{"id":"https://openalex.org/W3157247433","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533654","title":"ESResNe(X)t-fbsp: Learning Robust Time-Frequency Transformation of Audio","display_name":"ESResNe(X)t-fbsp: Learning Robust Time-Frequency Transformation of Audio","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3157247433","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533654","mag":"3157247433"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.11587","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051399221","display_name":"Andrey Guzhov","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andrey Guzhov","raw_affiliation_strings":["DFKI GmbH"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029509133","display_name":"Federico Raue","orcid":"https://orcid.org/0000-0002-8604-6207"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Federico Raue","raw_affiliation_strings":["DFKI GmbH","German Research Centre for Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"German Research Centre for Artificial Intelligence","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019899855","display_name":"J.J. van Hees","orcid":"https://orcid.org/0000-0002-0084-8998"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jorn Hees","raw_affiliation_strings":["DFKI GmbH"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH","institution_ids":["https://openalex.org/I33256026"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101904182","display_name":"Andreas Dengel","orcid":"https://orcid.org/0000-0002-6100-8255"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Dengel","raw_affiliation_strings":["DFKI GmbH"],"affiliations":[{"raw_affiliation_string":"DFKI GmbH","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5051399221"],"corresponding_institution_ids":["https://openalex.org/I33256026"],"apc_list":null,"apc_paid":null,"fwci":0.3078,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.51913265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"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":0.9959999918937683,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7326570153236389},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7105094194412231},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.6763556599617004},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6066750288009644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5145701766014099},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48622360825538635},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4792892336845398},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.47497838735580444},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.47087371349334717},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.45500823855400085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4205324351787567},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.4150099754333496},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14045721292495728},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14033913612365723},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.12126177549362183},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.10986965894699097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326570153236389},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7105094194412231},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.6763556599617004},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6066750288009644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5145701766014099},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48622360825538635},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4792892336845398},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.47497838735580444},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.47087371349334717},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.45500823855400085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4205324351787567},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.4150099754333496},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14045721292495728},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14033913612365723},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.12126177549362183},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.10986965894699097},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.11587","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11587","pdf_url":"https://arxiv.org/pdf/2104.11587","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2104.11587","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.11587","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3157247433","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.11587","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11587","pdf_url":"https://arxiv.org/pdf/2104.11587","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3157247433.pdf","grobid_xml":"https://content.openalex.org/works/W3157247433.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W396690109","https://openalex.org/W1522301498","https://openalex.org/W1605494325","https://openalex.org/W1766888123","https://openalex.org/W1972567154","https://openalex.org/W2020997493","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2086161653","https://openalex.org/W2103869314","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2509065397","https://openalex.org/W2531409750","https://openalex.org/W2549139847","https://openalex.org/W2593116425","https://openalex.org/W2593451766","https://openalex.org/W2745357708","https://openalex.org/W2766087987","https://openalex.org/W2888469011","https://openalex.org/W2914312680","https://openalex.org/W2962785008","https://openalex.org/W2963838685","https://openalex.org/W2964328535","https://openalex.org/W2972247414","https://openalex.org/W3034886385","https://openalex.org/W3045062880","https://openalex.org/W3091905774","https://openalex.org/W3093652365","https://openalex.org/W3098357269","https://openalex.org/W3158553615","https://openalex.org/W4232336823","https://openalex.org/W6613520308","https://openalex.org/W6631190155","https://openalex.org/W6775888111","https://openalex.org/W6779503413","https://openalex.org/W6783596713"],"related_works":["https://openalex.org/W1026195623","https://openalex.org/W2963512705","https://openalex.org/W2892296933","https://openalex.org/W3108701224","https://openalex.org/W3034771037","https://openalex.org/W3116250684","https://openalex.org/W3011356572","https://openalex.org/W3132755470","https://openalex.org/W3173044051","https://openalex.org/W3203277135","https://openalex.org/W2903066966","https://openalex.org/W3043639844","https://openalex.org/W2973067430","https://openalex.org/W3095439107","https://openalex.org/W2802137907","https://openalex.org/W2017092402","https://openalex.org/W3086212491","https://openalex.org/W2967948243","https://openalex.org/W2028561103","https://openalex.org/W2962866891"],"abstract_inverted_index":{"Environmental":[0],"Sound":[1],"Classification":[2],"(ESC)":[3],"is":[4,56,185],"a":[5,35,50,67],"rapidly":[6],"evolving":[7],"field":[8],"that":[9,27,55,162],"recently":[10],"demonstrated":[11],"the":[12,21,28,39,72,80,93,100,126,132,138,157,163,166,179],"advantages":[13],"of":[14,16,31,42,95,103,122,140,150,181],"application":[15],"visual":[17],"domain":[18],"techniques":[19],"to":[20,169,175],"audio-related":[22],"tasks.":[23],"Previous":[24],"studies":[25],"indicate":[26],"domain-specific":[29],"modification":[30],"cross-domain":[32],"approaches":[33,118],"show":[34],"promise":[36],"in":[37,173],"pushing":[38],"whole":[40],"area":[41],"ESC":[43],"forward.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,136],"present":[49],"new":[51],"time-frequency":[52],"transformation":[53],"layer":[54,159],"based":[57],"on":[58,87,125,131],"complex":[59],"frequency":[60],"B-spline":[61],"(fbsp)":[62],"wavelets.":[63],"Being":[64],"used":[65,82],"with":[66],"high-performance":[68],"audio":[69],"classification":[70],"model,":[71],"proposed":[73,114,158],"fbsp-layer":[74,164],"provides":[75],"an":[76,151],"accuracy":[77],"improvement":[78],"over":[79],"previously":[81],"Short-Time":[83],"Fourier":[84],"Transform":[85],"(STFT)":[86],"standard":[88],"datasets.":[89,134],"We":[90],"also":[91],"investigate":[92],"influence":[94],"different":[96],"pre-training":[97],"strategies,":[98],"including":[99],"joint":[101],"use":[102],"two":[104],"large-scale":[105],"datasets":[106],"for":[107],"weight":[108],"initialization:":[109],"ImageNet":[110],"and":[111,128,148,160],"AudioSet.":[112],"Our":[113],"model":[115,141],"out-performs":[116],"other":[117],"by":[119,156],"achieving":[120],"accuracies":[121],"95.20":[123],"%":[124,130],"ESC-50":[127],"89.14":[129],"UrbanSound8K":[133],"Additionally,":[135],"assess":[137],"increase":[139],"robustness":[142],"against":[143],"additive":[144],"white":[145],"Gaussian":[146],"noise":[147],"reduction":[149],"effective":[152],"sample":[153],"rate":[154],"introduced":[155],"demonstrate":[161],"improves":[165],"model's":[167],"ability":[168],"withstand":[170],"signal":[171],"perturbations,":[172],"comparison":[174],"STFT-based":[176],"training.":[177],"For":[178],"sake":[180],"reproducibility,":[182],"our":[183],"code":[184],"made":[186],"available.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}