{"id":"https://openalex.org/W4399418689","doi":"https://doi.org/10.1145/3651671.3651733","title":"Evaluation of Environmental Sound Classification using Vision Transformer","display_name":"Evaluation of Environmental Sound Classification using Vision Transformer","publication_year":2024,"publication_date":"2024-02-02","ids":{"openalex":"https://openalex.org/W4399418689","doi":"https://doi.org/10.1145/3651671.3651733"},"language":"en","primary_location":{"id":"doi:10.1145/3651671.3651733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3651671.3651733","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3651671.3651733","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3651671.3651733","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009153249","display_name":"Changlong Wang","orcid":"https://orcid.org/0009-0002-2882-6288"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Changlong Wang","raw_affiliation_strings":["School of Engineering, Tohoku University, Japan"],"raw_orcid":"https://orcid.org/0009-0002-2882-6288","affiliations":[{"raw_affiliation_string":"School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082389304","display_name":"Akinori Ito","orcid":"https://orcid.org/0000-0002-8835-7877"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Ito","raw_affiliation_strings":["School of Engineering, Tohoku University, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8835-7877","affiliations":[{"raw_affiliation_string":"School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091720513","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0002-2278-0429"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["School of Engineering, Tohoku University, Japan"],"raw_orcid":"https://orcid.org/0000-0002-2278-0429","affiliations":[{"raw_affiliation_string":"School of Engineering, Tohoku University, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004459028","display_name":"Chia-Ping Chen","orcid":"https://orcid.org/0000-0002-0151-2556"},"institutions":[{"id":"https://openalex.org/I142974352","display_name":"National Sun Yat-sen University","ror":"https://ror.org/00mjawt10","country_code":"TW","type":"education","lineage":["https://openalex.org/I142974352"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Ping Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, National Sun Yat-Sen University, China (Taiwan)"],"raw_orcid":"https://orcid.org/0000-0002-0151-2556","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, National Sun Yat-Sen University, China (Taiwan)","institution_ids":["https://openalex.org/I142974352"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009153249"],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":null,"apc_paid":null,"fwci":0.9865,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.73429465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"665","last_page":"669"},"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":0.9961000084877014,"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":0.984499990940094,"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/transformer","display_name":"Transformer","score":0.7420755624771118},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6639941334724426},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5682932138442993},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.501779317855835},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48565566539764404},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.26027339696884155}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7420755624771118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639941334724426},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5682932138442993},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.501779317855835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48565566539764404},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26027339696884155},{"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:10.1145/3651671.3651733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3651671.3651733","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3651671.3651733","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3651671.3651733","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3651671.3651733","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3651671.3651733","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 16th International Conference on Machine Learning and Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418689.pdf"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1972567154","https://openalex.org/W2052666245","https://openalex.org/W2403438050","https://openalex.org/W2509065397","https://openalex.org/W2529337537","https://openalex.org/W2593451766","https://openalex.org/W2745357708","https://openalex.org/W2751841560","https://openalex.org/W2766087987","https://openalex.org/W2962910554","https://openalex.org/W2981733351","https://openalex.org/W2997271062","https://openalex.org/W3098357269","https://openalex.org/W3116292642","https://openalex.org/W3161026535","https://openalex.org/W3178592608","https://openalex.org/W3197827948","https://openalex.org/W4226442948","https://openalex.org/W4292397060","https://openalex.org/W4372266552","https://openalex.org/W4386075535","https://openalex.org/W6931259419"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3082059448","https://openalex.org/W4313640622","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694"],"abstract_inverted_index":{"Recently,":[0],"attention-based":[1],"vision":[2,16,50,71,104],"transformers":[3,17,51,72,105],"have":[4],"achieved":[5],"significant":[6],"success":[7],"in":[8,26,106],"audio":[9,19],"classification":[10,20],"tasks.":[11],"While":[12],"most":[13],"cases":[14],"of":[15,34,103],"for":[18,69,100],"focus":[21],"on":[22,52],"achieving":[23],"satisfactory":[24],"scores":[25],"the":[27,53,74,101],"end,":[28],"there":[29],"is":[30,61],"still":[31],"a":[32,38,46,66],"lack":[33],"detailed":[35],"evaluation":[36],"from":[37],"practical":[39,98],"standpoint.":[40],"In":[41],"this":[42],"study,":[43,48],"we":[44],"conducted":[45],"comparative":[47,81],"boosting":[49],"ESC-50":[54],"dataset":[55],"step":[56],"by":[57],"step.":[58],"Our":[59,80],"goal":[60],"to":[62,73],"provide":[63],"practitioners":[64],"with":[65],"solid":[67],"foundation":[68],"adapting":[70],"general":[75],"Environmental":[76],"Sound":[77],"Classification":[78],"task.":[79],"study":[82],"encompasses":[83],"various":[84],"aspects,":[85],"including":[86],"model":[87,95],"setting,":[88],"data":[89],"augmentation,":[90],"cross-domain":[91],"transfer":[92],"learning,":[93],"and":[94],"pruning,":[96],"offering":[97],"insights":[99],"implementation":[102],"real-world":[107],"scenarios.":[108]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}