{"id":"https://openalex.org/W2962922588","doi":"https://doi.org/10.1109/icassp.2017.7952133","title":"CNN-LTE: A class of 1-X pooling convolutional neural networks on label tree embeddings for audio scene classification","display_name":"CNN-LTE: A class of 1-X pooling convolutional neural networks on label tree embeddings for audio scene classification","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2962922588","doi":"https://doi.org/10.1109/icassp.2017.7952133","mag":"2962922588"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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":["Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School for Computing in Medicine and Life Sciences, University of 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, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of 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, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of 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, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of 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, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of 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, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Signal Processing, University of 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":2.0543,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.88760748,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"136","last_page":"140"},"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":0.9997000098228455,"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":0.9947999715805054,"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/pooling","display_name":"Pooling","score":0.849153459072113},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7771549224853516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7283644676208496},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7234178781509399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7006142139434814},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5871598720550537},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5595118999481201},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5570670366287231},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5448683500289917},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5140367746353149},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45965829491615295},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.42091965675354004},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.41260504722595215},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13665664196014404},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.10511577129364014}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.849153459072113},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7771549224853516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283644676208496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7234178781509399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7006142139434814},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5871598720550537},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5595118999481201},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5570670366287231},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5448683500289917},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5140367746353149},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45965829491615295},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.42091965675354004},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.41260504722595215},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13665664196014404},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.10511577129364014},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2017.7952133","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:72673","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ICASSP.2017.7952133>)","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1832693441","https://openalex.org/W1976258180","https://openalex.org/W1978274651","https://openalex.org/W1979594949","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/W2095147901","https://openalex.org/W2095705004","https://openalex.org/W2103235956","https://openalex.org/W2114777924","https://openalex.org/W2130640900","https://openalex.org/W2137343183","https://openalex.org/W2142194269","https://openalex.org/W2156387975","https://openalex.org/W2156481234","https://openalex.org/W2157498370","https://openalex.org/W2158336491","https://openalex.org/W2162931300","https://openalex.org/W2212106655","https://openalex.org/W2214128417","https://openalex.org/W2403172465","https://openalex.org/W2404382656","https://openalex.org/W2472122037","https://openalex.org/W2566935005","https://openalex.org/W2911964244","https://openalex.org/W2963158330","https://openalex.org/W2964121744","https://openalex.org/W3099869713","https://openalex.org/W3103385400","https://openalex.org/W4233392025","https://openalex.org/W6631190155","https://openalex.org/W6645021456","https://openalex.org/W6674330103","https://openalex.org/W6682889407","https://openalex.org/W6683965311","https://openalex.org/W6713358509"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W147410782","https://openalex.org/W2748667022","https://openalex.org/W3211770882","https://openalex.org/W2010629964","https://openalex.org/W2983135586","https://openalex.org/W2565656575"],"abstract_inverted_index":{"We":[0],"present":[1],"in":[2,38,43],"this":[3],"work":[4],"an":[5,45],"approach":[6],"for":[7,89,103],"audio":[8,46],"scene":[9,47,66,104],"classification.":[10],"Firstly,":[11],"given":[12],"the":[13,17,26,39,59,62,65,90,100,109,117,120],"label":[14,20,53],"set":[15],"of":[16,58,74,99,119],"scenes,":[18],"a":[19,52],"tree":[21,54],"is":[22,35,49],"automatically":[23],"constructed":[24],"where":[25],"labels":[27],"are":[28,87,94],"grouped":[29],"into":[30,51],"meta-classes.":[31,71],"This":[32],"category":[33],"taxonomy":[34],"then":[36],"used":[37],"feature":[40],"extraction":[41],"step":[42],"which":[44,86],"instance":[48],"transformed":[50],"embedding":[55],"image.":[56],"Elements":[57],"image":[60,101],"indicate":[61],"likelihoods":[63],"that":[64],"instances":[67],"belong":[68],"to":[69],"different":[70],"A":[72],"class":[73],"simple":[75],"1-X":[76],"(i.e.":[77],"1-max,":[78],"1-mean,":[79],"and":[80,112],"1-mix)":[81],"pooling":[82],"convolutional":[83],"neural":[84],"networks,":[85],"tailored":[88],"task":[91],"at":[92],"hand,":[93],"finally":[95],"learned":[96],"on":[97,108],"top":[98],"features":[102],"recognition.":[105],"Experimental":[106],"results":[107],"DCASE":[110,113],"2013":[111],"2016":[114],"datasets":[115],"demonstrate":[116],"efficiency":[118],"proposed":[121],"method.":[122]},"counts_by_year":[{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}