{"id":"https://openalex.org/W4392908114","doi":"https://doi.org/10.1109/taslp.2024.3376984","title":"Dynamic Convolutional Neural Networks as Efficient Pre-Trained Audio Models","display_name":"Dynamic Convolutional Neural Networks as Efficient Pre-Trained Audio Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4392908114","doi":"https://doi.org/10.1109/taslp.2024.3376984"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3376984","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3376984","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10472152.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10472152.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Florian Schmid","raw_affiliation_strings":["Institute of Computational Perception (CP-JKU), Johannes Kepler University Linz, Linz, Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception (CP-JKU), Johannes Kepler University Linz, 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":["LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Linz, Austria","LIT Artificial Intelligence Lab, and the CP-JKU, Johannes Kepler University Linz 4040, Austria"],"affiliations":[{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, and the CP-JKU, Johannes Kepler University Linz 4040, 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":["LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Linz, Austria","LIT Artificial Intelligence Lab, and the CP-JKU, Johannes Kepler University Linz 4040, Austria"],"affiliations":[{"raw_affiliation_string":"LIT Artificial Intelligence Lab, Johannes Kepler University Linz, Linz, Austria","institution_ids":["https://openalex.org/I121883995"]},{"raw_affiliation_string":"LIT Artificial Intelligence Lab, and the CP-JKU, Johannes Kepler University Linz 4040, Austria","institution_ids":["https://openalex.org/I121883995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103009549"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":8.8479,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.98521698,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"32","issue":null,"first_page":"2227","last_page":"2241"},"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":0.9986000061035156,"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":0.9977999925613403,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7566256523132324},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7074240446090698},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48573142290115356},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3572930693626404}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7566256523132324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074240446090698},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48573142290115356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3572930693626404}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2024.3376984","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3376984","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10472152.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:epub.jku.at/:13380031","is_oa":true,"landing_page_url":"https://epub.jku.at/doi/10.1109/TASLP.2024.3376984","pdf_url":null,"source":{"id":"https://openalex.org/S4306401788","display_name":"University Library Linz repository (Johannes Kepler Universitat Linz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121883995","host_organization_name":"Johannes Kepler University of Linz","host_organization_lineage":["https://openalex.org/I121883995"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3376984","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3376984","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10472152.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1808229388","display_name":"Exploring Musical Possibilities via Machine Simulation","funder_award_id":"101019375","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392908114.pdf","grobid_xml":"https://content.openalex.org/works/W4392908114.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1982479097","https://openalex.org/W2052666245","https://openalex.org/W2108598243","https://openalex.org/W2294370754","https://openalex.org/W2593116425","https://openalex.org/W2752782242","https://openalex.org/W2883780447","https://openalex.org/W2890223989","https://openalex.org/W2912776959","https://openalex.org/W2936774411","https://openalex.org/W2963125010","https://openalex.org/W2963139879","https://openalex.org/W2963163009","https://openalex.org/W2963918968","https://openalex.org/W2981408784","https://openalex.org/W2982083293","https://openalex.org/W2982220924","https://openalex.org/W2995343971","https://openalex.org/W3012740297","https://openalex.org/W3034421924","https://openalex.org/W3035678286","https://openalex.org/W3081168214","https://openalex.org/W3094550259","https://openalex.org/W3119205652","https://openalex.org/W3138516171","https://openalex.org/W3165587897","https://openalex.org/W3170224286","https://openalex.org/W3172353912","https://openalex.org/W3177052299","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3205743929","https://openalex.org/W3206996142","https://openalex.org/W3213879871","https://openalex.org/W4205689591","https://openalex.org/W4221149441","https://openalex.org/W4224924125","https://openalex.org/W4225331914","https://openalex.org/W4226165006","https://openalex.org/W4226442948","https://openalex.org/W4280567182","https://openalex.org/W4289752563","https://openalex.org/W4297775537","https://openalex.org/W4372260403","https://openalex.org/W4372266552","https://openalex.org/W4377164418","https://openalex.org/W4379251221","https://openalex.org/W4385245566","https://openalex.org/W4386076493","https://openalex.org/W4388115392","https://openalex.org/W4388117483","https://openalex.org/W4392904001","https://openalex.org/W6631190155","https://openalex.org/W6638523607","https://openalex.org/W6679909955","https://openalex.org/W6696761078","https://openalex.org/W6716109767","https://openalex.org/W6737664043","https://openalex.org/W6745136726","https://openalex.org/W6746023985","https://openalex.org/W6753038380","https://openalex.org/W6756597712","https://openalex.org/W6757585730","https://openalex.org/W6762718338","https://openalex.org/W6767312599","https://openalex.org/W6771249245","https://openalex.org/W6779341498","https://openalex.org/W6784333009","https://openalex.org/W6793164127","https://openalex.org/W6809596386","https://openalex.org/W6810405975","https://openalex.org/W6840200333","https://openalex.org/W6843663730","https://openalex.org/W6846479224","https://openalex.org/W6848208918","https://openalex.org/W6852934099"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"introduction":[1],"of":[2,62,98,104,113,139,146],"large-scale":[3,151],"audio":[4,17,147],"datasets,":[5,39],"such":[6,134],"as":[7,22,135],"AudioSet,":[8],"paved":[9],"the":[10,16,23,102,140,144,150,158],"way":[11],"for":[12,28,168],"Transformers":[13,33,57,87],"to":[14,66],"conquer":[15],"domain":[18],"and":[19,84,100,121],"replace":[20],"CNNs":[21,46,79,106,129,161],"state-of-the-art":[24],"neural":[25],"network":[26],"architecture":[27],"many":[29],"tasks.":[30,51],"Audio":[31,55],"Spectrogram":[32,56],"are":[34,58],"excellent":[35],"at":[36,143],"exploiting":[37],"large":[38,89],"creating":[40],"powerful":[41],"pre-trained":[42],"models":[43,167],"that":[44,126,157],"surpass":[45],"when":[47],"fine-tuned":[48],"on":[49,88,149,171],"downstream":[50,172],"However,":[52],"current":[53],"popular":[54],"demanding":[59],"in":[60,137],"terms":[61,138],"computational":[63],"complexity":[64],"compared":[65],"CNNs.":[67],"Recently,":[68],"we":[69,94],"have":[70],"shown":[71],"that,":[72],"by":[73,107],"employing":[74],"Transformer-to-CNN":[75],"Knowledge":[76],"Distillation,":[77],"efficient":[78,105,132],"can":[80],"catch":[81],"up":[82],"with":[83,165],"even":[85],"outperform":[86,130],"datasets.":[90],"In":[91],"this":[92,96],"work,":[93],"extend":[95],"line":[97],"research":[99],"increase":[101],"capacity":[103],"introducing":[108],"dynamic":[109,114,117,128,160],"CNN":[110],"blocks":[111],"constructed":[112],"convolutions,":[115],"a":[116],"ReLU":[118],"activation":[119],"function,":[120],"Coordinate":[122],"Attention.":[123],"We":[124],"show":[125],"these":[127],"traditional":[131],"CNNs,":[133],"MobileNets,":[136],"performance\u2013complexity":[141],"trade-off":[142],"task":[145],"tagging":[148],"AudioSet.":[152],"Our":[153],"experiments":[154],"further":[155],"indicate":[156],"proposed":[159],"achieve":[162],"competitive":[163],"performance":[164],"Transformer-based":[166],"end-to-end":[169],"fine-tuning":[170],"tasks":[173],"while":[174],"being":[175],"much":[176],"more":[177],"computationally":[178],"efficient.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}