{"id":"https://openalex.org/W7127040883","doi":"https://doi.org/10.1145/3784833.3784885","title":"Lightweight Environmental Sound Classification via Local Temporal Graph Enhancement","display_name":"Lightweight Environmental Sound Classification via Local Temporal Graph Enhancement","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7127040883","doi":"https://doi.org/10.1145/3784833.3784885"},"language":null,"primary_location":{"id":"doi:10.1145/3784833.3784885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784885","pdf_url":null,"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 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3784833.3784885","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124715890","display_name":"Haihua Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haihua Zhu","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124748798","display_name":"Xiaoyu Li","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Li","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5124715890"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.70743306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"166","last_page":"170"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.76910001039505,"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":0.76910001039505,"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/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.09960000216960907,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11692","display_name":"Noise Effects and Management","score":0.026499999687075615,"subfield":{"id":"https://openalex.org/subfields/3616","display_name":"Speech and Hearing"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6146000027656555},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5860000252723694},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49779999256134033},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.375},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3555000126361847},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3190000057220459},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2987000048160553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7186999917030334},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6146000027656555},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5860000252723694},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49779999256134033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48500001430511475},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31290000677108765},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.25780001282691956},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3784833.3784885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784885","pdf_url":null,"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 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3784833.3784885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3784833.3784885","pdf_url":null,"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 2025 11th International Conference on Communication and Information Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7902730107307434,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1972567154","https://openalex.org/W2038484192","https://openalex.org/W2052666245","https://openalex.org/W2102625004","https://openalex.org/W2119821739","https://openalex.org/W2122111042","https://openalex.org/W2157331557","https://openalex.org/W2509065397","https://openalex.org/W2593116425","https://openalex.org/W2751841560","https://openalex.org/W3094550259","https://openalex.org/W3095753917","https://openalex.org/W3161026535","https://openalex.org/W3196974791","https://openalex.org/W4282565351","https://openalex.org/W4372266552","https://openalex.org/W4392903801","https://openalex.org/W4402673709"],"related_works":[],"abstract_inverted_index":{"Environmental":[0],"sound":[1],"classification":[2],"(ESC)":[3],"is":[4],"an":[5],"important":[6],"task":[7],"for":[8],"intelligent":[9],"perception":[10],"systems":[11,125],"with":[12],"applications":[13],"in":[14],"public":[15],"safety,":[16],"smart":[17],"cities,":[18],"and":[19,35,59,83,97,117],"healthcare.":[20],"Existing":[21],"methods":[22],"often":[23],"rely":[24],"on":[25,101,115,119],"large-scale":[26],"pretraining":[27],"or":[28,122],"complex":[29],"architectures,":[30],"which":[31],"limit":[32],"their":[33],"efficiency":[34],"practicality.":[36],"To":[37],"address":[38],"this":[39],"issue,":[40],"we":[41],"propose":[42],"a":[43,55,60,70],"lightweight":[44,56,77],"ESC":[45],"framework":[46],"that":[47],"integrates":[48],"offline":[49,67],"large":[50],"pre-trained":[51],"model":[52],"acoustic":[53],"features,":[54],"sequence":[57,81],"classifier,":[58],"local":[61],"temporal":[62,89],"graph":[63,85],"enhancement":[64],"module.":[65],"The":[66,76],"features":[68],"provide":[69],"stable":[71],"representation":[72],"without":[73],"costly":[74],"fine-tuning.":[75],"classifier":[78],"enables":[79],"efficient":[80],"modeling,":[82],"the":[84,107],"module":[86],"captures":[87],"fine-grained":[88],"dependencies":[90],"while":[91,126],"enhancing":[92],"robustness":[93],"to":[94],"overlapping":[95],"events":[96],"noise.":[98],"Experimental":[99],"results":[100],"two":[102],"widely":[103],"used":[104],"benchmarks":[105],"demonstrate":[106],"effectiveness":[108],"of":[109],"our":[110],"approach,":[111],"achieving":[112],"96.7%":[113],"accuracy":[114],"ESC-50":[116],"90.0%":[118],"UrbanSound8K,":[120],"surpassing":[121],"matching":[123],"state-of-the-art":[124],"using":[127],"substantially":[128],"fewer":[129],"computational":[130],"resources.":[131]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-02-03T00:00:00"}