{"id":"https://openalex.org/W2618553051","doi":"https://doi.org/10.1109/taslp.2017.2690564","title":"Improved Audio Scene Classification Based on Label-Tree Embeddings and Convolutional Neural Networks","display_name":"Improved Audio Scene Classification Based on Label-Tree Embeddings and Convolutional Neural Networks","publication_year":2017,"publication_date":"2017-05-23","ids":{"openalex":"https://openalex.org/W2618553051","doi":"https://doi.org/10.1109/taslp.2017.2690564","mag":"2618553051"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2690564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2690564","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/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":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":["Institute for Signal Processing and the Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing and the Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, L\u00fcbeck, Germany","institution_ids":["https://openalex.org/I9341345"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044379875","display_name":"Lars Hertel","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":"Lars Hertel","raw_affiliation_strings":["Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, 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":["Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, 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":["Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, 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":["Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, 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":["Institute for Signal Processing, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, 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":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.5364,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.9745462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"25","issue":"6","first_page":"1278","last_page":"1290"},"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":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9811999797821045,"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/computer-science","display_name":"Computer science","score":0.767812967300415},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.71592777967453},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7065250873565674},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.706322193145752},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6894751191139221},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6426116228103638},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5825007557868958},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4764678478240967},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.46730613708496094},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45262783765792847},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.45244142413139343},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.42493486404418945},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3396141231060028},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3276086449623108},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.12460610270500183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11230704188346863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767812967300415},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.71592777967453},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7065250873565674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.706322193145752},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6894751191139221},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6426116228103638},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5825007557868958},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4764678478240967},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.46730613708496094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45262783765792847},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.45244142413139343},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.42493486404418945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3396141231060028},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3276086449623108},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.12460610270500183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11230704188346863},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2017.2690564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2690564","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:kar.kent.ac.uk:72672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TASLP.2017.2690564>)","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:qmro.qmul.ac.uk:123456789/65051","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/65051","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W37225217","https://openalex.org/W102487131","https://openalex.org/W1510526001","https://openalex.org/W1522301498","https://openalex.org/W1522734439","https://openalex.org/W1618905105","https://openalex.org/W1832693441","https://openalex.org/W1976258180","https://openalex.org/W1978274651","https://openalex.org/W1979594949","https://openalex.org/W2046972719","https://openalex.org/W2048174296","https://openalex.org/W2049434052","https://openalex.org/W2062388453","https://openalex.org/W2065529590","https://openalex.org/W2066148499","https://openalex.org/W2086384421","https://openalex.org/W2087347434","https://openalex.org/W2087461551","https://openalex.org/W2095147901","https://openalex.org/W2095705004","https://openalex.org/W2103235956","https://openalex.org/W2103568877","https://openalex.org/W2114777924","https://openalex.org/W2118858186","https://openalex.org/W2123843894","https://openalex.org/W2130640900","https://openalex.org/W2135342008","https://openalex.org/W2137343183","https://openalex.org/W2137561966","https://openalex.org/W2142194269","https://openalex.org/W2147860648","https://openalex.org/W2156303437","https://openalex.org/W2156387975","https://openalex.org/W2156481234","https://openalex.org/W2157498370","https://openalex.org/W2158336491","https://openalex.org/W2165874743","https://openalex.org/W2200864288","https://openalex.org/W2212106655","https://openalex.org/W2214128417","https://openalex.org/W2295707189","https://openalex.org/W2403172465","https://openalex.org/W2404382656","https://openalex.org/W2464644320","https://openalex.org/W2472122037","https://openalex.org/W2566935005","https://openalex.org/W2911964244","https://openalex.org/W2962756039","https://openalex.org/W2963158330","https://openalex.org/W2964121744","https://openalex.org/W3099869713","https://openalex.org/W3103385400","https://openalex.org/W4233392025","https://openalex.org/W4293665662","https://openalex.org/W6630424276","https://openalex.org/W6631190155","https://openalex.org/W6636501900","https://openalex.org/W6645021456","https://openalex.org/W6672434361","https://openalex.org/W6677919164","https://openalex.org/W6682864246","https://openalex.org/W6682889407","https://openalex.org/W6684578312","https://openalex.org/W6713358509","https://openalex.org/W6719414543","https://openalex.org/W6729831399","https://openalex.org/W6980901144"],"related_works":["https://openalex.org/W2810679507","https://openalex.org/W2952813363","https://openalex.org/W2748667022","https://openalex.org/W2911497689","https://openalex.org/W3211770882","https://openalex.org/W4360783045","https://openalex.org/W2963346891","https://openalex.org/W3176438653","https://openalex.org/W2770149305","https://openalex.org/W2010629964"],"abstract_inverted_index":{"In":[0],"this":[1,132],"paper,":[2],"we":[3,114,208],"present":[4],"an":[5,120,126],"efficient":[6],"approach":[7],"for":[8,17,144,186],"audio":[9,189],"scene":[10,18,48,67],"classification.":[11,187],"We":[12,73,90,123,134,231],"aim":[13,135],"at":[14,136],"learning":[15,138,195,226],"representations":[16],"examples":[19],"by":[20,34],"exploring":[21],"the":[22,41,60,63,66,71,93,145,170,180,213,217,220,224,249,256,259],"structure":[23],"of":[24,40,59,95,219,258],"their":[25,88],"class":[26],"labels.":[27],"A":[28,47],"category":[29],"taxonomy":[30],"is":[31,50,98],"automatically":[32,137],"learned":[33,80,171],"collectively":[35],"optimizing":[36],"a":[37,54,165,174],"tree-structured":[38],"clustering":[39],"given":[42],"labels":[43],"into":[44,53,216],"multiple":[45,96],"metaclasses.":[46,72],"recording":[49],"then":[51,162],"transformed":[52],"label-tree":[55,77,106,175,205,240],"embedding":[56,78,107,176,206,241],"image.":[57],"Elements":[58],"image":[61,177],"represent":[62],"likelihoods":[64,218],"that":[65,92,116,141,168],"instance":[68],"belongs":[69],"to":[70,100,130],"investigate":[74],"classification":[75,128,146],"with":[76],"features":[79,84,97,185,200,215],"from":[81,148],"different":[82],"low-level":[83,199,214],"as":[85,87,164,184],"well":[86],"fusion.":[89],"show":[91],"combination":[94],"essential":[99],"obtain":[101],"good":[102,112],"performance.":[103],"While":[104],"averaging":[105],"images":[108,150,242],"over":[109],"time":[110],"yields":[111],"performance,":[113],"argue":[115],"average":[117],"pooling":[118],"possesses":[119],"intrinsic":[121],"shortcoming.":[122],"alternatively":[124],"propose":[125],"improved":[127],"scheme":[129],"bypass":[131],"limitation.":[133],"common":[139],"templates":[140,172],"are":[142,161,229],"useful":[143],"task":[147],"these":[149],"using":[151],"simple":[152],"but":[153],"tailored":[154],"convolutional":[155,235],"neural":[156,236],"networks.":[157,245],"The":[158],"trained":[159],"networks":[160,237],"employed":[163],"feature":[166],"extractor":[167],"matches":[169],"across":[173],"and":[178,196,211,227,243,251],"produce":[179],"maximum":[181],"matching":[182,197,228],"scores":[183],"Since":[188],"scenes":[190],"exhibit":[191],"rich":[192],"content,":[193],"template":[194,225],"on":[198,222,238,248],"would":[201],"be":[202],"inefficient.":[203],"With":[204],"features,":[207],"have":[209],"quantized":[210],"reduced":[212],"metaclasses,":[221],"which":[223],"efficient.":[230],"study":[232],"both":[233],"training":[234],"stacked":[239],"multistream":[244],"Experimental":[246],"results":[247],"DCASE2016":[250],"LITIS":[252],"Rouen":[253],"datasets":[254],"demonstrate":[255],"efficiency":[257],"proposed":[260],"methods.":[261]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}