{"id":"https://openalex.org/W2917294828","doi":"https://doi.org/10.1109/icassp.2019.8683774","title":"Semi-supervised Triplet Loss Based Learning of Ambient Audio Embeddings","display_name":"Semi-supervised Triplet Loss Based Learning of Ambient Audio Embeddings","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2917294828","doi":"https://doi.org/10.1109/icassp.2019.8683774","mag":"2917294828"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018442184","display_name":"Nicolas Turpault","orcid":null},"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/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Turpault","raw_affiliation_strings":["Université de Lorraine, CNRS, Nancy, F-54000, France","Universit\u00e9 de Lorraine, CNRS, Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Nancy, F-54000, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Nancy, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Romain Serizel","orcid":null},"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/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":["Université de Lorraine, CNRS, Nancy, F-54000, France","Universit\u00e9 de Lorraine, CNRS, Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Nancy, F-54000, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Nancy, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065635001","display_name":"Emmanuel Vincent","orcid":"https://orcid.org/0000-0002-0183-7289"},"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/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Emmanuel Vincent","raw_affiliation_strings":["Université de Lorraine, CNRS, Nancy, F-54000, France","Universit\u00e9 de Lorraine, CNRS, Nancy, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Université de Lorraine, CNRS, Nancy, F-54000, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]},{"raw_affiliation_string":"Universit\u00e9 de Lorraine, CNRS, Nancy, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I90183372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"760","last_page":"764"},"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":0.9998000264167786,"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":0.9922999739646912,"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/computer-science","display_name":"Computer science","score":0.7558125257492065},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7241120338439941},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6495351791381836},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6470563411712646},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.612760066986084},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6062220931053162},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5600066184997559},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5461041927337646},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5354113578796387},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5278639197349548},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.5031697154045105},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4989006519317627},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4984581470489502},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4695715606212616},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43304044008255005},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42162764072418213}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7558125257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7241120338439941},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6495351791381836},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6470563411712646},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.612760066986084},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6062220931053162},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5600066184997559},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5461041927337646},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5354113578796387},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5278639197349548},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.5031697154045105},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4989006519317627},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4984581470489502},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4695715606212616},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43304044008255005},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42162764072418213},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5611049820","display_name":"Learning to understand audio scenes","funder_award_id":"ANR-18-CE23-0020","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W310392861","https://openalex.org/W1496704041","https://openalex.org/W1975517671","https://openalex.org/W2096733369","https://openalex.org/W2106241685","https://openalex.org/W2107789863","https://openalex.org/W2171590421","https://openalex.org/W2561826558","https://openalex.org/W2591719913","https://openalex.org/W2593116425","https://openalex.org/W2622742434","https://openalex.org/W2646581507","https://openalex.org/W2759976799","https://openalex.org/W2767754137","https://openalex.org/W2768202427","https://openalex.org/W2770119437","https://openalex.org/W2771361008","https://openalex.org/W2884011836","https://openalex.org/W2884535146","https://openalex.org/W2962850179","https://openalex.org/W2963702081","https://openalex.org/W2963723765","https://openalex.org/W2963956526","https://openalex.org/W3099206234","https://openalex.org/W3104866538","https://openalex.org/W4289329167","https://openalex.org/W4289564011","https://openalex.org/W6610969475","https://openalex.org/W6676071220","https://openalex.org/W6739564277","https://openalex.org/W6745214240","https://openalex.org/W6746124584","https://openalex.org/W6746278845","https://openalex.org/W6749396741","https://openalex.org/W6753516609","https://openalex.org/W6753583920"],"related_works":["https://openalex.org/W3148060700","https://openalex.org/W4312414840","https://openalex.org/W34092691","https://openalex.org/W2096363773","https://openalex.org/W2794908468","https://openalex.org/W2531570999","https://openalex.org/W4206276646","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W2042184006"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"are":[3,93,95],"particularly":[4],"useful":[5],"to":[6,38,48,102,119],"learn":[7],"relevant":[8],"representations":[9],"from":[10],"data.":[11,137],"Recent":[12],"studies":[13],"have":[14,34,49],"demonstrated":[15],"the":[16,30,85,103,108,112,128,131,141,150,159,165],"potential":[17],"of":[18,29,81,133,161],"unsupervised":[19,64,122],"representation":[20,74,123],"learning":[21,70,75,124],"for":[22,88],"ambient":[23],"sound":[24],"analysis":[25],"using":[26,149],"various":[27],"flavors":[28,80],"triplet":[31,67],"loss.":[32],"They":[33],"compared":[35],"this":[36,60,82,162],"approach":[37,118],"supervised":[39,66,120],"learning.":[40],"However,":[41],"in":[42,111],"real":[43],"situations,":[44],"it":[45],"is":[46],"common":[47],"a":[50,55,72,100],"small":[51],"labeled":[52,134],"dataset":[53],"and":[54,65,121,135,156],"large":[56],"unlabeled":[57,94,136],"one.":[58],"In":[59],"paper,":[61],"we":[62,157],"combine":[63],"loss":[68],"based":[69],"into":[71],"semi-supervised":[73],"approach.":[76],"We":[77,115,138],"propose":[78],"two":[79],"approach,":[83],"whereby":[84],"positive":[86],"samples":[87],"those":[89],"triplets":[90],"whose":[91],"anchors":[92],"obtained":[96],"either":[97],"by":[98,106],"applying":[99],"transformation":[101],"anchor,":[104],"or":[105],"selecting":[107],"nearest":[109],"sample":[110],"training":[113],"set.":[114],"compare":[116],"our":[117],"as":[125,127],"well":[126],"ratio":[129,163],"between":[130],"amount":[132],"evaluate":[139],"all":[140],"above":[142],"approaches":[143],"on":[144,164],"an":[145],"audio":[146],"tagging":[147,166],"task":[148],"DCASE":[151],"2018":[152],"Task":[153],"4":[154],"dataset,":[155],"show":[158],"impact":[160],"performance.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}