{"id":"https://openalex.org/W4383899470","doi":"https://doi.org/10.1109/taslp.2023.3293032","title":"How Robust are Audio Embeddings for Polyphonic Sound Event Tagging?","display_name":"How Robust are Audio Embeddings for Polyphonic Sound Event Tagging?","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4383899470","doi":"https://doi.org/10.1109/taslp.2023.3293032"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3293032","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3293032","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10178070.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10178070.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047532715","display_name":"Jakob Abe\u00dfer","orcid":"https://orcid.org/0000-0003-4689-7944"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]},{"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":"Jakob Abe\u00dfer","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany","International Audio Laboratories Erlangen, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0003-4689-7944","affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068929948","display_name":"Sascha Grollmisch","orcid":"https://orcid.org/0000-0001-9703-110X"},"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":"Sascha Grollmisch","raw_affiliation_strings":["Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":"https://orcid.org/0000-0001-9703-110X","affiliations":[{"raw_affiliation_string":"Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard M\u00fcller","raw_affiliation_strings":["International Audio Laboratories Erlangen, Erlangen, Germany"],"raw_orcid":"https://orcid.org/0000-0001-6062-7524","affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5543,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62727498,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"31","issue":null,"first_page":"2658","last_page":"2667"},"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":0.9986000061035156,"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":0.9897000193595886,"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":0.8270890712738037},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7657783031463623},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6762282848358154},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5985661149024963},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5495407581329346},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5180590152740479},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.49689415097236633},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4906550943851471},{"id":"https://openalex.org/keywords/sound-recording-and-reproduction","display_name":"Sound recording and reproduction","score":0.479593425989151},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.413488507270813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35517337918281555},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.15572458505630493}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.8270890712738037},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7657783031463623},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6762282848358154},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5985661149024963},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5495407581329346},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5180590152740479},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.49689415097236633},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4906550943851471},{"id":"https://openalex.org/C128422554","wikidata":"https://www.wikidata.org/wiki/Q20077126","display_name":"Sound recording and reproduction","level":2,"score":0.479593425989151},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.413488507270813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35517337918281555},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.15572458505630493},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2023.3293032","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3293032","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10178070.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/450970","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/450970","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":"journal article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2023.3293032","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3293032","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10178070.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","score":0.5099999904632568,"display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G3041439062","display_name":null,"funder_award_id":"AB 675/2-2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7537619583","display_name":null,"funder_award_id":"MU 2686/11-2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320873","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4383899470.pdf","grobid_xml":"https://content.openalex.org/works/W4383899470.grobid-xml"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1990368529","https://openalex.org/W2051224630","https://openalex.org/W2052666245","https://openalex.org/W2130865646","https://openalex.org/W2410860376","https://openalex.org/W2526050071","https://openalex.org/W2593116425","https://openalex.org/W2606176153","https://openalex.org/W2759976799","https://openalex.org/W2802272416","https://openalex.org/W2810655876","https://openalex.org/W2936774411","https://openalex.org/W2939574508","https://openalex.org/W2962910554","https://openalex.org/W2997819898","https://openalex.org/W3004910802","https://openalex.org/W3041133507","https://openalex.org/W3094111018","https://openalex.org/W3094550259","https://openalex.org/W3098670224","https://openalex.org/W3115751294","https://openalex.org/W3119727976","https://openalex.org/W3122335742","https://openalex.org/W3161026535","https://openalex.org/W3162391496","https://openalex.org/W3163827866","https://openalex.org/W3196974791","https://openalex.org/W3205475937","https://openalex.org/W3214872027","https://openalex.org/W3215881519","https://openalex.org/W4205236539","https://openalex.org/W4205689591","https://openalex.org/W4210663539","https://openalex.org/W4221150524","https://openalex.org/W4226151502","https://openalex.org/W4284898017","https://openalex.org/W4287802874","https://openalex.org/W4293342670","https://openalex.org/W4311137818","https://openalex.org/W4312445970","https://openalex.org/W4312592048","https://openalex.org/W4312886255","https://openalex.org/W4312938053","https://openalex.org/W4372266552","https://openalex.org/W4383340360","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6736723571","https://openalex.org/W6748326514","https://openalex.org/W6752996073","https://openalex.org/W6776218486","https://openalex.org/W6804120432","https://openalex.org/W6809947431","https://openalex.org/W6843026064","https://openalex.org/W7026384963"],"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/W2318538434","https://openalex.org/W4404440671"],"abstract_inverted_index":{"Sound":[0],"classification":[1,88,181],"algorithms":[2,27],"are":[3],"challenged":[4],"by":[5],"the":[6,48,74,105,111,117,123,126,146,150,174,194,199],"natural":[7],"variability":[8],"of":[9,51,77,113,125,165,176],"everyday":[10],"sounds,":[11],"particularly":[12],"for":[13,66,86,203],"large":[14],"sound":[15,41,67,87,114,189,205],"class":[16],"taxonomies.":[17],"In":[18,69],"order":[19],"to":[20,32,44,168,184,187],"be":[21,30,45],"applicable":[22],"in":[23,89,116,149],"real-life":[24],"environments,":[25],"such":[26],"must":[28],"also":[29],"able":[31],"handle":[33],"polyphonic":[34,90],"scenarios,":[35],"where":[36],"simultaneously":[37],"occurring":[38],"and":[39,83,95,110,132,141,172],"overlapping":[40],"events":[42],"need":[43],"classified.":[46],"With":[47],"rapid":[49],"progress":[50],"deep":[52,55],"learning,":[53],"several":[54,97,129],"audio":[56,80,130],"embeddings":[57,127,196],"(DAEs)":[58],"have":[59,197],"been":[60],"proposed":[61],"as":[62,154],"pre-trained":[63],"feature":[64,108],"representations":[65,81],"classification.":[68],"this":[70],"article,":[71],"we":[72,100,121,158],"analyze":[73],"embedding":[75,118,151,169],"spaces":[76],"two":[78,134],"non-trainable":[79],"(NTARs)":[82],"five":[84],"DAEs":[85],"scenarios":[91],"(sound":[92],"event":[93,206],"tagging)":[94],"make":[96],"contributions.":[98],"First,":[99],"compare":[101],"general":[102],"properties":[103],"like":[104],"inter-correlation":[106],"between":[107,163],"dimensions":[109],"scattering":[112],"classes":[115],"spaces.":[119],"Second,":[120],"test":[122],"robustness":[124],"against":[128],"degradations":[131],"propose":[133],"sensitivity":[135],"measures":[136],"based":[137],"on":[138,145],"a":[139,142,155,161],"class-agnostic":[140],"class-centric":[143],"view":[144],"resulting":[147],"drift":[148],"space.":[152],"Finally,":[153],"central":[156],"contribution,":[157],"study":[159],"how":[160,173],"blending":[162],"pairs":[164],"sounds":[166],"maps":[167],"space":[170],"trajectories":[171,178],"path":[175],"these":[177],"can":[179],"cause":[180],"errors":[182],"due":[183],"their":[185],"proximity":[186],"other":[188],"classes.":[190],"Throughout":[191],"our":[192],"analyses,":[193],"PANN":[195],"shown":[198],"best":[200],"overall":[201],"performance":[202],"low-polyphony":[204],"tagging.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
