{"id":"https://openalex.org/W4392909753","doi":"https://doi.org/10.1109/icassp48485.2024.10446177","title":"Bringing the Discussion of Minima Sharpness to the Audio Domain: A Filter-Normalised Evaluation for Acoustic Scene Classification","display_name":"Bringing the Discussion of Minima Sharpness to the Audio Domain: A Filter-Normalised Evaluation for Acoustic Scene Classification","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909753","doi":"https://doi.org/10.1109/icassp48485.2024.10446177"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5037647437","display_name":"Manuel Milling","orcid":"https://orcid.org/0000-0002-8842-2958"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Manuel Milling","raw_affiliation_strings":["Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012240826","display_name":"Andreas Triantafyllopoulos","orcid":"https://orcid.org/0000-0001-8338-617X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Triantafyllopoulos","raw_affiliation_strings":["Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092639661","display_name":"Iosif Tsangko","orcid":"https://orcid.org/0009-0007-9614-5894"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Iosif Tsangko","raw_affiliation_strings":["University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113012701","display_name":"Simon Rampp","orcid":null},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon David Noel Rampp","raw_affiliation_strings":["University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of Augsburg,Chair of Embedded Intelligence for Health Care and Wellbeing,Germany","institution_ids":["https://openalex.org/I179225836"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bj\u00f6rn Wolfgang Schuller","raw_affiliation_strings":["Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,CHI – Chair of Health Informatics, MRI,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Embedded Intelligence for Health Care and Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5037647437"],"corresponding_institution_ids":["https://openalex.org/I179225836","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":1.3662,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79133107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"391","last_page":"395"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.964900016784668,"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":0.964900016784668,"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":0.9114999771118164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.732069730758667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6984957456588745},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5833368897438049},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5287871956825256},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4912371039390564},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4760344326496124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44533684849739075},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3604002594947815},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3316788673400879},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.32107219099998474},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.171674907207489},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06313824653625488}],"concepts":[{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.732069730758667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6984957456588745},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5833368897438049},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5287871956825256},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4912371039390564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4760344326496124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44533684849739075},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3604002594947815},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3316788673400879},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32107219099998474},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.171674907207489},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06313824653625488},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446177","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446177","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5104279231","display_name":null,"funder_award_id":"Koselleck","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7189395530","display_name":null,"funder_award_id":"442218748","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W74727102","https://openalex.org/W1850240193","https://openalex.org/W2108598243","https://openalex.org/W2137983211","https://openalex.org/W2552194003","https://openalex.org/W2588366490","https://openalex.org/W2745969942","https://openalex.org/W2900315145","https://openalex.org/W2911682203","https://openalex.org/W2912811302","https://openalex.org/W2963026800","https://openalex.org/W2972470942","https://openalex.org/W2975301014","https://openalex.org/W2995348821","https://openalex.org/W3034491857","https://openalex.org/W3042317849","https://openalex.org/W3092873005","https://openalex.org/W3094550259","https://openalex.org/W3096276501","https://openalex.org/W3105698610","https://openalex.org/W3118608800","https://openalex.org/W3138582970","https://openalex.org/W3153582542","https://openalex.org/W3161663055","https://openalex.org/W3177316030","https://openalex.org/W3212348395","https://openalex.org/W4213406532","https://openalex.org/W4321012955","https://openalex.org/W4391566946","https://openalex.org/W6638926925","https://openalex.org/W6683107984","https://openalex.org/W6726983090","https://openalex.org/W6733748987","https://openalex.org/W6736583452","https://openalex.org/W6747381837","https://openalex.org/W6749107692","https://openalex.org/W6758508654","https://openalex.org/W6768204257","https://openalex.org/W6779341498","https://openalex.org/W6779774951","https://openalex.org/W6780496662","https://openalex.org/W6784164614","https://openalex.org/W6784426856","https://openalex.org/W6796913975","https://openalex.org/W6797978197","https://openalex.org/W6801687290","https://openalex.org/W6849569567"],"related_works":["https://openalex.org/W2375684291","https://openalex.org/W2354676191","https://openalex.org/W3188646203","https://openalex.org/W2909957174","https://openalex.org/W136674370","https://openalex.org/W4246278799","https://openalex.org/W2105527480","https://openalex.org/W2052387497","https://openalex.org/W2050203848","https://openalex.org/W2050191802"],"abstract_inverted_index":{"The":[0],"correlation":[1],"between":[2],"the":[3,11,30,38,48,54,100,115,124],"sharpness":[4,69,125],"of":[5,13,32,40,53,106,117,123,126],"loss":[6,143],"minima":[7,77,85,127],"and":[8,66,128,142],"generalisation":[9,82,104],"in":[10,29,37,113],"context":[12,31],"deep":[14],"neural":[15],"networks":[16],"has":[17],"been":[18],"subject":[19],"to":[20,79,99,135],"discussion":[21],"for":[22,47,89],"a":[23,67,120],"long":[24],"time.":[25],"Whilst":[26],"mostly":[27],"investigated":[28],"selected":[33],"benchmark":[34],"data":[35],"sets":[36],"area":[39],"computer":[41],"vision,":[42],"we":[43,129],"explore":[44],"this":[45],"aspect":[46],"acoustic":[49],"scene":[50],"classification":[51],"task":[52],"DCASE2020":[55],"challenge":[56],"data.":[57],"Our":[58,71,137],"analysis":[59,73],"is":[60,119],"based":[61],"on":[62],"two-dimensional":[63],"filter-normalised":[64],"visualisations":[65,145],"derived":[68],"measure.":[70],"exploratory":[72],"shows":[74],"that":[75],"sharper":[76],"tend":[78],"show":[80],"better":[81,103],"than":[83],"flat":[84,107],"\u2013even":[86],"more":[87],"so":[88],"out-of-domain":[90],"data,":[91],"recorded":[92],"from":[93],"previously":[94],"unseen":[95],"devices\u2013,":[96],"thus":[97],"adding":[98],"dispute":[101],"about":[102],"capabilities":[105],"minima.":[108],"We":[109],"further":[110],"find":[111],"that,":[112],"particular,":[114],"choice":[116],"optimisers":[118],"main":[121],"driver":[122],"discuss":[130],"resulting":[131],"limitations":[132],"with":[133],"respect":[134],"comparability.":[136],"code,":[138],"trained":[139],"model":[140],"states":[141],"landscape":[144],"are":[146],"publicly":[147],"available.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}