{"id":"https://openalex.org/W7225257172","doi":"https://doi.org/10.5281/zenodo.23954009","title":"Patch-AST: A Patch-Based Audio Spectrogram Transformer for Multiclass Environmental Noise Classification in Noisy Speech Under Variable SNR Conditions","display_name":"Patch-AST: A Patch-Based Audio Spectrogram Transformer for Multiclass Environmental Noise Classification in Noisy Speech Under Variable SNR Conditions","publication_year":2026,"publication_date":"2026-11-04","ids":{"openalex":"https://openalex.org/W7225257172","doi":"https://doi.org/10.5281/zenodo.23954009"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23954009","doi":"https://doi.org/10.5281/zenodo.23954009","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23954009","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23954009","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063781411","display_name":"Achal Nilhani","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Nilhani, Achal","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-8569-996X","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5063781411"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.5160999894142151,"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":0.5160999894142151,"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":0.350600004196167,"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":0.12370000034570694,"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/audio-spectrogram-transformer","display_name":"Audio Spectrogram Transformer","score":0.9330000281333923},{"id":"https://openalex.org/keywords/mel-spectrogram","display_name":"Mel spectrogram","score":0.6349999904632568},{"id":"https://openalex.org/keywords/self-attention-encoder","display_name":"self-attention encoder","score":0.7509999871253967},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"signal-to-noise ratio","score":0.8619999885559082},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.6980000138282776},{"id":"https://openalex.org/keywords/background-noise","display_name":"background noise","score":0.3970000147819519},{"id":"https://openalex.org/keywords/airport-noise","display_name":"airport noise","score":0.5410000085830688},{"id":"https://openalex.org/keywords/babble-noise","display_name":"babble noise","score":0.9120000004768372},{"id":"https://openalex.org/keywords/restaurant-noise","display_name":"restaurant noise","score":0.9800000190734863},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.5440000295639038},{"id":"https://openalex.org/keywords/hearing-aids","display_name":"hearing aids","score":0.5180000066757202},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.36500000953674316}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9043999910354614},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.713699996471405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518999934196472},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46799999475479126},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4253000020980835},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4251999855041504},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41530001163482666},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41100001335144043},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.40230000019073486},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.3343999981880188},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31049999594688416},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23954009","doi":"https://doi.org/10.5281/zenodo.23954009","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23954009","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23954010","doi":"https://doi.org/10.5281/zenodo.23954010","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23954010","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23954009","doi":"https://doi.org/10.5281/zenodo.23954009","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23954009","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4389240925","https://openalex.org/W4407986641","https://openalex.org/W3196974791","https://openalex.org/W4403733710","https://openalex.org/W3206996142","https://openalex.org/W4372187991","https://openalex.org/W3172426420","https://openalex.org/W7133514121","https://openalex.org/W4406364355","https://openalex.org/W4407901436"],"abstract_inverted_index":{"Abstract\u2014Reliable":[0],"identification":[1],"of":[2,94,122,132,166,185],"the":[3,123,128,133,152,155,179],"acoustic":[4],"environment":[5],"surrounding":[6],"a":[7,27,71,86,107,112,164],"speech":[8,11,17,45,221],"signal":[9],"supports":[10],"enhancement,":[12],"hearing-aid":[13],"noise":[14,129,216],"suppression,":[15],"adaptive":[16],"recognition":[18],"and":[19,40,68,91,103,116,173,175,195,202],"context-aware":[20],"voice":[21],"assistants.":[22],"This":[23],"paper":[24],"presents":[25],"Patch-AST,":[26],"compact":[28],"Audio":[29],"Spectrogram":[30],"Transformer":[31],"that":[32,127],"classifies":[33],"four":[34],"background-noise":[35],"environments":[36],"(Airport,":[37],"Babble,":[38],"Restaurant":[39],"Station)":[41],"mixed":[42,97],"with":[43,76],"clean":[44],"at":[46,136,141,193,200],"six":[47],"signal-to-noise":[48,219],"ratios":[49],"(SNRs)":[50],"from":[51,83],"\u22125":[52],"to":[53,197],"10dB.":[54],"Log-Mel":[55],"spectrograms":[56],"are":[57],"split":[58],"into":[59],"frame-level":[60],"tokens,":[61],"linearly":[62],"embedded,":[63],"given":[64],"learned":[65],"positional":[66],"encodings,":[67],"processed":[69],"by":[70],"six-layer":[72],"multi-head":[73],"self-attention":[74],"encoder":[75],"20,099,844":[77],"parameters.":[78],"The":[79],"model":[80,125,156],"is":[81],"trained":[82],"scratch":[84],"on":[85],"corpus":[87],"balanced":[88],"across":[89],"classes":[90],"SNR":[92,149],"levels":[93],"120,000":[95],"synthetically":[96],"utterances":[98],"(84,000":[99],"training,":[100],"18,000":[101,104],"validation":[102],"test)":[105],"using":[106],"class-weighted":[108],"focal":[109],"loss,":[110],"AdamW,":[111],"one-cycle":[113],"learning-rate":[114],"schedule":[115],"early":[117],"stopping.":[118],"A":[119],"short":[120],"analysis":[121],"mixing":[124],"shows":[126],"contributes":[130],"76%":[131],"mixture":[134],"energy":[135],"\u22125dB":[137,194],"but":[138],"only":[139],"9%":[140],"10dB,":[142,201],"which":[143],"explains":[144],"why":[145],"accuracy":[146,159],"decreases":[147],"as":[148],"increases.":[150],"On":[151],"test":[153],"set":[154],"reaches":[157],"94.59%":[158],"(95%":[160],"Wilson":[161],"interval":[162],"94.25\u201394.91%),":[163],"macro-F1":[165],"0.95,":[167],"per-class":[168],"Brier":[169],"scores":[170],"between":[171],"0.0129":[172],"0.0201,":[174],"an":[176],"area":[177],"under":[178],"receiver":[180],"operating":[181],"characteristic":[182],"curve":[183],"(ROC-AUC)":[184],"1.00":[186],"for":[187],"every":[188],"class.":[189],"Accuracy":[190],"exceeds":[191],"98%":[192],"falls":[196],"about":[198],"84%":[199],"two-dimensional":[203],"embedding":[204],"projections":[205],"show":[206],"largely":[207],"separable":[208],"classes.":[209],"Index":[210],"Terms\u2014Audio":[211],"spectrogram":[212],"transformer,":[213],"Mel":[214],"spectrogram,":[215],"classification,":[217],"self-attention,":[218],"ratio,":[220],"enhancement":[222]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}