{"id":"https://openalex.org/W2903185874","doi":"https://doi.org/10.23919/eusipco.2018.8553225","title":"A Fusion of Deep Convolutional Generative Adversarial Networks and Sequence to Sequence Autoencoders for Acoustic Scene Classification","display_name":"A Fusion of Deep Convolutional Generative Adversarial Networks and Sequence to Sequence Autoencoders for Acoustic Scene Classification","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2903185874","doi":"https://doi.org/10.23919/eusipco.2018.8553225","mag":"2903185874"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco.2018.8553225","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/45046/45046.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000854998","display_name":"Shahin Arniriparian","orcid":null},"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"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Shahin Arniriparian","raw_affiliation_strings":["Machine Intelligence & Signal Processinz Groun, Technische Universitat, M\u00fcnchen, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processinz Groun, Technische Universitat, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005165934","display_name":"Michael Freitag","orcid":"https://orcid.org/0000-0003-1767-9104"},"institutions":[{"id":"https://openalex.org/I186354981","display_name":"University of Passau","ror":"https://ror.org/05ydjnb78","country_code":"DE","type":"education","lineage":["https://openalex.org/I186354981"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michael Freitag","raw_affiliation_strings":["University of Passau, Germany"],"affiliations":[{"raw_affiliation_string":"University of Passau, Germany","institution_ids":["https://openalex.org/I186354981"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090485343","display_name":"Nicholas Cummins","orcid":"https://orcid.org/0000-0002-1178-917X"},"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":"Nicholas Cummins","raw_affiliation_strings":["ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091269736","display_name":"Maurice Gerczuk","orcid":"https://orcid.org/0000-0001-8293-6635"},"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":"Maurice Gerczuk","raw_affiliation_strings":["ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045384658","display_name":"Sergey Pugachevskiy","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":"Sergey Pugachevskiy","raw_affiliation_strings":["ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"ZD.B Chair of Embedded Intelligence for Health Care & 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"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany"],"affiliations":[{"raw_affiliation_string":"ZD.B Chair of Embedded Intelligence for Health Care & Wellbeing, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5000854998"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":2.1469,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88722403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"977","last_page":"981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.991100013256073,"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/sequence","display_name":"Sequence (biology)","score":0.7349715232849121},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7228509187698364},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7034496068954468},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7018114328384399},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6928955316543579},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5445653200149536},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47694769501686096},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4513985514640808},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32877248525619507}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7349715232849121},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7228509187698364},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7034496068954468},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7018114328384399},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6928955316543579},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5445653200149536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47694769501686096},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4513985514640808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32877248525619507},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23919/eusipco.2018.8553225","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco.2018.8553225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 26th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:45046","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/45046","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/45046/45046.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":{"id":"pmh:oai:uni-augsburg.opus-bayern.de:45046","is_oa":true,"landing_page_url":"https://opus.bibliothek.uni-augsburg.de/opus4/frontdoor/index/index/docId/45046","pdf_url":"https://opus.bibliothek.uni-augsburg.de/opus4/files/45046/45046.pdf","source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"},"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2903185874.pdf","grobid_xml":"https://content.openalex.org/works/W2903185874.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1997430507","https://openalex.org/W2062118960","https://openalex.org/W2066148499","https://openalex.org/W2086384421","https://openalex.org/W2095705004","https://openalex.org/W2099471712","https://openalex.org/W2103235956","https://openalex.org/W2130942839","https://openalex.org/W2155541015","https://openalex.org/W2163605009","https://openalex.org/W2163922914","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2398456099","https://openalex.org/W2561826558","https://openalex.org/W2566935005","https://openalex.org/W2584667682","https://openalex.org/W2732459531","https://openalex.org/W2746419079","https://openalex.org/W2750299714","https://openalex.org/W2765860599","https://openalex.org/W2773245850","https://openalex.org/W2775505379","https://openalex.org/W2775794021","https://openalex.org/W2786267588","https://openalex.org/W2786800255","https://openalex.org/W2962756039","https://openalex.org/W2963194800","https://openalex.org/W3104866538","https://openalex.org/W4293665662","https://openalex.org/W4294375521","https://openalex.org/W4320013936","https://openalex.org/W6637373629","https://openalex.org/W6674330103","https://openalex.org/W6679436768","https://openalex.org/W6682778277","https://openalex.org/W6684191040","https://openalex.org/W6712469065","https://openalex.org/W6729831399","https://openalex.org/W6732862412","https://openalex.org/W6742713230","https://openalex.org/W6743468362","https://openalex.org/W6746871685","https://openalex.org/W6746941363","https://openalex.org/W6747331233","https://openalex.org/W7043259713"],"related_works":["https://openalex.org/W4312417841","https://openalex.org/W4321369474","https://openalex.org/W2738221750","https://openalex.org/W2732542196","https://openalex.org/W564581980","https://openalex.org/W4211070796","https://openalex.org/W4301431435","https://openalex.org/W4214561993","https://openalex.org/W4226271949","https://openalex.org/W4200633480"],"abstract_inverted_index":{"Unsupervised":[0],"representation":[1,47],"learning":[2,48],"shows":[3],"high":[4],"promise":[5],"for":[6,10],"generating":[7],"robust":[8],"features":[9,25,55],"acoustic":[11,141],"scene":[12,142],"analysis.":[13],"In":[14,162],"this":[15],"regard,":[16],"we":[17],"propose":[18],"and":[19,36,75,87,106,153,158,192],"investigate":[20],"a":[21,29,37,80,122],"novel":[22],"combination":[23],"of":[24,45,67,72,79,92,139,146,155,198],"learnt":[26,61],"using":[27,177,188],"both":[28],"deep":[30],"convolutional":[31],"generative":[32],"adversarial":[33],"network":[34],"(DCGAN)":[35],"recurrent":[38],"sequence":[39,41],"to":[40,110,126,164,174,181,193],"autoencoder":[42],"(S2SAE).":[43],"Each":[44],"the":[46,65,68,73,77,85,93,104,112,128,136,140,147,165,167,179,185,190,199],"algorithms":[49],"is":[50,133,169],"trained":[51],"individually":[52],"on":[53,103,135,151,184],"spectral":[54],"extracted":[56],"from":[57,171],"audio":[58],"instances.":[59],"The":[60,115,131],"representations":[62],"are:":[63],"(i)":[64],"activations":[66,78],"discriminator":[69],"in":[70,90,121],"case":[71,91],"DCGAN,":[74,180],"(ii)":[76],"fully":[81],"connected":[82],"layer":[83],"between":[84],"decoder":[86],"encoder":[88],"units":[89],"S2SAE.":[94],"We":[95],"then":[96],"train":[97],"two":[98],"multilayer":[99],"perceptron":[100],"neural":[101],"networks":[102],"DCGAN":[105],"S2SAE":[107],"feature":[108],"vectors":[109],"predict":[111],"class":[113],"labels.":[114],"individual":[116,200],"predicted":[117],"labels":[118],"are":[119],"combined":[120],"weighted":[123],"decision-level":[124],"fusion":[125,197],"achieve":[127],"final":[129],"prediction.":[130],"system":[132],"evaluated":[134],"development":[137,186],"partition":[138],"classification":[143],"data":[144],"set":[145,187],"IEEE":[148],"AASP":[149],"Challenge":[150],"Detection":[152],"Classification":[154],"Acoustic":[156],"Scenes":[157],"Events":[159],"(DCASE":[160],"2017).":[161],"comparison":[163],"baseline,":[166],"accuracy":[168],"increased":[170],"74.8":[172],"%":[173,176,183,195],"86.4":[175],"only":[178,189],"88.5":[182],"S2SAE,":[191],"91.1":[194],"after":[196],"predictions.":[201]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-12-11T00:00:00"}