{"id":"https://openalex.org/W4205319688","doi":"https://doi.org/10.1109/ic-nidc54101.2021.9660525","title":"Audio Event Recognition by Multitask Learning of Audio Attribute Classification","display_name":"Audio Event Recognition by Multitask Learning of Audio Attribute Classification","publication_year":2021,"publication_date":"2021-11-17","ids":{"openalex":"https://openalex.org/W4205319688","doi":"https://doi.org/10.1109/ic-nidc54101.2021.9660525"},"language":"en","primary_location":{"id":"doi:10.1109/ic-nidc54101.2021.9660525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic-nidc54101.2021.9660525","pdf_url":null,"source":{"id":"https://openalex.org/S4363608589","display_name":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","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/A5100412489","display_name":"Gang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Liu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087964419","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0002-0811-6150"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102300833","display_name":"Xiaofeng Hong","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Hong","raw_affiliation_strings":["School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100412489"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.172,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.39623909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"324","last_page":"328"},"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":0.9908999800682068,"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":0.9506000280380249,"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":0.810206413269043},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6946713328361511},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5175482630729675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49648743867874146},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.48111170530319214},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4666239023208618},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44764444231987},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41871964931488037},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35429537296295166},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.22740566730499268},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.1803629994392395},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.1371731162071228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810206413269043},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6946713328361511},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5175482630729675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49648743867874146},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.48111170530319214},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4666239023208618},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44764444231987},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41871964931488037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35429537296295166},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.22740566730499268},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.1803629994392395},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.1371731162071228},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic-nidc54101.2021.9660525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic-nidc54101.2021.9660525","pdf_url":null,"source":{"id":"https://openalex.org/S4363608589","display_name":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 7th IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2015140204","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2770119437","https://openalex.org/W2913340405","https://openalex.org/W3015205011","https://openalex.org/W3015469592","https://openalex.org/W3015474227","https://openalex.org/W3015594652","https://openalex.org/W3049446265","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6746278845"],"related_works":["https://openalex.org/W2539919382","https://openalex.org/W22517275","https://openalex.org/W2042419400","https://openalex.org/W2122924390","https://openalex.org/W2064347532","https://openalex.org/W2289868279","https://openalex.org/W2064012922","https://openalex.org/W1620668332","https://openalex.org/W2033602688","https://openalex.org/W2156141367"],"abstract_inverted_index":{"Audio":[0],"Event":[1],"Recognize,":[2],"which":[3],"is":[4,15],"about":[5],"how":[6],"to":[7,48,56,100],"recognize":[8,57],"audio":[9,34,41,58,75,85,97,113],"events":[10,59],"in":[11],"the":[12,20,30,38,52,61,84,89,108,128,131,135],"environment.":[13],"It":[14],"receiving":[16],"increased":[17],"attention.":[18],"With":[19],"development":[21],"of":[22,33,74,96,130,137],"technologies":[23],"and":[24,110,119,134],"hardware,":[25],"deep":[26],"learning":[27,73],"has":[28],"become":[29],"primary":[31],"method":[32,69],"event":[35,42],"recognition.":[36],"In":[37,88],"convention":[39],"methods,":[40],"recognition":[43,120],"lacks":[44],"supervised":[45],"information.":[46,142],"Thus,":[47],"learn":[49],"from":[50],"using":[51],"multiple":[53],"information":[54,99],"fusion":[55],"like":[60],"human":[62],"auditory":[63],"system,":[64],"this":[65],"paper":[66,126],"proposes":[67],"a":[68],"based":[70],"on":[71],"multitask":[72],"attribute":[76,79,98,114,138],"classification.":[77],"The":[78],"labels":[80],"are":[81],"defined":[82],"by":[83],"production":[86],"process.":[87],"preliminary":[90],"experiments,":[91],"we":[92],"add":[93],"three":[94,132],"kinds":[95],"support":[101],"network":[102],"learning.":[103],"Experiments":[104],"show":[105],"that":[106],"for":[107],"ESC-50":[109],"Urbansound8K":[111],"datasets,":[112],"classification":[115],"achieves":[116],"higher":[117],"accuracy,":[118],"system":[121],"performance":[122],"improves":[123],"obviously.":[124],"This":[125],"verified":[127],"stability":[129],"attributes":[133],"effectiveness":[136],"tags":[139],"as":[140],"auxiliary":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}