{"id":"https://openalex.org/W4392911143","doi":"https://doi.org/10.1109/icassp48485.2024.10447743","title":"Contrastive Loss Based Frame-Wise Feature Disentanglement for Polyphonic Sound Event Detection","display_name":"Contrastive Loss Based Frame-Wise Feature Disentanglement for Polyphonic Sound Event Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392911143","doi":"https://doi.org/10.1109/icassp48485.2024.10447743"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5053853990","display_name":"Yadong Guan","orcid":"https://orcid.org/0009-0002-6031-9892"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yadong Guan","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101508830","display_name":"Jiqing Han","orcid":"https://orcid.org/0000-0002-4297-4300"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiqing Han","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057908066","display_name":"Hongwei Song","orcid":"https://orcid.org/0000-0003-1928-8182"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Song","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103037548","display_name":"Wenjie Song","orcid":"https://orcid.org/0000-0001-9474-6951"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Song","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041058909","display_name":"Guibin Zheng","orcid":"https://orcid.org/0000-0002-4280-5224"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guibin Zheng","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101846141","display_name":"Tieran Zheng","orcid":"https://orcid.org/0009-0006-5179-0278"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tieran Zheng","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026346396","display_name":"Yongjun He","orcid":"https://orcid.org/0000-0002-5156-651X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjun He","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5053853990"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":1.5001,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80822358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1021","last_page":"1025"},"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/T13996","display_name":"Diverse Musicological Studies","score":0.9919999837875366,"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"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9894999861717224,"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/polyphony","display_name":"Polyphony","score":0.7911486625671387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.728145956993103},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6607810258865356},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.656670331954956},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.656242311000824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6163483262062073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5042213201522827},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44236311316490173},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4257437288761139},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3347550630569458},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32773303985595703},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1426098644733429},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13091447949409485},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08389011025428772},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.04981181025505066}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.7911486625671387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.728145956993103},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6607810258865356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.656670331954956},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.656242311000824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6163483262062073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5042213201522827},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44236311316490173},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4257437288761139},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3347550630569458},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32773303985595703},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1426098644733429},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13091447949409485},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08389011025428772},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.04981181025505066},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447743","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6499999761581421}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2591013610","https://openalex.org/W2922509574","https://openalex.org/W3006275583","https://openalex.org/W3015190346","https://openalex.org/W3084086733","https://openalex.org/W3162400960","https://openalex.org/W3182910640","https://openalex.org/W3199127113","https://openalex.org/W3203468141","https://openalex.org/W4221149441","https://openalex.org/W4225324023","https://openalex.org/W4283816693","https://openalex.org/W4289521424","https://openalex.org/W4296068822","https://openalex.org/W4297797459","https://openalex.org/W4297808394","https://openalex.org/W4312097369","https://openalex.org/W4313679745","https://openalex.org/W4321374470","https://openalex.org/W4372263379","https://openalex.org/W4375868937","https://openalex.org/W4384702789","https://openalex.org/W6745136726","https://openalex.org/W6774314701","https://openalex.org/W6781130467","https://openalex.org/W6844194202","https://openalex.org/W6848190777"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"Overlapping":[0],"sound":[1,11],"events":[2,31],"are":[3],"ubiquitous":[4],"in":[5],"real-world":[6],"environments,":[7],"but":[8],"existing":[9],"end-to-end":[10],"event":[12],"detection":[13],"(SED)":[14],"methods":[15,28],"still":[16],"struggle":[17],"to":[18,54,64,131],"detect":[19],"them":[20],"effectively.":[21],"A":[22],"critical":[23],"reason":[24],"is":[25,114],"that":[26,74,105,123],"these":[27,75],"represent":[29],"overlapping":[30],"using":[32],"shared":[33],"and":[34,96],"entangled":[35],"frame-wise":[36,67,90,99,120],"features,":[37],"which":[38],"degrades":[39],"the":[40,45,66,86,93,106,111,139],"feature":[41,51,76,133],"discrimination.":[42],"To":[43,72],"solve":[44],"problem,":[46],"we":[47,60,84,116],"propose":[48,97,117],"a":[49,56,98,118],"disentangled":[50],"learning":[52],"framework":[53],"learn":[55,65],"category-specific":[57],"representation.":[58],"Specifically,":[59],"employ":[61],"different":[62],"projectors":[63],"features":[68,91],"for":[69],"each":[70],"category.":[71],"ensure":[73],"does":[77],"not":[78],"contain":[79],"information":[80,88],"of":[81,128,141],"other":[82],"categories,":[83],"maximize":[85],"common":[87],"between":[89],"within":[92],"same":[94],"category":[95],"contrastive":[100,121],"loss.":[101],"In":[102],"addition,":[103],"considering":[104],"labeled":[107],"data":[108,130],"used":[109],"by":[110],"proposed":[112],"method":[113],"limited,":[115],"semi-supervised":[119],"loss":[122],"can":[124],"leverage":[125],"large":[126],"amounts":[127],"unlabeled":[129],"achieve":[132],"disentanglement.":[134],"The":[135],"experimental":[136],"results":[137],"demonstrate":[138],"effectiveness":[140],"our":[142],"method.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"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"}
