{"id":"https://openalex.org/W4286278015","doi":"https://doi.org/10.1109/ist55454.2022.9827729","title":"Spectrogram Transformers for Audio Classification","display_name":"Spectrogram Transformers for Audio Classification","publication_year":2022,"publication_date":"2022-06-21","ids":{"openalex":"https://openalex.org/W4286278015","doi":"https://doi.org/10.1109/ist55454.2022.9827729"},"language":"en","primary_location":{"id":"doi:10.1109/ist55454.2022.9827729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ist55454.2022.9827729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Imaging Systems and Techniques (IST)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Spectrogram_transformers_for_audio_classification/21186001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100635278","display_name":"Yixiao Zhang","orcid":"https://orcid.org/0000-0001-7026-4202"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yixiao Zhang","raw_affiliation_strings":["Loughborough University,Department of Computer Science,Loughborough,U.K","Department of Computer Science, Loughborough University, Loughborough, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University,Department of Computer Science,Loughborough,U.K","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Department of Computer Science, Loughborough University, Loughborough, U.K","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072835010","display_name":"Baihua Li","orcid":"https://orcid.org/0000-0002-4930-7690"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Baihua Li","raw_affiliation_strings":["Loughborough University,Department of Computer Science,Loughborough,U.K","Department of Computer Science, Loughborough University, Loughborough, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University,Department of Computer Science,Loughborough,U.K","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Department of Computer Science, Loughborough University, Loughborough, U.K","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046565976","display_name":"Hui Fang","orcid":"https://orcid.org/0000-0001-9365-7420"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hui Fang","raw_affiliation_strings":["Loughborough University,Department of Computer Science,Loughborough,U.K","Department of Computer Science, Loughborough University, Loughborough, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University,Department of Computer Science,Loughborough,U.K","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Department of Computer Science, Loughborough University, Loughborough, U.K","institution_ids":["https://openalex.org/I143804889"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014654309","display_name":"Qinggang Meng","orcid":"https://orcid.org/0000-0002-9483-5724"},"institutions":[{"id":"https://openalex.org/I143804889","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365","country_code":"GB","type":"education","lineage":["https://openalex.org/I143804889"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qinggang Meng","raw_affiliation_strings":["Loughborough University,Department of Computer Science,Loughborough,U.K","Department of Computer Science, Loughborough University, Loughborough, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Loughborough University,Department of Computer Science,Loughborough,U.K","institution_ids":["https://openalex.org/I143804889"]},{"raw_affiliation_string":"Department of Computer Science, Loughborough University, Loughborough, U.K","institution_ids":["https://openalex.org/I143804889"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100635278"],"corresponding_institution_ids":["https://openalex.org/I143804889"],"apc_list":null,"apc_paid":null,"fwci":3.2722,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.9269616,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9979000091552734,"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":0.9825999736785889,"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":0.933773398399353},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7288858890533447},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6721757650375366},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6490967273712158},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5703093409538269},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5094855427742004},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39588478207588196},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1213761568069458}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.933773398399353},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7288858890533447},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6721757650375366},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6490967273712158},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5703093409538269},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5094855427742004},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39588478207588196},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1213761568069458},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ist55454.2022.9827729","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ist55454.2022.9827729","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Imaging Systems and Techniques (IST)","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/21186001","is_oa":true,"landing_page_url":null,"pdf_url":"https://figshare.com/articles/conference_contribution/Spectrogram_transformers_for_audio_classification/21186001","source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/21186001","is_oa":true,"landing_page_url":null,"pdf_url":"https://figshare.com/articles/conference_contribution/Spectrogram_transformers_for_audio_classification/21186001","source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320341","display_name":"Loughborough University","ror":"https://ror.org/04vg4w365"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4286278015.pdf"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2052666245","https://openalex.org/W2059652044","https://openalex.org/W2143800062","https://openalex.org/W2305675433","https://openalex.org/W2518102674","https://openalex.org/W2526050071","https://openalex.org/W2566935005","https://openalex.org/W2641889749","https://openalex.org/W2738563279","https://openalex.org/W2766397045","https://openalex.org/W2768083292","https://openalex.org/W2793307691","https://openalex.org/W2883651221","https://openalex.org/W2884436603","https://openalex.org/W2936774411","https://openalex.org/W2972425456","https://openalex.org/W3000820788","https://openalex.org/W3016081131","https://openalex.org/W3022215617","https://openalex.org/W3045062880","https://openalex.org/W3158553615","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3206162967","https://openalex.org/W4286582832","https://openalex.org/W4289288178","https://openalex.org/W4293665662","https://openalex.org/W4385245566","https://openalex.org/W6729831399","https://openalex.org/W6739901393","https://openalex.org/W6740195615","https://openalex.org/W6755726434","https://openalex.org/W6761305474","https://openalex.org/W6781150751","https://openalex.org/W6792861227","https://openalex.org/W6802331139","https://openalex.org/W6802510933","https://openalex.org/W6840046036"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W2404514746","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W1652783584","https://openalex.org/W2088733771","https://openalex.org/W2958404818"],"abstract_inverted_index":{"Audio":[0],"classification":[1,124],"is":[2],"an":[3],"important":[4],"task":[5],"in":[6],"the":[7,18,30,59,117,123,134],"machine":[8],"learning":[9,22],"field":[10],"with":[11,151],"a":[12,49],"wide":[13],"range":[14],"of":[15,51,62,93],"applications.":[16],"Since":[17],"last":[19],"decade,":[20],"deep":[21],"based":[23],"methods":[24,136],"have":[25],"been":[26],"widely":[27],"used":[28],"and":[29,72,81,110],"transformer-based":[31,52],"models":[32,53,132],"are":[33,48,87],"becoming":[34],"new":[35],"paradigm":[36],"for":[37,54],"audio":[38,55,63,76],"classification.":[39,56],"In":[40],"this":[41],"paper,":[42],"we":[43,65],"present":[44],"Spectrogram":[45],"Transformers,":[46],"which":[47],"group":[50],"Based":[57],"on":[58,137],"fundamental":[60],"semantics":[61],"spectrogram,":[64,77],"design":[66],"two":[67],"mechanisms":[68],"to":[69,115,121],"extract":[70,116],"temporal":[71],"frequency":[73],"features":[74],"from":[75],"named":[78],"time-dimension":[79],"sampling":[80],"frequency-dimension":[82],"sampling.":[83],"These":[84],"discriminative":[85],"representations":[86],"then":[88],"enhanced":[89],"by":[90],"various":[91],"combinations":[92],"attention":[94],"block":[95],"architectures,":[96],"including":[97],"Tempo-ral":[98],"Only":[99],"(TO)":[100],"attention,":[101,105,109,114],"Temporal-Frequency":[102,106,112],"sequential":[103],"(TFS)":[104],"Parallel":[107],"(TFP)":[108],"Two-stream":[111],"(TSTF)":[113],"sound":[118],"record":[119],"signatures":[120],"serve":[122],"task.":[125],"Our":[126],"experiments":[127],"demonstrate":[128],"that":[129],"these":[130],"Transformer":[131],"outper-form":[133],"state-of-the-art":[135],"ESC-50":[138],"dataset":[139],"without":[140],"pre-training":[141],"stage.":[142],"Furthermore,":[143],"our":[144],"method":[145],"also":[146],"shows":[147],"great":[148],"efficiency":[149],"compared":[150],"other":[152],"leading":[153],"methods.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}