{"id":"https://openalex.org/W4392969643","doi":"https://doi.org/10.1109/icassp48485.2024.10448376","title":"From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers","display_name":"From Coarse to Fine: Efficient Training for Audio Spectrogram Transformers","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392969643","doi":"https://doi.org/10.1109/icassp48485.2024.10448376"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5102441906","display_name":"Jiu Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jiu Feng","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043775291","display_name":"Mehmet Hamza Erol","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mehmet Hamza Erol","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038723822","display_name":"Joon Son Chung","orcid":"https://orcid.org/0000-0001-7741-7275"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon Son Chung","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070707693","display_name":"Arda Senocak","orcid":"https://orcid.org/0000-0001-9141-3270"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Arda Senocak","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,South Korea","Korea Advanced Institute of Science and Technology, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,South Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102441906"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":1.0087,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.7269404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1416","last_page":"1420"},"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":0.9998000264167786,"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":0.9950000047683716,"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":0.9218274354934692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.725672721862793},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7168819904327393},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48332834243774414},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4561537802219391},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40078645944595337},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.1482892632484436},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14161169528961182}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9218274354934692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.725672721862793},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7168819904327393},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48332834243774414},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4561537802219391},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40078645944595337},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.1482892632484436},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14161169528961182},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448376","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G1739134435","display_name":null,"funder_award_id":"IITP-","funder_id":"https://openalex.org/F4320324891","funder_display_name":"Iran Telecommunication Research Center"},{"id":"https://openalex.org/G2327342398","display_name":null,"funder_award_id":"RS-2023-0021","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G8670528041","display_name":null,"funder_award_id":"IITP-2024-RS-2023-00259991","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2619947201","https://openalex.org/W2981087920","https://openalex.org/W3015371781","https://openalex.org/W3094550259","https://openalex.org/W3117786798","https://openalex.org/W3138516171","https://openalex.org/W3196974791","https://openalex.org/W3197580070","https://openalex.org/W3205475937","https://openalex.org/W3206996142","https://openalex.org/W4226442948","https://openalex.org/W4297841853","https://openalex.org/W4308827614","https://openalex.org/W4319300082","https://openalex.org/W4367692538","https://openalex.org/W4372260443","https://openalex.org/W4372266890","https://openalex.org/W4372341324","https://openalex.org/W4385822401","https://openalex.org/W4386075535","https://openalex.org/W4393157029","https://openalex.org/W6734260513","https://openalex.org/W6784333009","https://openalex.org/W6810510949","https://openalex.org/W6810980340","https://openalex.org/W6840200333","https://openalex.org/W6846372546","https://openalex.org/W6851996479","https://openalex.org/W6852086931","https://openalex.org/W6955071965"],"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":{"Transformers":[0],"have":[1],"become":[2],"central":[3],"to":[4,43,49,127,148],"recent":[5],"advances":[6],"in":[7,52,99,111],"audio":[8,13,35,60],"classification.":[9],"However,":[10],"training":[11,46,58,122],"an":[12],"spectrogram":[14,36,61],"transformer,":[15],"e.g.":[16],"AST,":[17],"from":[18,95],"scratch":[19],"can":[20],"be":[21],"resource":[22],"and":[23,103,140],"time-intensive.":[24],"Furthermore,":[25],"the":[26,33,50,53,65,91,100,120],"complexity":[27],"of":[28,59,68,80,88,153],"transformers":[29,62],"heavily":[30],"depends":[31],"on":[32],"input":[34],"size.":[37],"In":[38],"this":[39],"work,":[40],"we":[41,76],"aim":[42],"optimize":[44],"AST":[45,125],"by":[47,63],"linking":[48],"resolution":[51],"time-axis.":[54],"We":[55],"introduce":[56],"multi-phase":[57],"connecting":[64],"seminal":[66],"idea":[67],"coarse-to-fine":[69],"with":[70,107,132],"transformer":[71,92],"models.":[72],"To":[73],"achieve":[74],"this,":[75],"propose":[77],"a":[78,112],"set":[79],"methods":[81,151],"for":[82,124],"temporal":[83],"compression.":[84],"By":[85],"employing":[86],"one":[87],"these":[89],"methods,":[90],"model":[93],"learns":[94],"lowerresolution":[96],"(coarse)":[97],"data":[98,109],"initial":[101],"phases,":[102],"then":[104],"is":[105,145],"fine-tuned":[106],"high-resolution":[108],"later":[110],"curriculum":[113],"learning":[114,155],"strategy.":[115],"Experimental":[116],"results":[117],"demonstrate":[118],"that":[119],"proposed":[121],"mechanism":[123],"leads":[126],"improved":[128],"(or":[129],"on-par)":[130],"performance":[131],"faster":[133],"convergence,":[134],"i.e.":[135],"requiring":[136],"fewer":[137],"computational":[138],"resources":[139],"less":[141],"time.":[142],"This":[143],"approach":[144],"also":[146],"generalizable":[147],"other":[149],"AST-based":[150],"regardless":[152],"their":[154],"paradigms.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
