{"id":"https://openalex.org/W4388570656","doi":"https://doi.org/10.3390/s23229084","title":"EnViTSA: Ensemble of Vision Transformer with SpecAugment for Acoustic Event Classification","display_name":"EnViTSA: Ensemble of Vision Transformer with SpecAugment for Acoustic Event Classification","publication_year":2023,"publication_date":"2023-11-10","ids":{"openalex":"https://openalex.org/W4388570656","doi":"https://doi.org/10.3390/s23229084","pmid":"https://pubmed.ncbi.nlm.nih.gov/38005472"},"language":"en","primary_location":{"id":"doi:10.3390/s23229084","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23229084","pdf_url":"https://www.mdpi.com/1424-8220/23/22/9084/pdf?version=1699583143","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/22/9084/pdf?version=1699583143","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017532046","display_name":"Kian Ming Lim","orcid":"https://orcid.org/0000-0003-1929-7978"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Kian Ming Lim","raw_affiliation_strings":["Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-1929-7978","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086127398","display_name":"Chin Poo Lee","orcid":"https://orcid.org/0000-0003-3679-8977"},"institutions":[{"id":"https://openalex.org/I173029219","display_name":"Multimedia University","ror":"https://ror.org/04zrbnc33","country_code":"MY","type":"education","lineage":["https://openalex.org/I173029219"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Chin Poo Lee","raw_affiliation_strings":["Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia"],"raw_orcid":"https://orcid.org/0000-0003-3679-8977","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia","institution_ids":["https://openalex.org/I173029219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111072528","display_name":"Zhi Yang Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I2801750897","display_name":"DKT International","ror":"https://ror.org/005aqed95","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I2801750897"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi Yang Lee","raw_affiliation_strings":["DZH International Sdn. Bhd., Kuala Lumpur 55100, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DZH International Sdn. Bhd., Kuala Lumpur 55100, Malaysia","institution_ids":["https://openalex.org/I2801750897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010388353","display_name":"Ali Alqahtani","orcid":"https://orcid.org/0000-0003-1052-2657"},"institutions":[{"id":"https://openalex.org/I82952536","display_name":"King Khalid University","ror":"https://ror.org/052kwzs30","country_code":"SA","type":"education","lineage":["https://openalex.org/I82952536"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ali Alqahtani","raw_affiliation_strings":["Center for Artificial Intelligence (CAI), King Khalid University, Abha 61421, Saudi Arabia","Department of Computer Science, King Khalid University, Abha 61421, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0003-1052-2657","affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence (CAI), King Khalid University, Abha 61421, Saudi Arabia","institution_ids":["https://openalex.org/I82952536"]},{"raw_affiliation_string":"Department of Computer Science, King Khalid University, Abha 61421, Saudi Arabia","institution_ids":["https://openalex.org/I82952536"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5086127398"],"corresponding_institution_ids":["https://openalex.org/I173029219"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2598},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2598},"fwci":2.4338,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90228033,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"23","issue":"22","first_page":"9084","last_page":"9084"},"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":0.9976000189781189,"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":0.98580002784729,"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/overfitting","display_name":"Overfitting","score":0.8984394073486328},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6989362239837646},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6537294387817383},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6282579898834229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5957587957382202},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5063716173171997},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.48229196667671204},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4439055025577545},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.41386204957962036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40453043580055237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3834609091281891},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.22644534707069397}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8984394073486328},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6989362239837646},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6537294387817383},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6282579898834229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957587957382202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5063716173171997},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.48229196667671204},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4439055025577545},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41386204957962036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40453043580055237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3834609091281891},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.22644534707069397},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/s23229084","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23229084","pdf_url":"https://www.mdpi.com/1424-8220/23/22/9084/pdf?version=1699583143","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:38005472","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38005472","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:shdl.mmu.edu.my:11977","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196753","display_name":"Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I173029219","host_organization_name":"Multimedia University","host_organization_lineage":["https://openalex.org/I173029219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},{"id":"pmh:oai:pubmedcentral.nih.gov:10674441","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10674441","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10674441/pdf/sensors-23-09084.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:0ad6ab3ae3ca4e1b813f6e3ecce9c58e","is_oa":true,"landing_page_url":"https://doaj.org/article/0ad6ab3ae3ca4e1b813f6e3ecce9c58e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 22, p 9084 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/s23229084","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23229084","pdf_url":"https://www.mdpi.com/1424-8220/23/22/9084/pdf?version=1699583143","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G1783768018","display_name":null,"funder_award_id":"RGP2/332/44","funder_id":"https://openalex.org/F4320326578","funder_display_name":"Telekom Malaysia Berhad"},{"id":"https://openalex.org/G3641693691","display_name":null,"funder_award_id":"RDTC/231084","funder_id":"https://openalex.org/F4320326578","funder_display_name":"Telekom Malaysia Berhad"},{"id":"https://openalex.org/G7777154079","display_name":null,"funder_award_id":"RDTC/231084","funder_id":"https://openalex.org/F4320324433","funder_display_name":"King Khalid University"},{"id":"https://openalex.org/G8481798901","display_name":null,"funder_award_id":"RGP2/332/44","funder_id":"https://openalex.org/F4320324433","funder_display_name":"King Khalid University"}],"funders":[{"id":"https://openalex.org/F4320324433","display_name":"King Khalid University","ror":"https://ror.org/052kwzs30"},{"id":"https://openalex.org/F4320326578","display_name":"Telekom Malaysia Berhad","ror":"https://ror.org/00s3fdw25"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388570656.pdf"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494733680","https://openalex.org/W1540471222","https://openalex.org/W1972567154","https://openalex.org/W1986315484","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2135131618","https://openalex.org/W2313745396","https://openalex.org/W2406743043","https://openalex.org/W2509065397","https://openalex.org/W2745357708","https://openalex.org/W2751841560","https://openalex.org/W2766087987","https://openalex.org/W2766397045","https://openalex.org/W2768083292","https://openalex.org/W2770228505","https://openalex.org/W2773357023","https://openalex.org/W2888469011","https://openalex.org/W2904809000","https://openalex.org/W2909327627","https://openalex.org/W2912262211","https://openalex.org/W2936774411","https://openalex.org/W2962785008","https://openalex.org/W2970602317","https://openalex.org/W2972247414","https://openalex.org/W2972425456","https://openalex.org/W3014593905","https://openalex.org/W3043920615","https://openalex.org/W3082878506","https://openalex.org/W3095348033","https://openalex.org/W3098357269","https://openalex.org/W3107683761","https://openalex.org/W3112251627","https://openalex.org/W3158553615","https://openalex.org/W3211391719","https://openalex.org/W4213019189","https://openalex.org/W4213099919","https://openalex.org/W4213125503","https://openalex.org/W4226085666","https://openalex.org/W4283268647","https://openalex.org/W4385245566","https://openalex.org/W6642568193","https://openalex.org/W6739901393","https://openalex.org/W6744053936"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W2922073769","https://openalex.org/W3099765033","https://openalex.org/W1038900426","https://openalex.org/W3124943098","https://openalex.org/W4308112567","https://openalex.org/W3162132941"],"abstract_inverted_index":{"Recent":[0],"successes":[1],"in":[2,51,85,116,190,200],"deep":[3,10,19],"learning":[4,20],"have":[5],"inspired":[6],"researchers":[7],"to":[8,13,30,33,67,100],"apply":[9],"neural":[11],"networks":[12],"Acoustic":[14],"Event":[15],"Classification":[16],"(AEC).":[17],"While":[18],"methods":[21],"can":[22],"train":[23],"effective":[24],"AEC":[25,70],"models,":[26],"they":[27],"are":[28,75],"susceptible":[29],"overfitting":[31,95],"due":[32],"the":[34,124,128,150,165,193,201],"models'":[35],"high":[36],"complexity.":[37],"In":[38,145],"this":[39,146],"paper,":[40],"we":[41,97,148],"introduce":[42],"EnViTSA,":[43],"an":[44,55],"innovative":[45],"approach":[46,134],"that":[47],"tackles":[48],"key":[49],"challenges":[50],"AEC.":[52],"EnViTSA":[53,114,151,185],"combines":[54],"ensemble":[56,118,133],"of":[57,113,119,127,167,174,195],"Vision":[58,121,129,196],"Transformers":[59,197],"with":[60],"SpecAugment,":[61],"a":[62,86,187],"novel":[63],"data":[64,92],"augmentation":[65],"technique,":[66],"significantly":[68],"enhance":[69],"performance.":[71],"Raw":[72],"acoustic":[73,202],"signals":[74],"transformed":[76],"into":[77],"Log":[78],"Mel-spectrograms":[79],"using":[80],"Short-Time":[81],"Fourier":[82],"Transform,":[83],"resulting":[84],"fixed-size":[87],"spectrogram":[88],"representation.":[89],"To":[90],"address":[91],"scarcity":[93],"and":[94,108,159,177,182,198],"issues,":[96],"employ":[98],"SpecAugment":[99,199],"generate":[101],"additional":[102],"training":[103],"samples":[104],"through":[105],"time":[106],"masking":[107],"frequency":[109],"masking.":[110],"The":[111,161],"core":[112],"resides":[115],"its":[117],"pre-trained":[120],"Transformers,":[122],"harnessing":[123],"unique":[125],"strengths":[126],"Transformer":[130],"architecture.":[131],"This":[132],"not":[135],"only":[136],"reduces":[137],"inductive":[138],"biases":[139],"but":[140],"also":[141],"effectively":[142],"mitigates":[143],"overfitting.":[144],"study,":[147],"evaluate":[149],"method":[152],"on":[153,179],"three":[154],"benchmark":[155],"datasets:":[156],"ESC-10,":[157,180],"ESC-50,":[158,181],"UrbanSound8K.":[160],"experimental":[162],"results":[163],"underscore":[164],"efficacy":[166],"our":[168],"approach,":[169],"achieving":[170],"impressive":[171],"accuracy":[172],"scores":[173],"93.50%,":[175],"85.85%,":[176],"83.20%":[178],"UrbanSound8K,":[183],"respectively.":[184],"represents":[186],"substantial":[188],"advancement":[189],"AEC,":[191],"demonstrating":[192],"potential":[194],"domain.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
