{"id":"https://openalex.org/W2929703785","doi":"https://doi.org/10.21437/interspeech.2019-3040","title":"Spatio-Temporal Attention Pooling for Audio Scene Classification","display_name":"Spatio-Temporal Attention Pooling for Audio Scene Classification","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2929703785","doi":"https://doi.org/10.21437/interspeech.2019-3040","mag":"2929703785"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-3040","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1904.03543","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058452657","display_name":"Huy Phan","orcid":"https://orcid.org/0000-0003-4096-785X"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Huy Phan","raw_affiliation_strings":["University of Kent:"],"affiliations":[{"raw_affiliation_string":"University of Kent:","institution_ids":["https://openalex.org/I20581793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074236126","display_name":"Oliver Y. Ch\u00e9n","orcid":"https://orcid.org/0000-0002-5696-3127"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Oliver Y. Ch\u00e9n","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075250567","display_name":"Lam Pham","orcid":"https://orcid.org/0000-0001-8155-7553"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lam Pham","raw_affiliation_strings":["University of Kent, Canterbury, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Kent, Canterbury, United Kingdom","institution_ids":["https://openalex.org/I20581793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044840858","display_name":"Philipp Koch","orcid":"https://orcid.org/0000-0002-8795-758X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philipp Koch","raw_affiliation_strings":["University of L\u00fcbeck, L\u00fcbeck, Germany"],"affiliations":[{"raw_affiliation_string":"University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064593698","display_name":"Maarten De Vos","orcid":"https://orcid.org/0000-0002-3482-5145"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maarten De Vos","raw_affiliation_strings":["University of Oxford, Oxford, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Oxford, Oxford, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I20581793","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56","country_code":"GB","type":"education","lineage":["https://openalex.org/I20581793"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian McLoughlin","raw_affiliation_strings":["University of Kent, Canterbury, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Kent, Canterbury, United Kingdom","institution_ids":["https://openalex.org/I20581793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063948113","display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"institutions":[{"id":"https://openalex.org/I9341345","display_name":"University of L\u00fcbeck","ror":"https://ror.org/00t3r8h32","country_code":"DE","type":"education","lineage":["https://openalex.org/I9341345"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alfred Mertins","raw_affiliation_strings":["University of L\u00fcbeck, L\u00fcbeck, Germany"],"affiliations":[{"raw_affiliation_string":"University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5058452657"],"corresponding_institution_ids":["https://openalex.org/I20581793"],"apc_list":null,"apc_paid":null,"fwci":0.6679,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.67413268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9990000128746033,"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":0.9745000004768372,"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/pooling","display_name":"Pooling","score":0.9001021385192871},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8545039892196655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7561633586883545},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6947576999664307},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.639056384563446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6228288412094116},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6071004867553711},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4638379216194153},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4621160328388214},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4446585178375244},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4325111210346222},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40893125534057617},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2377621829509735}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9001021385192871},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8545039892196655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7561633586883545},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6947576999664307},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.639056384563446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6228288412094116},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6071004867553711},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4638379216194153},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4621160328388214},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4446585178375244},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4325111210346222},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40893125534057617},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2377621829509735},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2019-3040","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-3040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.03543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03543","pdf_url":"https://arxiv.org/pdf/1904.03543","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2929703785","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.03543.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.03543","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.03543","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.03543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.03543","pdf_url":"https://arxiv.org/pdf/1904.03543","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G5321982477","display_name":null,"funder_award_id":"Titan V GPU","funder_id":"https://openalex.org/F4320309480","funder_display_name":"Nvidia"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320666","display_name":"University of Kent","ror":"https://ror.org/00xkeyj56"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2929703785.pdf","grobid_xml":"https://content.openalex.org/works/W2929703785.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1549656520","https://openalex.org/W1618905105","https://openalex.org/W1665214252","https://openalex.org/W1836465849","https://openalex.org/W1902237438","https://openalex.org/W2062388453","https://openalex.org/W2087347434","https://openalex.org/W2095147901","https://openalex.org/W2095705004","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2158336491","https://openalex.org/W2200864288","https://openalex.org/W2212106655","https://openalex.org/W2271840356","https://openalex.org/W2403172465","https://openalex.org/W2472122037","https://openalex.org/W2591013610","https://openalex.org/W2593451766","https://openalex.org/W2618553051","https://openalex.org/W2745969942","https://openalex.org/W2775794021","https://openalex.org/W2887072080","https://openalex.org/W2888784333","https://openalex.org/W2889527961","https://openalex.org/W2894608918","https://openalex.org/W2896911561","https://openalex.org/W2921763313","https://openalex.org/W2962922588","https://openalex.org/W2963500860","https://openalex.org/W2963590343","https://openalex.org/W2963794569","https://openalex.org/W2964121744","https://openalex.org/W2964328535","https://openalex.org/W3098357269","https://openalex.org/W3186890425"],"related_works":["https://openalex.org/W2972651776","https://openalex.org/W2142694332","https://openalex.org/W2186025005","https://openalex.org/W2808507676","https://openalex.org/W2981005517","https://openalex.org/W3164049065","https://openalex.org/W2978166512","https://openalex.org/W2510642588","https://openalex.org/W2951033927","https://openalex.org/W2964083648","https://openalex.org/W2962709777","https://openalex.org/W3043973718","https://openalex.org/W2890155761","https://openalex.org/W2553687433","https://openalex.org/W2981501041","https://openalex.org/W2754595124","https://openalex.org/W2342662179","https://openalex.org/W2609405962","https://openalex.org/W2945661781","https://openalex.org/W2901524904"],"abstract_inverted_index":{"Acoustic":[0],"scenes":[1],"are":[2,31,37,59],"rich":[3],"and":[4,86,98],"redundant":[5],"in":[6,46],"their":[7],"content.":[8],"In":[9],"this":[10,47],"work,":[11],"we":[12],"present":[13],"a":[14,21,73,104,131],"spatio-temporal":[15],"attention":[16,75,88,94],"pooling":[17],"layer":[18],"coupled":[19],"with":[20,114],"convolutional":[22,44,70,133],"recurrent":[23,57,101],"neural":[24,134],"network":[25,48,111,135],"to":[26,62,96],"learn":[27,49],"from":[28,52,91,118],"patterns":[29],"that":[30,36,124],"discriminative":[32],"while":[33],"suppressing":[34],"those":[35],"irrelevant":[38],"for":[39,108],"acoustic":[40],"scene":[41],"classification.":[42,109],"The":[43,55,110],"layers":[45,58,95],"invariant":[50],"features":[51],"time-frequency":[53],"input.":[54],"bidirectional":[56],"then":[60],"able":[61],"encode":[63],"the":[64,68,80,84,100,125,144],"temporal":[65,87],"dynamics":[66],"of":[67,83],"resulting":[69],"features.":[71],"Afterwards,":[72],"two-dimensional":[74],"mask":[76],"is":[77,112],"formed":[78],"via":[79],"outer":[81],"product":[82],"spatial":[85],"vectors":[89],"learned":[90],"two":[92],"designated":[93],"weigh":[97],"pool":[99],"output":[102],"into":[103],"final":[105],"feature":[106],"vector":[107],"trained":[113],"between-class":[115,119],"examples":[116],"generated":[117],"data":[120],"augmentation.":[121],"Experiments":[122],"demonstrate":[123],"proposed":[126],"method":[127],"not":[128],"only":[129],"outperforms":[130],"strong":[132],"baseline":[136],"but":[137],"also":[138],"sets":[139],"new":[140],"state-of-the-art":[141],"performance":[142],"on":[143],"LITIS":[145],"Rouen":[146],"dataset.":[147]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}