{"id":"https://openalex.org/W2802272416","doi":"https://doi.org/10.1109/icassp.2018.8461396","title":"Maximal Figure-of-Merit Embedding for Multi-Label Audio Classification","display_name":"Maximal Figure-of-Merit Embedding for Multi-Label Audio Classification","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2802272416","doi":"https://doi.org/10.1109/icassp.2018.8461396","mag":"2802272416"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5083404931","display_name":"Ivan Kukanov","orcid":"https://orcid.org/0000-0003-4052-2754"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ivan Kukanov","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037259225","display_name":"Ville Hautam\u00e4ki","orcid":"https://orcid.org/0000-0002-5885-0003"},"institutions":[{"id":"https://openalex.org/I175532246","display_name":"University of Eastern Finland","ror":"https://ror.org/00cyydd11","country_code":"FI","type":"education","lineage":["https://openalex.org/I175532246"]},{"id":"https://openalex.org/I4210107997","display_name":"Finland University","ror":"https://ror.org/014rks409","country_code":"FI","type":"education","lineage":["https://openalex.org/I4210107997"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ville Hautamaki","raw_affiliation_strings":["School of Computing, University of Eastern Finland, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, University of Eastern Finland, Finland","institution_ids":["https://openalex.org/I4210107997","https://openalex.org/I175532246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3325,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.54852376,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"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":1.0,"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":0.9987999796867371,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9887999892234802,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261437177658081},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.707621157169342},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.6245500445365906},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.6036779284477234},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.585654616355896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5605568885803223},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5454190969467163},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5164085030555725},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4897001087665558},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4741853177547455},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47129881381988525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3817272186279297},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3580360412597656},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1836702823638916},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.14762979745864868}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261437177658081},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.707621157169342},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.6245500445365906},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.6036779284477234},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.585654616355896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5605568885803223},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5454190969467163},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5164085030555725},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4897001087665558},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4741853177547455},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47129881381988525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3817272186279297},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3580360412597656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1836702823638916},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.14762979745864868},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/15","score":0.4099999964237213,"display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W168164358","https://openalex.org/W1924770834","https://openalex.org/W2009086942","https://openalex.org/W2009758992","https://openalex.org/W2013477326","https://openalex.org/W2023840808","https://openalex.org/W2055667362","https://openalex.org/W2119466907","https://openalex.org/W2130640900","https://openalex.org/W2132083787","https://openalex.org/W2147917435","https://openalex.org/W2176412452","https://openalex.org/W2403438050","https://openalex.org/W2408239454","https://openalex.org/W2566935005","https://openalex.org/W2586846985","https://openalex.org/W2591013610","https://openalex.org/W2914312680","https://openalex.org/W2951829787","https://openalex.org/W2963285578","https://openalex.org/W2963451564","https://openalex.org/W2971670255","https://openalex.org/W3098357269","https://openalex.org/W4232093537","https://openalex.org/W6640212811","https://openalex.org/W6664478996","https://openalex.org/W6678009824","https://openalex.org/W6679386718","https://openalex.org/W6685562342","https://openalex.org/W6727174287","https://openalex.org/W6732967411","https://openalex.org/W6764454516","https://openalex.org/W6785157504"],"related_works":["https://openalex.org/W4385957115","https://openalex.org/W2061372042","https://openalex.org/W3047779762","https://openalex.org/W3037097571","https://openalex.org/W3094220251","https://openalex.org/W3080935557","https://openalex.org/W4388821232","https://openalex.org/W2607836359","https://openalex.org/W4308016144","https://openalex.org/W3134134808"],"abstract_inverted_index":{"This":[0],"work":[1],"tackles":[2],"the":[3,6,53,78,86,100,114],"problem":[4],"of":[5,31,70,91],"domestic":[7],"audio":[8,16],"tagging":[9],"or":[10,21],"environmental":[11],"sound":[12],"classification,":[13],"where":[14],"one":[15,20],"recording":[17],"can":[18],"contain":[19],"more":[22,107],"acoustic":[23],"events":[24],"and":[25,105],"a":[26,41],"recognizer":[27],"should":[28],"output":[29,49],"all":[30],"those":[32],"tags.":[33],"A":[34],"baseline":[35,115],"model":[36,116],"for":[37,67],"this":[38,68,73],"task":[39],"is":[40],"convolutional":[42],"recurrent":[43],"neural":[44],"network":[45],"(CRNN)":[46],"with":[47,117],"sigmoid":[48],"nodes":[50],"optimized":[51],"using":[52],"binary":[54,118],"cross-entropy":[55],"objective.":[56],"Traditional":[57],"error":[58,93],"metrics,":[59],"such":[60],"as":[61],"classification":[62],"error,":[63],"are":[64],"not":[65],"suitable":[66],"type":[69],"task.":[71],"In":[72],"work,":[74],"we":[75],"show":[76],"that":[77],"maximal":[79],"figure-of-merit":[80],"(MFoM)":[81],"framework":[82],"helps":[83],"to":[84,113],"separate":[85],"multi-label":[87],"classes":[88],"in":[89],"terms":[90],"equal":[92],"rate":[94],"(EER).":[95],"We":[96],"embed":[97],"MFoM":[98],"into":[99],"deep":[101],"learning":[102],"objective":[103],"function":[104],"gain":[106],"than":[108],"9%":[109],"relative":[110],"improvement,":[111],"compared":[112],"cross-entropy.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}