{"id":"https://openalex.org/W4311681683","doi":"https://doi.org/10.1145/3551626.3564962","title":"Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices","display_name":"Wider or Deeper Neural Network Architecture for Acoustic Scene Classification with Mismatched Recording Devices","publication_year":2022,"publication_date":"2022-12-07","ids":{"openalex":"https://openalex.org/W4311681683","doi":"https://doi.org/10.1145/3551626.3564962"},"language":"en","primary_location":{"id":"doi:10.1145/3551626.3564962","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551626.3564962","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551626.3564962","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3551626.3564962","any_repository_has_fulltext":null},"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":false,"raw_author_name":"Lam Pham","raw_affiliation_strings":["Austrian Institute of Technology, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology, Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031178621","display_name":"Khoa Tran","orcid":"https://orcid.org/0000-0001-7376-5061"},"institutions":[{"id":"https://openalex.org/I3130697706","display_name":"University of Science and Technology - The University of Da Nang","ror":"https://ror.org/001ydh096","country_code":"VN","type":"education","lineage":["https://openalex.org/I3130697706"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Khoa Tran","raw_affiliation_strings":["Da Nang University, Viet Nam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Da Nang University, Viet Nam","institution_ids":["https://openalex.org/I3130697706"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Essex, UK","institution_ids":["https://openalex.org/I110002522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082199118","display_name":"Hieu Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I109689652","display_name":"FPT University","ror":"https://ror.org/03esj4g97","country_code":"VN","type":"education","lineage":["https://openalex.org/I109689652"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Hieu Tang","raw_affiliation_strings":["FPT University, Viet Nam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FPT University, Viet Nam","institution_ids":["https://openalex.org/I109689652"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109230625","display_name":"Son Phan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Son Phan","raw_affiliation_strings":["Amanotes Company, Viet Nam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amanotes Company, Viet Nam","institution_ids":[]}]},{"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, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Austrian Institute of Technology, Austria","institution_ids":["https://openalex.org/I132118926"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8919,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7308045,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9994999766349792,"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":0.9955000281333923,"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":0.8145177364349365},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6811901926994324},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6806379556655884},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5984861254692078},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5606389045715332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5324823260307312},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4540456533432007},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.44454312324523926},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.4389113187789917},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.42557191848754883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3827836215496063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36605268716812134},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1369139552116394},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.08270111680030823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8145177364349365},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6811901926994324},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6806379556655884},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5984861254692078},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5606389045715332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5324823260307312},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4540456533432007},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.44454312324523926},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.4389113187789917},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.42557191848754883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3827836215496063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36605268716812134},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1369139552116394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.08270111680030823},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3551626.3564962","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551626.3564962","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551626.3564962","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3551626.3564962","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3551626.3564962","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3551626.3564962","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 4th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.44999998807907104}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311681683.pdf","grobid_xml":"https://content.openalex.org/works/W4311681683.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2052666245","https://openalex.org/W2095147901","https://openalex.org/W2191779130","https://openalex.org/W2596356468","https://openalex.org/W2607662938","https://openalex.org/W2886388258","https://openalex.org/W2900595477","https://openalex.org/W2939084498","https://openalex.org/W2962711843","https://openalex.org/W2963590343","https://openalex.org/W2972470942","https://openalex.org/W2972560948","https://openalex.org/W3114298706","https://openalex.org/W3196576635"],"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/W3137434606","https://openalex.org/W3168739063","https://openalex.org/W4372263373"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,62,92],"present":[4],"a":[5,34,103],"robust":[6],"and":[7,71,102,120],"low":[8,60,104],"complexity":[9,105],"model":[10,31,54,72,96],"for":[11,122],"Acoustic":[12],"Scene":[13],"Classification":[14],"(ASC),":[15],"the":[16,20,44,53,59,75,84,94,117],"task":[17],"of":[18,22,46,66,68,100,106],"identifying":[19],"scene":[21],"an":[23,29,98],"audio":[24],"recording.":[25],"We":[26],"firstly":[27],"construct":[28],"ASC":[30,77],"in":[32],"which":[33,112],"novel":[35],"inception-residual-based":[36],"network":[37],"architecture":[38],"is":[39,113],"proposed":[40,76],"to":[41,74,116],"deal":[42],"with":[43],"issue":[45],"mismatched":[47],"recording":[48],"devices.":[49,127],"To":[50],"further":[51],"improve":[52],"performance":[55],"but":[56],"still":[57],"satisfy":[58],"footprint,":[61],"apply":[63],"two":[64],"techniques":[65],"ensemble":[67],"multiple":[69],"spectrograms":[70],"compression":[73],"model.":[78],"By":[79],"conducting":[80],"extensive":[81],"experiments":[82],"on":[83,125],"benchmark":[85],"DCASE":[86],"2020":[87],"Task":[88],"1A":[89],"Development":[90],"dataset,":[91],"achieve":[93],"best":[95],"performing":[97],"accuracy":[99],"71.3%":[101],"0.5":[107],"Million":[108],"(M)":[109],"trainable":[110],"parameters,":[111],"very":[114],"competitive":[115],"state-of-the-art":[118],"systems":[119],"potential":[121],"real-life":[123],"applications":[124],"edge":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
