{"id":"https://openalex.org/W4414810227","doi":"https://doi.org/10.1002/itl2.70156","title":"Large Model\u2010Enhanced <scp>CNN</scp> \u2013Transformer Architecture for Adaptive Music Quality Classification in Wireless Communication Networks","display_name":"Large Model\u2010Enhanced <scp>CNN</scp> \u2013Transformer Architecture for Adaptive Music Quality Classification in Wireless Communication Networks","publication_year":2025,"publication_date":"2025-10-04","ids":{"openalex":"https://openalex.org/W4414810227","doi":"https://doi.org/10.1002/itl2.70156"},"language":"en","primary_location":{"id":"doi:10.1002/itl2.70156","is_oa":false,"landing_page_url":"https://doi.org/10.1002/itl2.70156","pdf_url":null,"source":{"id":"https://openalex.org/S4210238311","display_name":"Internet Technology Letters","issn_l":"2476-1508","issn":["2476-1508"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Internet Technology Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030259359","display_name":"Tianyu Chen","orcid":"https://orcid.org/0009-0005-3438-1467"},"institutions":[{"id":"https://openalex.org/I28777354","display_name":"Sejong University","ror":"https://ror.org/00aft1q37","country_code":"KR","type":"education","lineage":["https://openalex.org/I28777354"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Tianyu Chen","raw_affiliation_strings":["Sejong University  Seoul South Korea","Sejong University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Sejong University  Seoul South Korea","institution_ids":["https://openalex.org/I28777354"]},{"raw_affiliation_string":"Sejong University, Seoul, South Korea","institution_ids":["https://openalex.org/I28777354"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5030259359"],"corresponding_institution_ids":["https://openalex.org/I28777354"],"apc_list":{"value":2630,"currency":"USD","value_usd":2630},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33934663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"6","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":0.9986000061035156,"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":0.9986000061035156,"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":0.9767000079154968,"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":0.9550999999046326,"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/wireless","display_name":"Wireless","score":0.555899977684021},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5149999856948853},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5072000026702881},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.49810001254081726},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4571000039577484},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44839999079704285},{"id":"https://openalex.org/keywords/wireless-network","display_name":"Wireless network","score":0.43470001220703125},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4065000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681000232696533},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5149999856948853},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.49810001254081726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46869999170303345},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4571000039577484},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44839999079704285},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.43470001220703125},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4065000116825104},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.38580000400543213},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3264000117778778},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C24590314","wikidata":"https://www.wikidata.org/wiki/Q336038","display_name":"Wireless sensor network","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.25850000977516174},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/itl2.70156","is_oa":false,"landing_page_url":"https://doi.org/10.1002/itl2.70156","pdf_url":null,"source":{"id":"https://openalex.org/S4210238311","display_name":"Internet Technology Letters","issn_l":"2476-1508","issn":["2476-1508"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Internet Technology Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W3131876117","https://openalex.org/W3134483411","https://openalex.org/W4293732132","https://openalex.org/W4311623199","https://openalex.org/W4400127166","https://openalex.org/W4400768137","https://openalex.org/W4406691611","https://openalex.org/W4408519584","https://openalex.org/W4411011555"],"related_works":[],"abstract_inverted_index":{"ABSTRACT":[0],"This":[1],"letter":[2],"presents":[3],"an":[4],"enhanced":[5],"convolutional":[6],"neural":[7],"network":[8],"(CNN)\u2013transformer":[9],"architecture":[10],"integrated":[11],"with":[12,39,134],"large":[13],"model":[14,129],"(LM)":[15],"capabilities":[16],"for":[17,51,145],"adaptive":[18],"music":[19,64,88,116,146],"quality":[20,117,147],"classification":[21,58,118,132],"in":[22,87,149],"wireless":[23,92,150],"communication":[24],"networks":[25,82],"(WCNs).":[26],"The":[27],"proposed":[28],"approach":[29],"combines":[30],"the":[31,40,63,115,123],"global":[32],"feature":[33,71,111],"learning":[34],"strength":[35],"of":[36,45],"transformer":[37,81],"encoders":[38],"local":[41],"pattern":[42],"recognition":[43],"abilities":[44],"CNNs":[46],"while":[47,94],"leveraging":[48],"LM":[49],"knowledge":[50],"improved":[52],"audio":[53,101],"signal":[54,65],"understanding.":[55],"To":[56],"enhance":[57],"accuracy,":[59,133],"we":[60,74,104],"first":[61],"preprocess":[62],"data":[66],"through":[67],"channel\u2010aware":[68],"normalization":[69],"and":[70,113,137],"standardization.":[72],"Subsequently,":[73],"employ":[75],"a":[76],"multi\u2010head":[77],"attention":[78],"mechanism":[79],"from":[80],"to":[83,98,108],"capture":[84],"long\u2010range":[85],"dependencies":[86],"features":[89],"affected":[90],"by":[91],"transmission":[93],"utilizing":[95],"CNN":[96],"layers":[97],"extract":[99],"localized":[100],"patterns.":[102],"Finally,":[103],"incorporate":[105],"inception":[106],"modules":[107],"achieve":[109],"multi\u2010scale":[110],"fusion":[112],"complete":[114],"task.":[119],"Experimental":[120],"validation":[121],"on":[122],"MusicCaps":[124],"dataset":[125],"demonstrates":[126],"that":[127],"our":[128],"achieves":[130],"97.8%":[131],"precision,":[135],"recall,":[136],"F1\u2010score":[138],"all":[139],"exceeding":[140],"97.5%,":[141],"outperforming":[142],"existing":[143],"approaches":[144],"assessment":[148],"environments.":[151]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}