{"id":"https://openalex.org/W3005501015","doi":"https://doi.org/10.1145/3377713.3377720","title":"A Multi-task Learning Approach Based on Convolutional Neural Network for Acoustic Scene Classification","display_name":"A Multi-task Learning Approach Based on Convolutional Neural Network for Acoustic Scene Classification","publication_year":2019,"publication_date":"2019-12-20","ids":{"openalex":"https://openalex.org/W3005501015","doi":"https://doi.org/10.1145/3377713.3377720","mag":"3005501015"},"language":"en","primary_location":{"id":"doi:10.1145/3377713.3377720","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377713.3377720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence","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/A5021635896","display_name":"Kuilong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kuilong Xu","raw_affiliation_strings":["School of Computer Science and Technology, Anhui University, Hefei, China, Shenzhen Raisound Technologies, Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Anhui University, Hefei, China, Shenzhen Raisound Technologies, Co., Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110518840","display_name":"Shilei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shilei Huang","raw_affiliation_strings":["Shenzhen Raisound Technologies, Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Raisound Technologies, Co., Ltd, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014070150","display_name":"Gang Cheng","orcid":"https://orcid.org/0000-0002-0462-3411"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gang Cheng","raw_affiliation_strings":["Shenzhen Raisound Technologies, Co., Ltd, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Shenzhen Raisound Technologies, Co., Ltd, Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050439131","display_name":"Xiao Song","orcid":"https://orcid.org/0000-0003-4279-426X"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Song","raw_affiliation_strings":["Peking University Shenzhen Institute, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University Shenzhen Institute, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021635896"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.1659,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.4864981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"27"},"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":0.998199999332428,"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":0.9937999844551086,"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":0.7558835744857788},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6140622496604919},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.594825029373169},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5879562497138977},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5743814706802368},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5737600326538086},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.5590476989746094},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5021851062774658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4816928803920746},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.46069571375846863},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4374038577079773},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42216798663139343},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39713647961616516}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7558835744857788},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6140622496604919},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.594825029373169},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5879562497138977},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5743814706802368},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5737600326538086},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.5590476989746094},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5021851062774658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4816928803920746},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.46069571375846863},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4374038577079773},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42216798663139343},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39713647961616516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3377713.3377720","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3377713.3377720","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W1522301498","https://openalex.org/W1896424170","https://openalex.org/W2085457662","https://openalex.org/W2086384421","https://openalex.org/W2294059674","https://openalex.org/W2295072214","https://openalex.org/W2464644320","https://openalex.org/W2612919868","https://openalex.org/W2651986237","https://openalex.org/W2807929272","https://openalex.org/W2949117887","https://openalex.org/W6631782140","https://openalex.org/W6759193872"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W4283754361"],"abstract_inverted_index":{"Acoustic":[0],"Scene":[1],"Classification":[2],"(ASC)":[3],"aim":[4],"to":[5,89,93],"recognize":[6],"an":[7,86],"acoustic":[8,15,35,43,160],"scene":[9,16,44,161],"in":[10,38,100,104,130],"audio":[11,147],"signal":[12],"records.":[13],"The":[14,134],"is":[17,136],"a":[18,47,74],"mixture":[19],"of":[20,34,55,96,106,109,124,146,180],"background":[21],"sounds":[22],"and":[23,27,66,72,173],"various":[24],"sound":[25,28,56,98,111],"events,":[26],"events":[29],"often":[30],"determine":[31],"the":[32,52,63,94,97,101,107,110,125,131,138,158,175,183],"type":[33],"scene.":[36],"However,":[37],"many":[39],"research":[40],"methods":[41],"for":[42],"classification,":[45],"only":[46],"few":[48],"people":[49],"have":[50],"noticed":[51],"important":[53],"information":[54,95],"events.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,117],"combine":[62],"ASC":[64,186],"task":[65,88],"Sound":[67],"Event":[68],"Detection":[69],"(SED)":[70],"task,":[71],"propose":[73],"new":[75],"CNN":[76,166],"approach":[77,167],"with":[78,113,168],"multi-task":[79],"Learning":[80],"(MTL),":[81],"which":[82],"uses":[83],"SED":[84],"as":[85],"auxiliary":[87],"pay":[90],"more":[91],"attention":[92],"event":[99,112],"model.":[102],"Besides,":[103],"view":[105],"characteristic":[108],"high-energy":[114,143],"time-frequency":[115,144],"components,":[116],"use":[118],"Global":[119],"Max":[120],"Pooling":[121],"(GMP)":[122],"instead":[123],"Fully":[126],"Connected":[127],"layer":[128],"(FC)":[129],"traditional":[132],"CNN.":[133],"advantage":[135],"that":[137],"model":[139],"focused":[140],"on":[141,157],"distinct":[142],"components":[145],"signals":[148],"(sound":[149],"event).":[150],"Finally,":[151],"extensive":[152],"experiments":[153],"are":[154],"carried":[155],"out":[156],"TUT":[159],"2017":[162,185],"dataset.":[163],"Our":[164],"proposed":[165],"MTL":[169],"shows":[170],"better":[171],"generalization,":[172],"improves":[174],"Unweighted":[176],"Average":[177],"Recall":[178],"(UAR)":[179],"5.2%":[181],"over":[182],"DCASE":[184],"baseline":[187],"system.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}