{"id":"https://openalex.org/W4388183682","doi":"https://doi.org/10.23919/eusipco58844.2023.10289774","title":"On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers","display_name":"On Frequency-Wise Normalizations for Better Recording Device Generalization in Audio Spectrogram Transformers","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388183682","doi":"https://doi.org/10.23919/eusipco58844.2023.10289774"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289774","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289774","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":"conference-paper","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/A5084326954","display_name":"Paul Primus","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142635","display_name":"PATH To Reading","ror":"https://ror.org/0482xmh13","country_code":"US","type":"other","lineage":["https://openalex.org/I4210142635"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Primus","raw_affiliation_strings":["Institute of Computational Perception (CP-JKU)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception (CP-JKU)","institution_ids":["https://openalex.org/I4210142635"]}]},{"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"]},{"id":"https://openalex.org/I4210142635","display_name":"PATH To Reading","ror":"https://ror.org/0482xmh13","country_code":"US","type":"other","lineage":["https://openalex.org/I4210142635"]}],"countries":["AT","US"],"is_corresponding":false,"raw_author_name":"Gerhard Widmer","raw_affiliation_strings":["Institute of Computational Perception (CP-JKU)","LIT Artificial Intelligence Lab, Johannes Kepler University, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception (CP-JKU)","institution_ids":["https://openalex.org/I4210142635"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"395"},"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":0.9997000098228455,"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":0.9943000078201294,"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/spectrogram","display_name":"Spectrogram","score":0.9360183477401733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7440025806427002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5721644163131714},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5518372058868408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49202868342399597},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4773262143135071},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4351414442062378},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38621869683265686},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13107511401176453},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09289154410362244}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9360183477401733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7440025806427002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5721644163131714},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5518372058868408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49202868342399597},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4773262143135071},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4351414442062378},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38621869683265686},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13107511401176453},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09289154410362244},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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":1,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289774","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289774","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2052666245","https://openalex.org/W2147800946","https://openalex.org/W2502312327","https://openalex.org/W2593116425","https://openalex.org/W2765407302","https://openalex.org/W2803808038","https://openalex.org/W2884366600","https://openalex.org/W2936774411","https://openalex.org/W3094502228","https://openalex.org/W3166601111","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W4205689591","https://openalex.org/W4221150524","https://openalex.org/W4224980507","https://openalex.org/W4283693214","https://openalex.org/W4295723153","https://openalex.org/W4312048190","https://openalex.org/W4375869340","https://openalex.org/W6631190155","https://openalex.org/W6724804524","https://openalex.org/W6745136726","https://openalex.org/W6751546485","https://openalex.org/W6752516136","https://openalex.org/W6753385908","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6792861227","https://openalex.org/W6809947431","https://openalex.org/W6810510949","https://openalex.org/W6810841414","https://openalex.org/W6848208918"],"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":{"Varying":[0],"conditions":[1],"between":[2],"the":[3,24,53,77,96,112,117,126,141,145,157],"data":[4],"seen":[5],"at":[6,9],"training":[7],"and":[8,43],"application":[10],"time":[11],"remain":[12],"a":[13,150],"major":[14],"challenge":[15],"for":[16,68,153],"machine":[17],"learning.":[18],"We":[19,102,148],"study":[20],"this":[21,61,84,131],"problem":[22],"in":[23,47,81,95,111,140],"context":[25],"of":[26,41,60,100],"Acoustic":[27],"Scene":[28],"Classification":[29],"(ASC)":[30],"with":[31],"mismatching":[32],"recording":[33,54,90,105,137,162],"devices.":[34],"Previous":[35],"works":[36],"successfully":[37],"employed":[38],"frequency-wise":[39,66],"normalization":[40,67],"inputs":[42],"hidden":[44,97],"layer":[45,98],"activations":[46,99],"convolutional":[48],"neural":[49],"networks":[50],"to":[51,64,168],"reduce":[52],"device":[55,91,106,138],"discrepancy.":[56],"The":[57],"main":[58],"objective":[59],"work":[62],"was":[63],"adopt":[65],"Audio":[69],"Spectrogram":[70],"Transformers":[71],"(ASTs),":[72],"which":[73],"have":[74],"recently":[75],"become":[76],"dominant":[78],"model":[79],"architecture":[80],"ASC.":[82],"To":[83],"end,":[85],"we":[86,133],"first":[87,118],"investigate":[88],"how":[89],"characteristics":[92,139],"are":[93],"encoded":[94,110],"ASTs.":[101],"find":[103],"that":[104,135,155],"information":[107],"is":[108,122,144],"initially":[109],"frequency":[113],"dimension;":[114],"however,":[115],"after":[116],"self-attention":[119],"block,":[120],"it":[121],"largely":[123],"transformed":[124],"into":[125],"token":[127],"dimension.":[128],"Based":[129],"on":[130,160,164],"observation,":[132],"conjecture":[134],"suppressing":[136],"input":[142],"spectrogram":[143],"most":[146],"effective.":[147],"propose":[149],"frequency-centering":[151],"operation":[152],"spectrograms":[154],"improves":[156],"ASC":[158],"performance":[159],"unseen":[161],"devices":[163],"average":[165],"by":[166],"up":[167],"18.2":[169],"percentage":[170],"points.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}