{"id":"https://openalex.org/W2977846024","doi":"https://doi.org/10.1109/ijcnn.2019.8852143","title":"Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection","display_name":"Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W2977846024","doi":"https://doi.org/10.1109/ijcnn.2019.8852143","mag":"2977846024"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2019.8852143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"preprint","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/A5088037163","display_name":"Thomas Pellegrini","orcid":"https://orcid.org/0000-0001-8984-1399"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Thomas Pellegrini","raw_affiliation_strings":["IRIT, Universit\u00e9 Paul Sabatier, CNRS, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"IRIT, Universit\u00e9 Paul Sabatier, CNRS, Toulouse, France","institution_ids":["https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012999699","display_name":"L\u00e9o Cances","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119061","display_name":"Institut de Recherche en Informatique de Toulouse","ror":"https://ror.org/01rx4qw44","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I205747304","https://openalex.org/I205747304","https://openalex.org/I4210119061","https://openalex.org/I4387153255","https://openalex.org/I4405258862","https://openalex.org/I4405258862"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I134560555","display_name":"Universit\u00e9 Toulouse III - Paul Sabatier","ror":"https://ror.org/02v6kpv12","country_code":"FR","type":"education","lineage":["https://openalex.org/I134560555","https://openalex.org/I4405258862"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Leo Cances","raw_affiliation_strings":["IRIT, Universit\u00e9 Paul Sabatier, CNRS, Toulouse, France"],"affiliations":[{"raw_affiliation_string":"IRIT, Universit\u00e9 Paul Sabatier, CNRS, Toulouse, France","institution_ids":["https://openalex.org/I134560555","https://openalex.org/I4210119061","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5088037163"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210119061","https://openalex.org/I134560555"],"apc_list":null,"apc_paid":null,"fwci":1.805981,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86194419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"220","issue":null,"first_page":"1","last_page":"8"},"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":0.9955999851226807,"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":0.9757999777793884,"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/similarity","display_name":"Similarity (geometry)","score":0.6934303641319275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6711990833282471},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6691431999206543},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5830798149108887},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5602006912231445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.551701545715332},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.5480204224586487},{"id":"https://openalex.org/keywords/sound-analysis","display_name":"Sound analysis","score":0.5036737322807312},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.49151167273521423},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4894343912601471},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.485840767621994},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.4845942258834839},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4603879451751709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4474734961986542},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.4382171928882599},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32171928882598877},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09444636106491089}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6934303641319275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711990833282471},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6691431999206543},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5830798149108887},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5602006912231445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.551701545715332},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.5480204224586487},{"id":"https://openalex.org/C2984030306","wikidata":"https://www.wikidata.org/wiki/Q4819857","display_name":"Sound analysis","level":2,"score":0.5036737322807312},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.49151167273521423},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4894343912601471},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.485840767621994},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4845942258834839},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4603879451751709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4474734961986542},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.4382171928882599},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32171928882598877},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09444636106491089},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2019.8852143","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2019.8852143","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6499999761581421,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2010792435","https://openalex.org/W2024060531","https://openalex.org/W2091746061","https://openalex.org/W2110119381","https://openalex.org/W2114747788","https://openalex.org/W2354870669","https://openalex.org/W2567070169","https://openalex.org/W2593116425","https://openalex.org/W2807977755","https://openalex.org/W2884011836","https://openalex.org/W2887437386","https://openalex.org/W2963723765","https://openalex.org/W2963970792","https://openalex.org/W3096841046","https://openalex.org/W3103314642","https://openalex.org/W4289329167","https://openalex.org/W6731370813","https://openalex.org/W6734260513","https://openalex.org/W6753516609","https://openalex.org/W6754295504","https://openalex.org/W6785333363"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W4388925068","https://openalex.org/W4390905756","https://openalex.org/W2135277937","https://openalex.org/W3099922831","https://openalex.org/W4385571733","https://openalex.org/W4223433861","https://openalex.org/W4388419449","https://openalex.org/W3080936386","https://openalex.org/W2909589791"],"abstract_inverted_index":{"The":[0,54,68],"design":[1],"of":[2,14,23,59,87,138,162,179,188,196],"new":[3],"methods":[4],"and":[5,26,135,182,198],"models":[6],"when":[7],"only":[8],"weakly-labeled":[9],"data":[10],"are":[11],"available":[12,51],"is":[13,50,70],"paramount":[15],"importance":[16],"in":[17,42,111,173,192,231],"order":[18],"to":[19,120,204,223],"reduce":[20],"the":[21,27,43,88,92,99,132,136,139,154,160,163,169,174,186,207,217,224,232],"costs":[22],"manual":[24],"annotation":[25],"considerable":[28],"human":[29],"effort":[30],"associated":[31],"with":[32,149,234],"it.":[33],"In":[34],"this":[35,150],"work,":[36],"we":[37,113,152],"address":[38],"Sound":[39],"Event":[40],"Detection":[41],"case":[44],"where":[45],"a":[46,115,126,189,193,213,235],"weakly":[47],"annotated":[48],"dataset":[49],"for":[52],"training.":[53,167],"weak":[55,133],"annotations":[56],"provide":[57,65],"tags":[58],"audio":[60,73],"events":[61],"but":[62],"do":[63],"not":[64,205],"temporal":[66],"boundaries.":[67],"objective":[69],"twofold:":[71],"1)":[72],"tagging,":[74],"i.e.":[75,85],"multi-label":[76],"classification":[77],"at":[78,123],"recording":[79],"level,":[80],"2)":[81],"sound":[82,144,184],"event":[83,89],"detection,":[84],"localization":[86,194],"boundaries":[90],"within":[91],"recordings.":[93],"This":[94],"work":[95],"focuses":[96],"mainly":[97],"on":[98,131,216],"second":[100,230],"objective.":[101],"We":[102],"explore":[103],"an":[104],"approach":[105,227],"inspired":[106],"by":[107,156],"Multiple":[108],"Instance":[109],"Learning,":[110],"which":[112],"train":[114],"convolutional":[116],"recurrent":[117],"neural":[118],"network":[119],"give":[121],"predictions":[122,161],"frame-level,":[124],"using":[125,206],"custom":[127],"loss":[128],"function":[129],"based":[130],"labels":[134],"statistics":[137],"frame-based":[140],"predictions.":[141],"Since":[142],"some":[143],"classes":[145,165],"cannot":[146],"be":[147],"distinguished":[148],"approach,":[151],"improve":[153],"method":[155],"penalizing":[157],"similarity":[158],"between":[159],"positive":[164],"during":[166],"On":[168],"test":[170],"set":[171],"used":[172],"DCASE":[175],"2018":[176],"challenge,":[177],"consisting":[178],"288":[180],"recordings":[181],"10":[183],"classes,":[185],"addition":[187],"penalty":[190],"resulted":[191],"F-score":[195,215],"34.75%,":[197],"brought":[199],"10%":[200],"relative":[201],"improvement":[202],"compared":[203],"penalty.":[208],"Our":[209],"best":[210],"model":[211],"achieved":[212],"26.20%":[214],"DCASE-2018":[218],"official":[219],"Eval":[220],"subset":[221],"close":[222],"10-system":[225],"ensemble":[226],"that":[228],"ranked":[229],"challenge":[233],"29.9%":[236],"F-score.":[237]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}