{"id":"https://openalex.org/W2787600432","doi":"https://doi.org/10.1109/apsipa.2017.8282241","title":"Convolutional neural network with multi-task learning scheme for acoustic scene classification","display_name":"Convolutional neural network with multi-task learning scheme for acoustic scene classification","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787600432","doi":"https://doi.org/10.1109/apsipa.2017.8282241","mag":"2787600432"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5050008407","display_name":"Tin Lay Nwe","orcid":"https://orcid.org/0000-0003-1111-580X"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Tin Lay Nwe","raw_affiliation_strings":["Institute for Infocomm Research, I2R, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, I2R, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110125670","display_name":"Tran Huy Dat","orcid":null},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tran Huy Dat","raw_affiliation_strings":["Institute for Infocomm Research, I2R, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, I2R, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Institute for Infocomm Research, I2R, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, I2R, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050008407"],"corresponding_institution_ids":["https://openalex.org/I3005327000"],"apc_list":null,"apc_paid":null,"fwci":2.7739,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.91913337,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1347","last_page":"1350"},"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":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7975713014602661},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.669353187084198},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.6323145031929016},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6144708395004272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6143792867660522},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5963291525840759},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.580185055732727},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4385245442390442},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43405479192733765},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39010798931121826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3546094298362732}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7975713014602661},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.669353187084198},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.6323145031929016},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6144708395004272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6143792867660522},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5963291525840759},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.580185055732727},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4385245442390442},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43405479192733765},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39010798931121826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3546094298362732},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1650531274","https://openalex.org/W1850325679","https://openalex.org/W2119662931","https://openalex.org/W2130640900","https://openalex.org/W2295072214","https://openalex.org/W2464644320","https://openalex.org/W2612919868","https://openalex.org/W2913340405","https://openalex.org/W2951213053","https://openalex.org/W2952505042","https://openalex.org/W2963173190","https://openalex.org/W6648737282","https://openalex.org/W6713960836","https://openalex.org/W6719414543"],"related_works":["https://openalex.org/W2948333011","https://openalex.org/W4386619269","https://openalex.org/W4392903819","https://openalex.org/W1942758450","https://openalex.org/W2994972936","https://openalex.org/W2922338626","https://openalex.org/W4303645333","https://openalex.org/W4221067497","https://openalex.org/W4312745891","https://openalex.org/W2108010283"],"abstract_inverted_index":{"Deep":[0],"Neural":[1,82],"Network":[2,83],"(DNN)":[3],"with":[4,28],"Multi-Task":[5],"Learning":[6],"(MTL)":[7],"methods":[8,39],"have":[9,40],"recently":[10],"demonstrated":[11],"significant":[12],"performance":[13,67],"gains":[14],"on":[15],"a":[16],"number":[17],"of":[18,91],"classification,":[19],"detection,":[20],"recognition":[21],"tasks":[22],"compared":[23],"to":[24,61,64,84,88,104],"conventional":[25],"DNN.":[26],"DNN":[27,60],"MTL":[29,38,58,78],"framework":[30,79],"involves":[31],"cross-task":[32,47],"and":[33],"within-task":[34],"knowledge":[35,48,54],"sharing":[36,49,55],"layers.":[37,50],"benefit":[41],"for":[42,68],"regularization":[43],"effect":[44],"from":[45],"the":[46,66],"And,":[51],"within-":[52],"task":[53],"layers":[56],"allow":[57],"based":[59],"learn":[62,85],"information":[63,86],"optimize":[65],"individual":[69],"task.":[70],"We":[71,93],"formulate":[72],"our":[73],"acoustic":[74,107],"scene":[75,108],"classification":[76],"in":[77],"using":[80,96],"Convolutional":[81],"specific":[87],"different":[89],"types":[90],"environment.":[92],"conduct":[94],"experiments":[95],"DCASE2016":[97],"dataset.":[98],"Proposed":[99],"approach":[100],"achieves":[101],"83.8%":[102],"accuracy":[103],"classify":[105],"15":[106],"classes.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}