{"id":"https://openalex.org/W4388117367","doi":"https://doi.org/10.23919/eusipco58844.2023.10289789","title":"Uncertainty in Semi-Supervised Audio Classification \u2013 A Novel Extension for FixMatch","display_name":"Uncertainty in Semi-Supervised Audio Classification \u2013 A Novel Extension for FixMatch","publication_year":2023,"publication_date":"2023-09-04","ids":{"openalex":"https://openalex.org/W4388117367","doi":"https://doi.org/10.23919/eusipco58844.2023.10289789"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco58844.2023.10289789","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st 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/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":["Industrial Media Applications, Fraunhofer IDMT,Ilmenau,Germany","Industrial Media Applications, Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Industrial Media Applications, Fraunhofer IDMT,Ilmenau,Germany","institution_ids":["https://openalex.org/I4210138578"]},{"raw_affiliation_string":"Industrial Media Applications, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"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/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Estefan\u00eda Cano","raw_affiliation_strings":["Songquito UG,Erlangen,Germany","Songquito UG, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Songquito UG,Erlangen,Germany","institution_ids":[]},{"raw_affiliation_string":"Songquito UG, Erlangen, Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067411318","display_name":"Hanna Lukashevich","orcid":"https://orcid.org/0000-0002-9041-9475"},"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":"Hanna Lukashevich","raw_affiliation_strings":["Semantic Music Technologies, Fraunhofer IDMT,Ilmenau,Germany","Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT,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":"last","author":{"id":"https://openalex.org/A5047532715","display_name":"Jakob Abe\u00dfer","orcid":"https://orcid.org/0000-0003-4689-7944"},"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":"Jakob Abe\u00dfer","raw_affiliation_strings":["Semantic Music Technologies, Fraunhofer IDMT,Ilmenau,Germany","Semantic Music Technologies, Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Semantic Music Technologies, Fraunhofer IDMT,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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14200817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.982200026512146,"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/T11220","display_name":"Water Systems and Optimization","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777477502822876},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6386843323707581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6363762617111206},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5465521216392517},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.5352625846862793},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.4903111755847931},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.47662484645843506},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45961469411849976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45594489574432373},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.412168025970459},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3503054976463318},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15295511484146118},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08171895146369934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777477502822876},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6386843323707581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6363762617111206},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5465521216392517},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.5352625846862793},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.4903111755847931},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.47662484645843506},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45961469411849976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45594489574432373},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.412168025970459},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3503054976463318},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15295511484146118},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08171895146369934},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco58844.2023.10289789","is_oa":false,"landing_page_url":"http://dx.doi.org/10.23919/eusipco58844.2023.10289789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/456716","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/456716","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W2194775991","https://openalex.org/W2600383743","https://openalex.org/W2606176153","https://openalex.org/W2626967530","https://openalex.org/W2948194985","https://openalex.org/W2953070460","https://openalex.org/W2963238274","https://openalex.org/W2963995504","https://openalex.org/W2996501936","https://openalex.org/W3001197829","https://openalex.org/W3091002423","https://openalex.org/W3118608800","https://openalex.org/W3171608926","https://openalex.org/W3187026598","https://openalex.org/W3205500251","https://openalex.org/W3208082774","https://openalex.org/W4287388854","https://openalex.org/W4288356534","https://openalex.org/W4292122171","https://openalex.org/W4296457157","https://openalex.org/W4393583308","https://openalex.org/W6617145748","https://openalex.org/W6730042731","https://openalex.org/W6733814495","https://openalex.org/W6735443497","https://openalex.org/W6736723571","https://openalex.org/W6739651123","https://openalex.org/W6762357143","https://openalex.org/W6763087592","https://openalex.org/W6771787070","https://openalex.org/W6773005947","https://openalex.org/W6788329692","https://openalex.org/W6797119129","https://openalex.org/W6802864417","https://openalex.org/W6842024468"],"related_works":["https://openalex.org/W2132466791","https://openalex.org/W3091880950","https://openalex.org/W2783129721","https://openalex.org/W1983574915","https://openalex.org/W2157552837","https://openalex.org/W2169863116","https://openalex.org/W2296406158","https://openalex.org/W3170999895","https://openalex.org/W4389374014","https://openalex.org/W2149795293"],"abstract_inverted_index":{"Semi-supervised":[0],"learning":[1],"(SSL)":[2],"is":[3,11,16,176],"a":[4,25,49,101,178],"commonly":[5],"used":[6],"technique":[7],"when":[8],"annotated":[9],"data":[10,15],"scarce":[12],"but":[13],"unlabeled":[14,82],"easily":[17],"available.":[18,65],"In":[19,66],"recent":[20],"years,":[21],"SSL":[22,52],"has":[23],"seen":[24],"large":[26],"boost":[27],"in":[28],"the":[29,55,72,75,110,113,118,137,158,161,181],"computer":[30],"vision":[31],"domain":[32],"and":[33,54,89,99,108,124,147,169],"methods":[34,53],"such":[35],"as":[36],"FixMatch":[37,105],"were":[38,60],"successfully":[39],"adapted":[40],"to":[41,142,150,167,172,180],"audio":[42],"classification":[43,88],"tasks.":[44],"However,":[45],"there":[46,175],"still":[47,177],"remains":[48],"gap":[50,179],"between":[51,121],"fully":[56,182],"supervised":[57,183],"baselines,":[58],"which":[59],"trained":[61],"with":[62,133],"all":[63],"labels":[64,80],"this":[67],"work,":[68],"we":[69,97,116],"first":[70],"investigate":[71],"quality":[73,123],"of":[74,104,112],"pseudo-labels,":[76],"i.":[77],"e.,":[78],"generated":[79],"for":[81,84,144,152,187],"data,":[83],"musical":[85],"instrument":[86,145],"family":[87,146],"acoustic":[90,153],"scene":[91,154],"classification.":[92,155],"Based":[93],"on":[94,160],"these":[95],"insights,":[96],"propose":[98],"evaluate":[100],"novel":[102],"extension":[103],"that":[106,129],"quantifies":[107],"considers":[109],"uncertainty":[111],"pseudo-labels.":[114],"Additionally,":[115],"highlight":[117],"problematic":[119],"tradeoff":[120],"pseudo-label":[122,138],"quantity.":[125],"Our":[126],"results":[127],"show":[128],"Monte-Carlo":[130],"Dropout":[131],"combined":[132],"temperature":[134],"scaling":[135],"improved":[136,164],"accuracy":[139,159],"from":[140,148,165,170],"78.4%":[141],"86.7%":[143],"87.9%":[149],"89.9%":[151],"Even":[156],"though":[157],"test":[162],"sets":[163],"71.0%":[166],"72.1%":[168],"69.2%":[171],"70.8%,":[173],"respectively,":[174],"baseline":[184],"leaving":[185],"room":[186],"future":[188],"work.":[189]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}