{"id":"https://openalex.org/W3115751294","doi":"https://doi.org/10.23919/eusipco47968.2020.9287743","title":"Analyzing the Potential of Pre-Trained Embeddings for Audio Classification Tasks","display_name":"Analyzing the Potential of Pre-Trained Embeddings for Audio Classification Tasks","publication_year":2020,"publication_date":"2020-12-18","ids":{"openalex":"https://openalex.org/W3115751294","doi":"https://doi.org/10.23919/eusipco47968.2020.9287743","mag":"3115751294"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco47968.2020.9287743","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","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/A5068929948","display_name":"Sascha Grollmisch","orcid":"https://orcid.org/0000-0001-9703-110X"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sascha Grollmisch","raw_affiliation_strings":["TU Ilmenau,Institute for Media Technology,Ilmenau,Germany","Institute for Media Technology, TU Ilmenau, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Ilmenau,Institute for Media Technology,Ilmenau,Germany","institution_ids":["https://openalex.org/I119449181"]},{"raw_affiliation_string":"Institute for Media Technology, TU Ilmenau, Ilmenau, Germany","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031086670","display_name":"Estefan\u00eda Cano","orcid":"https://orcid.org/0000-0002-1056-5844"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Estefania Cano","raw_affiliation_strings":["Fraunhofer IDMT,Semantic Music Technologies,Ilmenau,Germany","Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT,Semantic Music Technologies,Ilmenau,Germany","institution_ids":["https://openalex.org/I4210138578"]},{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067553373","display_name":"Christian Kehling","orcid":"https://orcid.org/0000-0002-7828-503X"},"institutions":[{"id":"https://openalex.org/I119449181","display_name":"Technische Universit\u00e4t Ilmenau","ror":"https://ror.org/01weqhp73","country_code":"DE","type":"education","lineage":["https://openalex.org/I119449181"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Kehling","raw_affiliation_strings":["TU Ilmenau,Institute for Media Technology,Ilmenau,Germany","Institute for Media Technology, TU Ilmenau, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Ilmenau,Institute for Media Technology,Ilmenau,Germany","institution_ids":["https://openalex.org/I119449181"]},{"raw_affiliation_string":"Institute for Media Technology, TU Ilmenau, Ilmenau, Germany","institution_ids":["https://openalex.org/I119449181"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022729641","display_name":"Michael Taenzer","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Taenzer","raw_affiliation_strings":["Fraunhofer IDMT,Semantic Music Technologies,Ilmenau,Germany","Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT,Semantic Music Technologies,Ilmenau,Germany","institution_ids":["https://openalex.org/I4210138578"]},{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2811,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89218628,"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":"790","last_page":"794"},"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":0.9945999979972839,"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":0.9896000027656555,"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":0.8063448667526245},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.662968635559082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.635077714920044},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5280495285987854},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5170855522155762},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5043143033981323},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4160701036453247},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.387795627117157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063448667526245},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.662968635559082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635077714920044},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5280495285987854},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5170855522155762},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5043143033981323},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4160701036453247},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.387795627117157}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.23919/eusipco47968.2020.9287743","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco47968.2020.9287743","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 28th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:fraunhofer.de:N-637575","is_oa":false,"landing_page_url":"http://publica.fraunhofer.de/documents/N-637575.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IDMT","raw_type":"Conference Paper"},{"id":"pmh:oai:publica.fraunhofer.de:publica/411583","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/411583","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1556219185","https://openalex.org/W1686810756","https://openalex.org/W2012296273","https://openalex.org/W2052666245","https://openalex.org/W2095705004","https://openalex.org/W2161381512","https://openalex.org/W2165698076","https://openalex.org/W2524365899","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2604959036","https://openalex.org/W2619697695","https://openalex.org/W2751841560","https://openalex.org/W2902583091","https://openalex.org/W2911999479","https://openalex.org/W2939574508","https://openalex.org/W2945260553","https://openalex.org/W2962756039","https://openalex.org/W2962910554","https://openalex.org/W2963550089","https://openalex.org/W2964121744","https://openalex.org/W2971274815","https://openalex.org/W2984000344","https://openalex.org/W2990875942","https://openalex.org/W3098670224","https://openalex.org/W3133666898","https://openalex.org/W4293665662","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6729831399","https://openalex.org/W6734260513","https://openalex.org/W6736327223","https://openalex.org/W6738607494","https://openalex.org/W6758596246","https://openalex.org/W6762122294","https://openalex.org/W6770557639","https://openalex.org/W6785276831","https://openalex.org/W6790899780"],"related_works":["https://openalex.org/W2357114597","https://openalex.org/W2115416187","https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W4286910063","https://openalex.org/W2163707935","https://openalex.org/W83146503","https://openalex.org/W2169074127","https://openalex.org/W114581555","https://openalex.org/W202723009"],"abstract_inverted_index":{"In":[0,63],"the":[1,6,64,82,100,117,139,144,147,164,183],"context":[2],"of":[3,8,11,66,84,102,122,131,138,146,178],"deep":[4],"learning,":[5],"availability":[7],"large":[9,39],"amounts":[10],"training":[12,132,136,179],"data":[13],"can":[14,50],"play":[15],"a":[16,20,33,170,175],"critical":[17],"role":[18],"in":[19,32],"model's":[21],"performance.":[22],"Recently,":[23],"several":[24],"models":[25,158],"for":[26,71,127],"audio":[27,67,96],"classification":[28,97,120],"have":[29,77],"been":[30],"pre-trained":[31],"supervised":[34],"or":[35],"self-supervised":[36],"fashion":[37],"on":[38,94,119],"datasets":[40,56],"to":[41,59],"learn":[42],"complex":[43],"feature":[44],"representations,":[45],"socalled":[46],"embeddings.":[47,140],"These":[48],"embeddings":[49,93,111,166],"then":[51],"be":[52],"extracted":[53],"from":[54,99,160],"smaller":[55],"and":[57,106,134],"used":[58],"train":[60],"subsequent":[61],"classifiers.":[62],"field":[65],"event":[68],"detection":[69],"(AED)":[70],"example,":[72],"classifiers":[73],"using":[74],"these":[75],"features":[76],"achieved":[78],"high":[79],"accuracy":[80,121],"without":[81],"need":[83],"additional":[85],"domain":[86,137],"knowledge.":[87],"This":[88],"paper":[89],"evaluates":[90],"three":[91],"state-of-the-art":[92],"six":[95],"tasks":[98],"fields":[101],"music":[103],"information":[104],"retrieval":[105],"industrial":[107],"sound":[108],"analysis.":[109],"The":[110],"are":[112,151],"systematically":[113],"evaluated":[114],"by":[115],"analyzing":[116],"influence":[118],"classifier":[123],"architecture,":[124],"fusion":[125],"methods":[126],"file-wise":[128],"predictions,":[129],"amount":[130,177],"data,":[133],"initial":[135,184],"To":[141],"better":[142],"understand":[143],"impact":[145],"pre-training":[148],"step,":[149],"results":[150],"also":[152],"compared":[153],"with":[154,157,169],"those":[155],"acquired":[156],"trained":[159],"scratch.":[161],"On":[162],"average,":[163],"OpenL3":[165,181],"performed":[167],"best":[168],"linear":[171],"SVM":[172],"classifier.":[173],"For":[174],"reduced":[176],"examples,":[180],"outperforms":[182],"baseline.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}