 and U1836220","funder_id":"https://openalex.org/F4320327720","funder_display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China"},{"id":"https://openalex.org/G8904709242","display_name":"S&CC:  Promoting a Healthier Urban Community: Prioritization of Risk Factors for the Prevention and Treatment of Pediatric Obesity","funder_award_id":"1637312","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320327720","display_name":"Foundation for Innovative Research Groups of the National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981942095.pdf","grobid_xml":"https://content.openalex.org/works/W2981942095.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W80364729","https://openalex.org/W597395834","https://openalex.org/W1533561824","https://openalex.org/W1650531274","https://openalex.org/W1691728462","https://openalex.org/W1822987211","https://openalex.org/W1902027874","https://openalex.org/W1915328033","https://openalex.org/W1959608418","https://openalex.org/W1970578576","https://openalex.org/W2033875152","https://openalex.org/W2034215399","https://openalex.org/W2034424181","https://openalex.org/W2099471712","https://openalex.org/W2112353865","https://openalex.org/W2137561966","https://openalex.org/W2144499799","https://openalex.org/W2148154194","https://openalex.org/W2157617585","https://openalex.org/W2163922914","https://openalex.org/W2187089797","https://openalex.org/W2188956040","https://openalex.org/W2341412280","https://openalex.org/W2398456099","https://openalex.org/W2434741482","https://openalex.org/W2509990657","https://openalex.org/W2585105539","https://openalex.org/W2587284713","https://openalex.org/W2745616976","https://openalex.org/W2748560825","https://openalex.org/W2750162257","https://openalex.org/W2753738274","https://openalex.org/W2763761345","https://openalex.org/W2775505379","https://openalex.org/W2779801201","https://openalex.org/W2787284976","https://openalex.org/W2913668833","https://openalex.org/W2952161038","https://openalex.org/W2963829960","https://openalex.org/W4245923654","https://openalex.org/W4298103743"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Polyphonic":[0],"Acoustic":[1,111],"Event":[2],"Detection":[3,107],"(AED)":[4],"is":[5],"a":[6,48,56,82,129],"challenging":[7,125],"task":[8],"as":[9],"the":[10,15,21,25,62,100,106],"sounds":[11,35],"are":[12],"mixed":[13],"with":[14,31,128],"signals":[16],"from":[17,24,34],"different":[18],"events,":[19],"and":[20,108,113,134],"features":[22,32,86],"extracted":[23],"mixture":[26],"do":[27],"not":[28],"match":[29],"well":[30],"calculated":[33],"in":[36,61,77,105,124],"isolation,":[37],"leading":[38],"to":[39],"suboptimal":[40],"AED":[41,117,126],"performance.":[42],"In":[43],"this":[44],"paper,":[45],"we":[46],"propose":[47],"supervised":[49,79],"\u03b2-VAE":[50,80,120],"model":[51],"for":[52,87],"AED,":[53],"which":[54],"adds":[55],"novel":[57],"event-specific":[58],"disentangling":[59],"loss":[60],"objective":[63],"function":[64],"of":[65,84,110,132],"disentangled":[66],"learning.":[67],"By":[68],"incorporating":[69],"either":[70],"latent":[71,75],"factor":[72],"blocks":[73],"or":[74],"attention":[76],"disentangling,":[78],"learns":[81],"set":[83],"discriminative":[85],"each":[88],"event.":[89],"Extensive":[90],"experiments":[91],"on":[92],"benchmark":[93],"datasets":[94],"show":[95],"that":[96],"our":[97],"approach":[98],"outperforms":[99],"current":[101],"state-of-the-arts":[102],"(top-1":[103],"performers":[104],"Classification":[109],"Scenes":[112],"Events":[114],"(DCASE)":[115],"2017":[116],"challenge).":[118],"Supervised":[119],"has":[121],"great":[122],"success":[123],"tasks":[127],"large":[130],"variety":[131],"events":[133],"imbalanced":[135],"data.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}