{"id":"https://openalex.org/W4401161376","doi":"https://doi.org/10.1587/transinf.2024edl8013","title":"A CNN-Based Feature Pyramid Segmentation Strategy for Acoustic Scene Classification","display_name":"A CNN-Based Feature Pyramid Segmentation Strategy for Acoustic Scene Classification","publication_year":2024,"publication_date":"2024-07-31","ids":{"openalex":"https://openalex.org/W4401161376","doi":"https://doi.org/10.1587/transinf.2024edl8013"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2024edl8013","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2024edl8013","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/8/E107.D_2024EDL8013/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/8/E107.D_2024EDL8013/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101685775","display_name":"Ji Xi","orcid":"https://orcid.org/0000-0001-8516-4984"},"institutions":[{"id":"https://openalex.org/I4210108723","display_name":"Changzhou Institute of Technology","ror":"https://ror.org/020mrfq61","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210108723"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji XI","raw_affiliation_strings":["School of Computer Information Engineering, Changzhou Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Information Engineering, Changzhou Institute of Technology","institution_ids":["https://openalex.org/I4210108723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052217750","display_name":"Yue Xie","orcid":"https://orcid.org/0000-0002-5750-5873"},"institutions":[{"id":"https://openalex.org/I2799736854","display_name":"Nanjing Institute of Technology","ror":"https://ror.org/00n6txq60","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799736854"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue XIE","raw_affiliation_strings":["School of Communication Engineering, Nanjing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Communication Engineering, Nanjing Institute of Technology","institution_ids":["https://openalex.org/I2799736854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067420587","display_name":"Pengxu JIANG","orcid":"https://orcid.org/0000-0003-1738-1455"},"institutions":[{"id":"https://openalex.org/I4210090971","display_name":"Southeast University","ror":"https://ror.org/00cf0ab87","country_code":"BD","type":"education","lineage":["https://openalex.org/I4210090971"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Pengxu JIANG","raw_affiliation_strings":["School of Information Science and Engineering, Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Southeast University","institution_ids":["https://openalex.org/I4210090971"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002942261","display_name":"Wei Jiang","orcid":"https://orcid.org/0000-0002-9240-5851"},"institutions":[{"id":"https://openalex.org/I4210108723","display_name":"Changzhou Institute of Technology","ror":"https://ror.org/020mrfq61","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210108723"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei JIANG","raw_affiliation_strings":["School of Computer Information Engineering, Changzhou Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Information Engineering, Changzhou Institute of Technology","institution_ids":["https://openalex.org/I4210108723"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11992027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"E107.D","issue":"8","first_page":"1093","last_page":"1096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9805999994277954,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.859815239906311},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8545864820480347},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7368159890174866},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6833420991897583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6664834022521973},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6475303173065186},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.640950620174408},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6017743349075317},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5839637517929077},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.5633509755134583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.859815239906311},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8545864820480347},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7368159890174866},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6833420991897583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6664834022521973},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6475303173065186},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.640950620174408},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6017743349075317},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5839637517929077},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.5633509755134583},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2024edl8013","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2024edl8013","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/8/E107.D_2024EDL8013/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2024edl8013","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1587/transinf.2024edl8013","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E107.D/8/E107.D_2024EDL8013/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401161376.pdf"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2109255472","https://openalex.org/W2883935097","https://openalex.org/W2897435617","https://openalex.org/W2937299048","https://openalex.org/W2962711843","https://openalex.org/W3162320900","https://openalex.org/W3171304840","https://openalex.org/W4246863316","https://openalex.org/W4285178505","https://openalex.org/W4318831574"],"related_works":["https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W3108503355","https://openalex.org/W4226420367","https://openalex.org/W2962876041","https://openalex.org/W3090555870","https://openalex.org/W3022820045","https://openalex.org/W2801655600","https://openalex.org/W2899027234","https://openalex.org/W3120400911"],"abstract_inverted_index":{"Currently,":[0],"a":[1,101,108,138],"significant":[2],"portion":[3],"of":[4,35,45,60,86,91,161,188,199],"acoustic":[5],"scene":[6],"categorization":[7],"(ASC)":[8],"research":[9],"is":[10,21,117,145],"centered":[11],"around":[12],"utilizing":[13,52,123],"Convolutional":[14],"Neural":[15],"Network":[16],"(CNN)":[17],"models.":[18],"This":[19],"preference":[20],"primarily":[22],"due":[23],"to":[24,27,75,174,176,184,195],"CNN's":[25],"ability":[26],"effectively":[28],"extract":[29],"time-frequency":[30],"information":[31,93],"from":[32],"audio":[33],"recordings":[34],"scenes":[36],"by":[37,51],"employing":[38],"spectrum":[39,54,70,79,124],"data":[40],"as":[41,126],"input.":[42],"The":[43,84,119,154,180],"expression":[44],"many":[46],"dimensions":[47],"can":[48,72],"be":[49,73,170],"achieved":[50],"2D":[53],"characteristics.":[55],"Nevertheless,":[56],"the":[57,61,69,76,127,130,149,159,186,189,197,200],"diverse":[58],"interpretations":[59],"same":[62],"object's":[63],"existence":[64],"in":[65,94,100,103],"different":[66,89,178],"positions":[67],"on":[68,115,137],"map":[71],"attributed":[74],"discrepancies":[77],"between":[78,88],"properties":[80],"and":[81,141,165,172,192],"picture":[82],"qualities.":[83],"lack":[85],"distinction":[87],"aspects":[90],"input":[92,128],"ASC-based":[95],"CNN":[96,116,150],"networks":[97],"may":[98],"result":[99],"decline":[102],"system":[104],"performance.":[105],"Considering":[106],"this,":[107],"feature":[109,144,163],"pyramid":[110],"segmentation":[111],"(FPS)":[112],"approach":[113,121],"based":[114,136],"proposed.":[118],"proposed":[120],"involves":[122],"features":[125,133,168],"for":[129,152],"model.":[131],"These":[132],"are":[134],"split":[135],"preset":[139],"scale,":[140],"each":[142],"segment-level":[143],"then":[146],"fed":[147,173],"into":[148],"network":[151],"learning.":[153],"SoftMax":[155],"classifier":[156],"will":[157,169],"receive":[158],"output":[160],"all":[162],"scales,":[164],"these":[166],"high-level":[167],"fused":[171],"it":[175],"categorize":[177],"scenarios.":[179],"experiment":[181],"provides":[182],"evidence":[183],"support":[185],"efficacy":[187],"FPS":[190],"strategy":[191],"its":[193],"potential":[194],"enhance":[196],"performance":[198],"ASC":[201],"system.":[202]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}