{"id":"https://openalex.org/W4390571032","doi":"https://doi.org/10.1186/s13636-023-00323-5","title":"Deep semantic learning for acoustic scene classification","display_name":"Deep semantic learning for acoustic scene classification","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390571032","doi":"https://doi.org/10.1186/s13636-023-00323-5"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-023-00323-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00323-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00323-5","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/counter/pdf/10.1186/s13636-023-00323-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101472223","display_name":"Yunfei Shao","orcid":"https://orcid.org/0000-0003-2311-1670"},"institutions":[{"id":"https://openalex.org/I921716337","display_name":"Northeast Petroleum University","ror":"https://ror.org/03net5943","country_code":"CN","type":"education","lineage":["https://openalex.org/I921716337"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun-Fei Shao","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China","School of Mechanical Science and Engineering, Northeast Petroleum University, Daqing, 163318, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"School of Mechanical Science and Engineering, Northeast Petroleum University, Daqing, 163318, China","institution_ids":["https://openalex.org/I921716337"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033559982","display_name":"Xinxin Ma","orcid":"https://orcid.org/0000-0003-0763-7402"},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]},{"id":"https://openalex.org/I142415962","display_name":"Beijing Institute of Education","ror":"https://ror.org/03aefdx31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I142415962"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin-Xin Ma","raw_affiliation_strings":["School of Linguistic Sciences and Arts, Jiangsu Normal University, Xuzhou, 221009, China","TAL Education, Beijing, 100085, China"],"affiliations":[{"raw_affiliation_string":"School of Linguistic Sciences and Arts, Jiangsu Normal University, Xuzhou, 221009, China","institution_ids":["https://openalex.org/I118574674"]},{"raw_affiliation_string":"TAL Education, Beijing, 100085, China","institution_ids":["https://openalex.org/I142415962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002618865","display_name":"Yong Ma","orcid":"https://orcid.org/0000-0002-1116-0662"},"institutions":[{"id":"https://openalex.org/I118574674","display_name":"Jiangsu Normal University","ror":"https://ror.org/051hvcm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I118574674"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ma","raw_affiliation_strings":["School of Linguistic Sciences and Arts, Jiangsu Normal University, Xuzhou, 221009, China"],"affiliations":[{"raw_affiliation_string":"School of Linguistic Sciences and Arts, Jiangsu Normal University, Xuzhou, 221009, China","institution_ids":["https://openalex.org/I118574674"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101472223"],"corresponding_institution_ids":["https://openalex.org/I921716337","https://openalex.org/I99065089"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":3.9342,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94070937,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"2024","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":0.9983999729156494,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8216596841812134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7898651361465454},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7425158023834229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6961445808410645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5871890187263489},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5817280411720276},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5719545483589172},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.49969911575317383},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19236359000205994}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8216596841812134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7898651361465454},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7425158023834229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6961445808410645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5871890187263489},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5817280411720276},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5719545483589172},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.49969911575317383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19236359000205994},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-023-00323-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00323-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00323-5","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:c3f7f713611b47a488f10cfba307c862","is_oa":true,"landing_page_url":"https://doaj.org/article/c3f7f713611b47a488f10cfba307c862","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 2024, Iss 1, Pp 1-15 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-023-00323-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-023-00323-5","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/s13636-023-00323-5","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":[{"id":"https://openalex.org/G1014351457","display_name":null,"funder_award_id":"62276153","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3155635598","display_name":null,"funder_award_id":"2020AAA0104500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390571032.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2006546815","https://openalex.org/W2103235956","https://openalex.org/W2395611524","https://openalex.org/W2412782625","https://openalex.org/W2509065397","https://openalex.org/W2509990657","https://openalex.org/W2565639579","https://openalex.org/W2572730214","https://openalex.org/W2603777577","https://openalex.org/W2618530766","https://openalex.org/W2795280371","https://openalex.org/W2903099953","https://openalex.org/W2936774411","https://openalex.org/W2962711843","https://openalex.org/W2963881378","https://openalex.org/W2964309882","https://openalex.org/W2970737019","https://openalex.org/W2982677780","https://openalex.org/W2985214749","https://openalex.org/W3015530480","https://openalex.org/W3090619315","https://openalex.org/W3097327166","https://openalex.org/W3098357269","https://openalex.org/W3163527543","https://openalex.org/W3198860978","https://openalex.org/W4312892465","https://openalex.org/W6600007113","https://openalex.org/W6600238479","https://openalex.org/W6600281463","https://openalex.org/W6600424091","https://openalex.org/W6604344240","https://openalex.org/W6606863695","https://openalex.org/W6608374529","https://openalex.org/W6679338098"],"related_works":["https://openalex.org/W2953716828","https://openalex.org/W2904857019","https://openalex.org/W2944728705","https://openalex.org/W3011538607","https://openalex.org/W2904022177","https://openalex.org/W2591697403","https://openalex.org/W4321441197","https://openalex.org/W2359348847","https://openalex.org/W3125011624","https://openalex.org/W4294432981"],"abstract_inverted_index":{"Abstract":[0],"Acoustic":[1,131],"scene":[2,14,68],"classification":[3],"(ASC)":[4],"is":[5,20,33],"the":[6,10,36,60,88,94,99,126,150,178],"process":[7],"of":[8,101,120,130,147],"identifying":[9],"acoustic":[11],"environment":[12],"or":[13],"from":[15,35,93],"which":[16,32,54,85],"an":[17,27,81,117],"audio":[18,105],"signal":[19],"recorded.":[21],"In":[22,77],"this":[23],"work,":[24],"we":[25,79],"propose":[26,45,80],"encoder-decoder-based":[28],"approach":[29],"to":[30,63,74,97],"ASC,":[31],"borrowed":[34],"SegNet":[37],"in":[38,125],"image":[39,102],"semantic":[40,90],"segmentation":[41,91,95,103],"tasks.":[42],"We":[43],"also":[44],"a":[46,144],"novel":[47],"feature":[48],"normalization":[49,58],"method":[50,62],"named":[51],"Mixup":[52,61],"Normalization,":[53],"combines":[55],"channel-wise":[56],"instance":[57],"and":[59,69,128,133,162],"learn":[64],"useful":[65],"information":[66,72],"for":[67],"discard":[70],"specific":[71],"related":[73],"different":[75,123],"devices.":[76],"addition,":[78],"event":[82],"extraction":[83],"block,":[84],"can":[86],"extract":[87],"accurate":[89],"region":[92],"network,":[96],"imitate":[98],"effect":[100],"on":[104,122],"features.":[106],"With":[107],"four":[108],"data":[109,175],"augmentation":[110],"techniques,":[111],"our":[112],"best":[113],"single":[114],"system":[115],"achieved":[116],"average":[118],"accuracy":[119],"71.26%":[121],"devices":[124],"Detection":[127],"Classification":[129],"Scenes":[132],"Events":[134],"(DCASE)":[135],"2020":[136,152],"ASC":[137],"Task":[138,154],"1A":[139,155],"dataset.":[140,181],"The":[141],"result":[142],"indicates":[143],"minimum":[145],"margin":[146],"17%":[148],"against":[149],"DCASE":[151],"challenge":[153,180],"baseline":[156],"system.":[157],"It":[158],"has":[159],"lower":[160],"complexity":[161],"higher":[163],"performance":[164],"compared":[165],"with":[166],"other":[167,176],"state-of-the-art":[168],"CNN":[169],"models,":[170],"without":[171],"using":[172],"any":[173],"supplementary":[174],"than":[177],"official":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}