{"id":"https://openalex.org/W4372187991","doi":"https://doi.org/10.1109/icassp49357.2023.10095023","title":"MAST: Multiscale Audio Spectrogram Transformers","display_name":"MAST: Multiscale Audio Spectrogram Transformers","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372187991","doi":"https://doi.org/10.1109/icassp49357.2023.10095023"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095023","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5033408639","display_name":"Sreyan Ghosh","orcid":"https://orcid.org/0000-0003-3773-561X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreyan Ghosh","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018932560","display_name":"Ashish Seth","orcid":"https://orcid.org/0000-0003-3100-9342"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ashish Seth","raw_affiliation_strings":["IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India","Department of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Department of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085660348","display_name":"S. Umesh","orcid":"https://orcid.org/0000-0002-5957-1444"},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"education","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Umesh","raw_affiliation_strings":["IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India","Department of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIT Madras,Speech Lab,Department of Electrical Engineering,Chennai,India","institution_ids":["https://openalex.org/I24676775"]},{"raw_affiliation_string":"Department of Electrical Engineering, Speech Lab, IIT Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland,College Park,USA","University of Maryland, College Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland,College Park,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2083,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80014058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.9998000264167786,"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":0.996399998664856,"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":0.7969719767570496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6799393892288208},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6693828105926514},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5479779243469238},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5265586376190186},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5122029185295105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4411834478378296},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4188350439071655},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3646644353866577},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08149755001068115}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7969719767570496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6799393892288208},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6693828105926514},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5479779243469238},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5265586376190186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5122029185295105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4411834478378296},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4188350439071655},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3646644353866577},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08149755001068115},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095023","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2146334809","https://openalex.org/W2606176153","https://openalex.org/W2622627557","https://openalex.org/W2726515241","https://openalex.org/W2786568644","https://openalex.org/W2797583228","https://openalex.org/W2883935097","https://openalex.org/W2963669405","https://openalex.org/W3035524453","https://openalex.org/W3036601975","https://openalex.org/W3094502228","https://openalex.org/W3145450063","https://openalex.org/W3163937874","https://openalex.org/W3196974791","https://openalex.org/W3197704090","https://openalex.org/W3197940657","https://openalex.org/W3201143670","https://openalex.org/W3206649123","https://openalex.org/W3206996142","https://openalex.org/W4214614183","https://openalex.org/W4225713393","https://openalex.org/W4293370787","https://openalex.org/W4295723153","https://openalex.org/W4312769131","https://openalex.org/W4385245566","https://openalex.org/W6736723571","https://openalex.org/W6739901393","https://openalex.org/W6740167877","https://openalex.org/W6750665317","https://openalex.org/W6780218876","https://openalex.org/W6784333009","https://openalex.org/W6797356783","https://openalex.org/W6802796180"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2016904525"],"abstract_inverted_index":{"We":[0,64,104],"present":[1,110],"Multiscale":[2],"Audio":[3,20],"Spectrogram":[4,21],"Transformer":[5,22],"(MAST)":[6],"for":[7],"audio":[8,28,139],"classification,":[9],"which":[10,45,119],"brings":[11],"the":[12,19,46,53,58,62,164,189],"concept":[13],"of":[14,61,73,155,186],"multiscale":[15],"feature":[16],"hierarchies":[17],"to":[18,85,96,109],"(AST)":[23],"[1].":[24],"Given":[25],"an":[26,37,152,182],"input":[27],"spectrogram,":[29],"we":[30,143],"first":[31],"patchify":[32],"and":[33,41,91,131,160],"project":[34],"it":[35],"into":[36],"initial":[38],"temporal":[39,59,79],"resolution":[40,60,80],"embedding":[42,54,83],"dimension,":[43],"post":[44],"multiple":[47],"stages":[48],"in":[49,174],"MAST":[50,74,147],"progressively":[51],"expand":[52],"dimension":[55],"while":[56],"reducing":[57],"input.":[63],"use":[65],"a":[66,77,111,121,129,132,137],"pyramid":[67],"structure":[68],"that":[69,142],"allows":[70],"early":[71],"layers":[72,95],"operating":[75],"at":[76],"high":[78],"but":[81],"low":[82],"space":[84],"model":[86,97],"simple":[87],"low-level":[88],"acoustic":[89,99],"information":[90,100],"deeper":[92],"temporally":[93],"coarse":[94],"high-level":[98],"with":[101],"high-dimensional":[102],"embeddings.":[103],"also":[105],"extend":[106],"our":[107,178],"approach":[108,141],"new":[112],"Self-Supervised":[113],"Learning":[114],"(SSL)":[115],"method":[116],"called":[117],"SS-MAST,":[118],"calculates":[120],"symmetric":[122],"contrastive":[123],"loss":[124],"between":[125],"latent":[126],"representations":[127],"from":[128,163],"student":[130],"teacher":[133],"encoder,":[134],"leveraging":[135],"patch-drop,":[136],"novel":[138],"augmentation":[140],"introduce.":[144],"In":[145],"practice,":[146],"significantly":[148],"outperforms":[149],"AST":[150],"by":[151],"average":[153,184],"accuracy":[154],"3.4%":[156],"across":[157],"8":[158],"speech":[159],"non-speech":[161],"tasks":[162],"LAPE":[165],"Benchmark":[166],"[2],":[167],"achieving":[168],"state-of-the-art":[169],"results":[170],"on":[171],"keyword":[172],"spotting":[173],"Speech":[175],"Commands.":[176],"Additionally,":[177],"proposed":[179,191],"SS-MAST":[180],"achieves":[181],"absolute":[183],"improvement":[185],"2.6%":[187],"over":[188],"previously":[190],"SSAST":[192],"[3]1.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}