{"id":"https://openalex.org/W2598162002","doi":"https://doi.org/10.21437/interspeech.2017-101","title":"Audio Scene Classification with Deep Recurrent Neural Networks","display_name":"Audio Scene Classification with Deep Recurrent Neural Networks","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2598162002","doi":"https://doi.org/10.21437/interspeech.2017-101","mag":"2598162002"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-101","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","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/1703.04770","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/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":true,"raw_author_name":"Huy Phan","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/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/A5065398968","display_name":"Fabrice Katzberg","orcid":"https://orcid.org/0000-0002-5472-0500"},"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":"Fabrice Katzberg","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/A5048584044","display_name":"Marco Maa\u00df","orcid":"https://orcid.org/0000-0001-7422-147X"},"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":"Marco Maass","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/A5074089177","display_name":"Radoslaw Mazur","orcid":null},"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":"Radoslaw Mazur","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":"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":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058452657"],"corresponding_institution_ids":["https://openalex.org/I9341345"],"apc_list":null,"apc_paid":null,"fwci":1.21411276,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77942699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3043","last_page":"3047"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/subsequence","display_name":"Subsequence","score":0.8027928471565247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7486899495124817},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6834613680839539},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6340497732162476},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6194775700569153},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6176157593727112},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5804581642150879},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5551999807357788},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5062028765678406},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.49358952045440674},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.48140621185302734},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46280425786972046},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.45577406883239746},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.42383432388305664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32685577869415283},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10817515850067139}],"concepts":[{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.8027928471565247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486899495124817},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6834613680839539},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6340497732162476},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6194775700569153},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6176157593727112},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5804581642150879},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5062028765678406},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.49358952045440674},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.48140621185302734},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46280425786972046},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.45577406883239746},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.42383432388305664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32685577869415283},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10817515850067139},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2017-101","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:72671","is_oa":false,"landing_page_url":"https://doi.org/10.21437/Interspeech.2017-101>)","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"pmh:oai:arXiv.org:1703.04770","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.04770","pdf_url":"https://arxiv.org/pdf/1703.04770","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":null},{"id":"mag:2598162002","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1703.04770.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.1703.04770","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1703.04770","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:1703.04770","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1703.04770","pdf_url":"https://arxiv.org/pdf/1703.04770","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":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W581956982","https://openalex.org/W1522734439","https://openalex.org/W1924770834","https://openalex.org/W2064675550","https://openalex.org/W2086384421","https://openalex.org/W2087347434","https://openalex.org/W2095147901","https://openalex.org/W2095705004","https://openalex.org/W2147860648","https://openalex.org/W2157331557","https://openalex.org/W2158336491","https://openalex.org/W2200864288","https://openalex.org/W2403172465","https://openalex.org/W2618553051","https://openalex.org/W2952186347","https://openalex.org/W2962922588","https://openalex.org/W2964121744"],"related_works":["https://openalex.org/W2963500860","https://openalex.org/W3006331548","https://openalex.org/W2962922588","https://openalex.org/W3018177699","https://openalex.org/W2153182373","https://openalex.org/W2990715442","https://openalex.org/W2766768743","https://openalex.org/W2513750347","https://openalex.org/W2805227700","https://openalex.org/W2969367431","https://openalex.org/W2341018344","https://openalex.org/W3029562711","https://openalex.org/W2593750211","https://openalex.org/W2762075645","https://openalex.org/W3198726715","https://openalex.org/W2061160345","https://openalex.org/W2762026055","https://openalex.org/W2883024665","https://openalex.org/W2921985587","https://openalex.org/W2954579674"],"abstract_inverted_index":{"We":[0,72],"introduce":[1],"in":[2],"this":[3],"work":[4],"an":[5,79],"efficient":[6],"approach":[7,77,109],"for":[8,52,59,95],"audio":[9,18],"scene":[10,19],"classification":[11,70,116],"using":[12],"deep":[13,45],"recurrent":[14,47],"neural":[15,48],"networks.":[16],"An":[17],"is":[20,36,50,63,89,110],"firstly":[21],"transformed":[22],"into":[23,39],"a":[24,44],"sequence":[25,35,62],"of":[26,68,81],"high-level":[27],"label":[28,58],"tree":[29],"embedding":[30],"feature":[31],"vectors.":[32],"The":[33,55],"vector":[34],"then":[37],"divided":[38],"multiple":[40],"subsequences":[41],"on":[42,83,105],"which":[43,88],"GRU-based":[46],"network":[49],"trained":[51],"sequence-to-label":[53],"classification.":[54],"global":[56],"predicted":[57],"the":[60,84,90,96,100,106,114],"entire":[61],"finally":[64],"obtained":[65],"via":[66],"aggregation":[67],"subsequence":[69],"outputs.":[71],"will":[73],"show":[74],"that":[75],"our":[76,108],"obtains":[78],"F1-score":[80],"97.7%":[82],"LITIS":[85],"Rouen":[86],"dataset,":[87,107],"largest":[91],"dataset":[92],"publicly":[93],"available":[94],"task.":[97],"Compared":[98],"to":[99,112],"best":[101],"previously":[102],"reported":[103],"result":[104],"able":[111],"reduce":[113],"relative":[115],"error":[117],"by":[118],"35.3%.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}