{"id":"https://openalex.org/W4388117483","doi":"https://doi.org/10.23919/eusipco58844.2023.10289983","title":"Device-Robust Acoustic Scene Classification via Impulse Response Augmentation","display_name":"Device-Robust Acoustic Scene Classification via Impulse Response Augmentation","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117483","doi":"https://doi.org/10.23919/eusipco58844.2023.10289983"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289983","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","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/A5091952748","display_name":"Tobias Morocutti","orcid":null},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Tobias Morocutti","raw_affiliation_strings":["Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103009549","display_name":"Florian Schmid","orcid":"https://orcid.org/0009-0007-4988-6067"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Florian Schmid","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University,Linz,Austria","Institute of Computational Perception, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026220503","display_name":"Khaled Koutini","orcid":"https://orcid.org/0000-0002-9193-732X"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Khaled Koutini","raw_affiliation_strings":["Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003768123","display_name":"Gerhard Widmer","orcid":"https://orcid.org/0000-0003-3531-1282"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Institute of Computational Perception, Johannes Kepler University,Linz,Austria","LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","Institute of Computational Perception, Johannes Kepler University, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"Institute of Computational Perception, Johannes Kepler University, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091952748"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":2.8399,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.92001001,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"176","last_page":"180"},"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":0.9995999932289124,"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":0.9955999851226807,"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":0.7586066722869873},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7357556819915771},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.598567008972168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5504778027534485},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4615696668624878},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4270167946815491},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4249238967895508},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4178202450275421},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3799367845058441},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37806326150894165},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.22501140832901},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.16726088523864746},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12301084399223328}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7586066722869873},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7357556819915771},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.598567008972168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5504778027534485},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4615696668624878},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4270167946815491},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4249238967895508},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4178202450275421},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3799367845058441},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37806326150894165},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.22501140832901},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.16726088523864746},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12301084399223328},{"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:10.23919/eusipco58844.2023.10289983","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco58844.2023.10289983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2311973309","https://openalex.org/W2593116425","https://openalex.org/W2621009285","https://openalex.org/W2696967604","https://openalex.org/W2765407302","https://openalex.org/W2901243971","https://openalex.org/W2908510526","https://openalex.org/W2962909949","https://openalex.org/W2970112944","https://openalex.org/W2982469053","https://openalex.org/W2987999870","https://openalex.org/W3016967467","https://openalex.org/W3039883906","https://openalex.org/W3165587897","https://openalex.org/W3165945839","https://openalex.org/W3205475937","https://openalex.org/W4282044900","https://openalex.org/W4283693214","https://openalex.org/W4283726207","https://openalex.org/W4298091485","https://openalex.org/W4312943213","https://openalex.org/W6688325169","https://openalex.org/W6738830366","https://openalex.org/W6745136726","https://openalex.org/W6757817989","https://openalex.org/W6759401939","https://openalex.org/W6779341498"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W1975359510","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3110605476","https://openalex.org/W3043119899","https://openalex.org/W2766269877"],"abstract_inverted_index":{"The":[0,20,138],"ability":[1],"to":[2,4,36,62,87,109,148],"generalize":[3],"a":[5,12,71,78,165],"wide":[6],"range":[7],"of":[8,22,25,81,114,122,128],"recording":[9,115],"devices":[10,89,173],"is":[11,45,60],"crucial":[13],"performance":[14,54,168],"factor":[15],"for":[16],"audio":[17,33,74,97],"classification":[18],"models.":[19],"characteristics":[21],"different":[23,82],"types":[24],"microphones":[26,83],"introduce":[27],"distributional":[28],"shifts":[29],"in":[30,99,144],"the":[31,52,100,112,120,126,149],"digitized":[32],"signals":[34,63,75,98,170],"due":[35],"their":[37],"varying":[38],"frequency":[39],"responses.":[40],"If":[41],"this":[42,93],"domain":[43],"shift":[44],"not":[46],"taken":[47],"into":[48],"account":[49],"during":[50,175],"training,":[51],"model's":[53],"could":[55],"degrade":[56],"severely":[57],"when":[58],"it":[59],"applied":[61],"recorded":[64,76,171],"by":[65,172],"unseen":[66,88,174],"devices.":[67,116],"In":[68],"particular,":[69],"training":[70,101],"model":[72],"on":[73,125,169],"with":[77,103],"small":[79],"number":[80],"can":[84],"make":[85],"generalization":[86],"difficult.":[90],"To":[91],"tackle":[92],"problem,":[94],"we":[95,154],"convolve":[96],"set":[102],"pre-recorded":[104],"device":[105],"impulse":[106],"responses":[107],"(DIRs)":[108],"artificially":[110],"increase":[111],"diversity":[113],"We":[117],"systematically":[118],"study":[119],"effect":[121],"DIR":[123,142,158],"augmentation":[124,143,159],"task":[127],"Acoustic":[129],"Scene":[130],"Classification":[131],"using":[132],"CNNs":[133],"and":[134,160],"Audio":[135],"Spectrogram":[136],"Transformers.":[137],"results":[139],"show":[140,156],"that":[141,157],"isolation":[145],"performs":[146],"similarly":[147],"state-of-the-art":[150,167],"method":[151],"Freq-MixStyle.":[152],"However,":[153],"also":[155],"Freq-MixStyle":[161],"are":[162],"complementary,":[163],"achieving":[164],"new":[166],"training.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}