{"id":"https://openalex.org/W4389296915","doi":"https://doi.org/10.1109/ieeeconf59510.2023.10335258","title":"Light-Weight Deep Learning Models for Acoustic Scene Classification Using Teacher-Student Scheme and Multiple Spectrograms","display_name":"Light-Weight Deep Learning Models for Acoustic Scene Classification Using Teacher-Student Scheme and Multiple Spectrograms","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4389296915","doi":"https://doi.org/10.1109/ieeeconf59510.2023.10335258"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf59510.2023.10335258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59510.2023.10335258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 4th International Symposium on the Internet of Sounds","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/A5075250567","display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Lam Pham","raw_affiliation_strings":["Austrian Institute of Technology (AIT),Austria","Austrian Institute of Technology (AIT), Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology (AIT),Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Austrian Institute of Technology (AIT), Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100705490","display_name":"Tin Nguyen","orcid":"https://orcid.org/0009-0008-5041-3627"},"institutions":[{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Tin Nguyen","raw_affiliation_strings":["Ho Chi Minh City University of Technology,Vietnam","Ho Chi Minh City University of Technology, Vietnam"],"affiliations":[{"raw_affiliation_string":"Ho Chi Minh City University of Technology,Vietnam","institution_ids":["https://openalex.org/I47265099"]},{"raw_affiliation_string":"Ho Chi Minh City University of Technology, Vietnam","institution_ids":["https://openalex.org/I47265099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056967532","display_name":"Phat Lam","orcid":"https://orcid.org/0009-0003-5105-5976"},"institutions":[{"id":"https://openalex.org/I47265099","display_name":"Ho Chi Minh City University of Technology","ror":"https://ror.org/04qva2324","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I47265099"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Phat Lam","raw_affiliation_strings":["Ho Chi Minh City University of Technology,Vietnam","Ho Chi Minh City University of Technology, Vietnam"],"affiliations":[{"raw_affiliation_string":"Ho Chi Minh City University of Technology,Vietnam","institution_ids":["https://openalex.org/I47265099"]},{"raw_affiliation_string":"Ho Chi Minh City University of Technology, Vietnam","institution_ids":["https://openalex.org/I47265099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102968151","display_name":"Dat Ngo","orcid":"https://orcid.org/0000-0003-4374-5056"},"institutions":[{"id":"https://openalex.org/I110002522","display_name":"University of Essex","ror":"https://ror.org/02nkf1q06","country_code":"GB","type":"education","lineage":["https://openalex.org/I110002522"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dat Ngo","raw_affiliation_strings":["University of Essex,UK","University of Essex, UK"],"affiliations":[{"raw_affiliation_string":"University of Essex,UK","institution_ids":["https://openalex.org/I110002522"]},{"raw_affiliation_string":"University of Essex, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010149819","display_name":"Anahid Jalali","orcid":"https://orcid.org/0000-0002-8889-0735"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Anahid Jalali","raw_affiliation_strings":["Austrian Institute of Technology (AIT),Austria","Austrian Institute of Technology (AIT), Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology (AIT),Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Austrian Institute of Technology (AIT), Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102746568","display_name":"Alexander Schindler","orcid":"https://orcid.org/0000-0001-6058-7753"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Alexander Schindler","raw_affiliation_strings":["Austrian Institute of Technology (AIT),Austria","Austrian Institute of Technology (AIT), Austria"],"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology (AIT),Austria","institution_ids":["https://openalex.org/I132118926"]},{"raw_affiliation_string":"Austrian Institute of Technology (AIT), Austria","institution_ids":["https://openalex.org/I132118926"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075250567"],"corresponding_institution_ids":["https://openalex.org/I132118926"],"apc_list":null,"apc_paid":null,"fwci":0.405,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.59912003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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":0.9994000196456909,"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":0.9936000108718872,"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/spectrogram","display_name":"Spectrogram","score":0.9519646167755127},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7025175094604492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6192556619644165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48203790187835693},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45230841636657715},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43552353978157043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32835423946380615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1621464192867279}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9519646167755127},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7025175094604492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6192556619644165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48203790187835693},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45230841636657715},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43552353978157043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32835423946380615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1621464192867279},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ieeeconf59510.2023.10335258","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf59510.2023.10335258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 4th International Symposium on the Internet of Sounds","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1965555277","https://openalex.org/W2095705004","https://openalex.org/W2191779130","https://openalex.org/W2768188490","https://openalex.org/W2963590343","https://openalex.org/W2982469053","https://openalex.org/W3032636897","https://openalex.org/W3114298706","https://openalex.org/W3161798961","https://openalex.org/W3198860978","https://openalex.org/W4283726207","https://openalex.org/W4283754361","https://openalex.org/W4295723153","https://openalex.org/W4311681683","https://openalex.org/W4318716360","https://openalex.org/W4323519173","https://openalex.org/W6637242042","https://openalex.org/W6674330103","https://openalex.org/W6745930336","https://openalex.org/W6752516136","https://openalex.org/W6839321029","https://openalex.org/W6846928454"],"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/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"In":[0,53,87],"this":[1],"paper,":[2],"we":[3,41,93,118],"present":[4],"a":[5,30,43,49,59,65,212,230],"light-weight":[6,38,98,213],"deep":[7,45],"learning":[8,46],"based":[9],"system":[10,28],"for":[11],"acoustic":[12],"scene":[13],"classification":[14],"(ASC),":[15],"which":[16,63,77,96,182,224],"is":[17,69,225],"armed":[18],"to":[19,160,227],"be":[20],"integrated":[21],"into":[22],"an":[23,120],"Internet":[24],"of":[25,32,82,122,169,215,233],"Sound":[26],"(IoS)":[27],"with":[29,48,105,140,165,198],"limitation":[31],"hardware":[33],"resource.":[34],"To":[35,112],"achieve":[36,161],"the":[37,54,73,75,79,83,88,103,110,115,127,162,166,172,178,184,207],"ASC":[39],"model,":[40],"develop":[42],"teacher-student":[44],"scheme":[47],"two-phase":[50],"training":[51,72],"strategy.":[52],"first":[55],"phase":[56,90],"(Phase":[57,91],"I),":[58],"Teacher":[60,128],"network":[61,99],"architecture,":[62],"shows":[64],"large":[66],"model":[67,214],"footprint,":[68],"proposed.":[70],"After":[71],"Teacher,":[74],"embeddings,":[76],"are":[78,85],"feature":[80],"map":[81],"teacher,":[84],"extracted.":[86],"second":[89],"II),":[92],"propose":[94],"Students":[95,104],"presents":[97,211],"architectures.":[100],"We":[101],"train":[102],"leveraging":[106],"embeddings":[107],"extracted":[108],"from":[109],"Teacher.":[111],"further":[113],"improve":[114,183],"accuracy":[116,167],"performance,":[117],"apply":[119,228],"ensemble":[121],"multiple":[123],"spectrograms":[124],"on":[125,134,171,177,206,229],"both":[126],"and":[129,175,189,204,210,220],"Students.":[130],"Our":[131],"experiments":[132],"conducted":[133],"DCASE":[135,185],"2023":[136],"Task":[137],"1":[138],"dataset":[139],"ten":[141],"target":[142,200],"classes":[143,201],"(\u2018Airport\u2019,":[144],"\u2018Bus\u2019,":[145],"\u2018Metro\u2019,":[146],"\u2018Metro":[147],"station\u2019,":[148],"\u2018Park\u2019,":[149],"\u2018Public":[150],"square\u2019,":[151],"\u2018Shopping":[152],"mall\u2019,":[153],"\u2018Street":[154,156],"pedestrian\u2019,":[155],"traffic\u2019,":[157],"\u2018Tram\u2019)":[158],"helps":[159],"best":[163,193],"Student":[164,194],"performance":[168],"57.4%":[170],"Development":[173,208],"set":[174,209],"55.6%":[176],"blind":[179],"Evaluation":[180],"set,":[181],"baseline":[186],"by":[187],"14.5%":[188],"10.8%,":[190],"respectively.":[191],"The":[192],"also":[195],"achieves":[196],"82.3%":[197],"three":[199],"(\u2018Indoor\u2019,":[202],"\u2018Outdoor\u2019,":[203],"\u2018Transportation\u2019)":[205],"88.7":[216],"KB":[217],"memory":[218],"occupation":[219],"29.27":[221],"M":[222],"MACs,":[223],"potential":[226],"wide":[231],"range":[232],"edge":[234],"devices.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}