{"id":"https://openalex.org/W4410772444","doi":"https://doi.org/10.1145/3727353.3727361","title":"ECSR-Net: An Efficient Classroom Speech Recognition Network Based on Convolutional Neural Networks with Mixup Attention","display_name":"ECSR-Net: An Efficient Classroom Speech Recognition Network Based on Convolutional Neural Networks with Mixup Attention","publication_year":2025,"publication_date":"2025-01-10","ids":{"openalex":"https://openalex.org/W4410772444","doi":"https://doi.org/10.1145/3727353.3727361"},"language":"en","primary_location":{"id":"doi:10.1145/3727353.3727361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727361","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727361","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 4th International Conference on Big Data, Information and Computer Network","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727361","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052537761","display_name":"Xiaofeng Yuan","orcid":"https://orcid.org/0009-0008-2294-2396"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Yuan","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0008-2294-2396","affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106477685","display_name":"Sizhu Wang","orcid":"https://orcid.org/0009-0002-8230-929X"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sizhu Wang","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0002-8230-929X","affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qi Chen","orcid":"https://orcid.org/0009-0000-8025-8316"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["School of Artificial Intelligence, South China Normal University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0000-8025-8316","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, South China Normal University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100568269","display_name":"Zhang Weizhong","orcid":"https://orcid.org/0009-0004-8051-1528"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhong Zhang","raw_affiliation_strings":["School of Artificial Intelligence, South China Normal University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0004-8051-1528","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, South China Normal University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077259031","display_name":"Yingshan Shen","orcid":"https://orcid.org/0000-0002-2482-7614"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingshan Shen","raw_affiliation_strings":["School of Computer Science, South China Normal University, Guangzhou, Guangdong, China"],"raw_orcid":"https://orcid.org/0000-0002-2482-7614","affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9955000281333923,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9940999746322632,"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/T11309","display_name":"Music and Audio Processing","score":0.9890000224113464,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7763156890869141},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7633819580078125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6503204703330994},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5194886922836304},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.4614078104496002},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.43058595061302185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40389537811279297},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34503114223480225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06756362318992615}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7763156890869141},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633819580078125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6503204703330994},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5194886922836304},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.4614078104496002},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.43058595061302185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40389537811279297},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34503114223480225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06756362318992615},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3727353.3727361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727361","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727361","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 4th International Conference on Big Data, Information and Computer Network","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3727353.3727361","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3727353.3727361","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3727353.3727361","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 4th International Conference on Big Data, Information and Computer Network","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410772444.pdf","grobid_xml":"https://content.openalex.org/works/W4410772444.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2075997786","https://openalex.org/W2592667291","https://openalex.org/W3149547750","https://openalex.org/W3177525997","https://openalex.org/W4385454139","https://openalex.org/W4387540041","https://openalex.org/W4390950161","https://openalex.org/W6600566992","https://openalex.org/W6602646189"],"related_works":["https://openalex.org/W1584270863","https://openalex.org/W2603525251","https://openalex.org/W2085961337","https://openalex.org/W3113777316","https://openalex.org/W2386241395","https://openalex.org/W4246541945","https://openalex.org/W2357447513","https://openalex.org/W2107201395","https://openalex.org/W2381790306","https://openalex.org/W4241378172"],"abstract_inverted_index":{"Effective":[0],"classroom":[1,26,116],"teaching":[2],"requires":[3],"active":[4],"interactions":[5],"between":[6],"teachers":[7],"and":[8,83,93,110,134,152],"students,":[9],"which":[10,34,57],"can":[11],"be":[12],"objectively":[13],"analyzed":[14],"using":[15],"the":[16,46,50,76,159,174],"Student-Teacher":[17],"(S-T)":[18],"analysis":[19,27,32],"method.":[20],"This":[21],"paper":[22],"preposes":[23],"an":[24],"automated":[25],"method":[28],"based":[29],"on":[30],"S-T":[31],"method,":[33],"employs":[35],"a":[36,59,97,164],"deep":[37],"learning":[38],"model":[39],"to":[40,71],"process":[41],"audio":[42],"data":[43],"collected":[44],"in":[45,121],"classroom.":[47],"We":[48,95],"design":[49],"Efficient":[51,84],"Classroom":[52],"Speech":[53],"Recognition":[54],"Network":[55,63],"(ECSR-Net),":[56],"is":[58,168],"lightweight":[60],"Convoluntional":[61],"Neural":[62],"(CNN)":[64],"with":[65],"mixup":[66],"attention.":[67],"Fewer":[68],"convolutional":[69],"layers":[70],"prevent":[72],"overfitting":[73],"by":[74],"minimizing":[75],"loss":[77],"of":[78,156,173],"vertical":[79],"information,":[80],"Squeeze-and-Excitation":[81],"(SE)":[82],"Local":[85],"Attention":[86],"(ELA)":[87],"module":[88],"optimizing":[89],"feature":[90],"representation":[91],"globally":[92],"locally.":[94],"construct":[96],"multi-label":[98],"dataset":[99],"that":[100,145,167,172],"includes":[101],"three":[102],"speech":[103,109],"modes:":[104],"teacher":[105],"speech,":[106,113],"single":[107],"student":[108,112],"multiple":[111,124],"sourced":[114],"from":[115,138],"recordings":[117],"across":[118,126],"various":[119,127],"regions":[120],"China,":[122],"covering":[123],"subjects":[125],"elementary":[128],"grades.":[129],"Then":[130],"we":[131],"extract":[132],"static":[133],"dynamic":[135],"log-Mel":[136],"spectrogram":[137],"original":[139],"audio.":[140],"The":[141],"experimental":[142],"results":[143],"demonstrate":[144],"ECSR-Net":[146],"achieves":[147],"higher":[148],"accuracy,":[149],"precision,":[150],"recall,":[151],"especially":[153],"F1":[154],"score":[155],"0.904,":[157],"surpassing":[158],"optimal":[160],"performance,":[161],"while":[162],"maintaining":[163],"parameter":[165],"count":[166],"less":[169],"than":[170],"twice":[171],"CNN":[175],"baseline":[176],"model.":[177]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}