{"id":"https://openalex.org/W4390446570","doi":"https://doi.org/10.1145/3617233.3617265","title":"XAI-based Comparison of Audio Event Classifiers with different Input Representations","display_name":"XAI-based Comparison of Audio Event Classifiers with different Input Representations","publication_year":2023,"publication_date":"2023-09-20","ids":{"openalex":"https://openalex.org/W4390446570","doi":"https://doi.org/10.1145/3617233.3617265"},"language":"en","primary_location":{"id":"doi:10.1145/3617233.3617265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617233.3617265","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617233.3617265","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3617233.3617265","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061967247","display_name":"Annika Frommholz","orcid":"https://orcid.org/0009-0008-3600-1028"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Annika Frommholz","raw_affiliation_strings":["Fraunhofer Heinrich Hertz Institute, DE"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Heinrich Hertz Institute, DE","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017380677","display_name":"Fabian Seipel","orcid":"https://orcid.org/0009-0000-3352-0473"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian Seipel","raw_affiliation_strings":["Technical University Berlin, DE"],"affiliations":[{"raw_affiliation_string":"Technical University Berlin, DE","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017608155","display_name":"Sebastian Lapuschkin","orcid":"https://orcid.org/0000-0002-0762-7258"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Lapuschkin","raw_affiliation_strings":["Fraunhofer Heinrich Hertz Institute, DE"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Heinrich Hertz Institute, DE","institution_ids":["https://openalex.org/I2800274787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026451495","display_name":"Wojciech Samek","orcid":"https://orcid.org/0000-0002-6283-3265"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4401727010","display_name":"Berlin Institute for the Foundations of Learning and Data","ror":"https://ror.org/05dsfb086","country_code":null,"type":"facility","lineage":["https://openalex.org/I4401727010","https://openalex.org/I4577782","https://openalex.org/I7877124"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wojciech Samek","raw_affiliation_strings":["Fraunhofer Heinrich Hertz Institute, DE and Technical University Berlin, Germany and Berlin Institute for the Foundations of Learning and Data (BIFOLD), Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Heinrich Hertz Institute, DE and Technical University Berlin, Germany and Berlin Institute for the Foundations of Learning and Data (BIFOLD), Germany","institution_ids":["https://openalex.org/I2800274787","https://openalex.org/I4401727010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082427123","display_name":"Johanna Vielhaben","orcid":"https://orcid.org/0000-0001-9399-5710"},"institutions":[{"id":"https://openalex.org/I2800274787","display_name":"Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute","ror":"https://ror.org/02tbr6331","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2800274787","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johanna Vielhaben","raw_affiliation_strings":["Fraunhofer Heinrich Hertz Institute, DE"],"affiliations":[{"raw_affiliation_string":"Fraunhofer Heinrich Hertz Institute, DE","institution_ids":["https://openalex.org/I2800274787"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061967247"],"corresponding_institution_ids":["https://openalex.org/I2800274787"],"apc_list":null,"apc_paid":null,"fwci":0.7832,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72865533,"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":"126","last_page":"132"},"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9937000274658203,"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"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8482919335365295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7967970371246338},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6437364220619202},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5938436985015869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.570239245891571},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5547946095466614},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5434575080871582},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5030590891838074},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4671945571899414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44885680079460144},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.44484972953796387},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4391729533672333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38835975527763367},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10718154907226562}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8482919335365295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967970371246338},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6437364220619202},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5938436985015869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.570239245891571},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5547946095466614},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5434575080871582},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5030590891838074},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4671945571899414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44885680079460144},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.44484972953796387},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4391729533672333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38835975527763367},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10718154907226562},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3617233.3617265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617233.3617265","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617233.3617265","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},{"id":"pmh:oai:null:publica/464644","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/464644","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":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.1145/3617233.3617265","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617233.3617265","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617233.3617265","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th International Conference on Content-based Multimedia Indexing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1454386574","display_name":null,"funder_award_id":"01IS21069B","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G208215675","display_name":null,"funder_award_id":"KI-FOR 5363","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G3031800739","display_name":null,"funder_award_id":"BIFOLD","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G315874844","display_name":null,"funder_award_id":"21069","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G4307164954","display_name":null,"funder_award_id":"01IS18037I","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4533892997","display_name":null,"funder_award_id":"01IS18037","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G4956428346","display_name":null,"funder_award_id":"Horizon 2020 research and innovatio","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6743167992","display_name":null,"funder_award_id":"965221","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7225624288","display_name":null,"funder_award_id":"This work was","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G7257732812","display_name":null,"funder_award_id":"101093003","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7624340995","display_name":null,"funder_award_id":"01IS18025A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G8316084977","display_name":null,"funder_award_id":"01IS18037I","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390446570.pdf","grobid_xml":"https://content.openalex.org/works/W4390446570.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W48945593","https://openalex.org/W1496704041","https://openalex.org/W1787224781","https://openalex.org/W1972567154","https://openalex.org/W2038484192","https://openalex.org/W2195388612","https://openalex.org/W2400753342","https://openalex.org/W2526050071","https://openalex.org/W2593451766","https://openalex.org/W2774097455","https://openalex.org/W2902444285","https://openalex.org/W2973136764","https://openalex.org/W3082587889","https://openalex.org/W3091589898","https://openalex.org/W3146622378","https://openalex.org/W3150957536","https://openalex.org/W4200473284","https://openalex.org/W4286853561","https://openalex.org/W4288366319","https://openalex.org/W4289915738","https://openalex.org/W4297775537","https://openalex.org/W4322759118","https://openalex.org/W4324312869","https://openalex.org/W4389115020"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W4360764600"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"are":[3,20],"a":[4,135],"promising":[5],"tool":[6],"for":[7,26,92],"Audio":[8,93],"Event":[9,94],"Classification.":[10],"In":[11,58],"contrast":[12],"to":[13,34,38,66,87],"other":[14,107],"data":[15],"like":[16],"natural":[17],"images,":[18],"there":[19],"many":[21],"sensible":[22],"and":[23,105,142,149],"non-obvious":[24],"representations":[25,47],"audio":[27],"data,":[28],"which":[29],"could":[30],"serve":[31],"as":[32,101,113],"input":[33,46,77,89,143],"these":[35,130],"models.":[36],"Due":[37],"their":[39],"black-box":[40],"nature,":[41],"the":[42,68,99,102,106,139,156],"effect":[43],"of":[44,72,147],"different":[45,76],"has":[48],"so":[49],"far":[50],"mostly":[51],"been":[52],"investigated":[53],"by":[54],"measuring":[55],"classification":[56,70,158],"performance.":[57],"this":[59],"work,":[60],"we":[61,80,132,152],"leverage":[62],"eXplainable":[63],"AI":[64],"(XAI),":[65],"understand":[67],"underlying":[69],"strategies":[71,159],"models":[73],"trained":[74],"on":[75],"representations.":[78],"Specifically,":[79],"compare":[81],"two":[82],"model":[83,141],"architectures":[84],"with":[85,161],"regard":[86],"relevant":[88],"features":[90],"used":[91],"Detection:":[95],"one":[96],"directly":[97],"processes":[98],"signal":[100],"raw":[103],"waveform,":[104],"takes":[108],"its":[109],"time-frequency":[110],"spectrogram":[111],"representation":[112,144],"input.":[114],"We":[115],"show":[116],"how":[117],"relevance":[118],"heatmaps":[119],"obtained":[120],"via":[121],"Layer-wise":[122],"Relevance":[123],"Propagation":[124],"uncover":[125],"representation-dependent":[126],"decision":[127,137],"strategies.":[128],"With":[129],"insights,":[131],"can":[133,153],"make":[134],"well-informed":[136],"about":[138],"best":[140],"in":[145],"terms":[146],"robustness":[148],"representativity.":[150],"Further,":[151],"test":[154],"whether":[155],"model\u2019s":[157],"align":[160],"human":[162],"requirements.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2023-12-31T00:00:00"}