{"id":"https://openalex.org/W2295707189","doi":"https://doi.org/10.1109/taslp.2016.2530401","title":"Learning Representations for Nonspeech Audio Events Through Their Similarities to Speech Patterns","display_name":"Learning Representations for Nonspeech Audio Events Through Their Similarities to Speech Patterns","publication_year":2016,"publication_date":"2016-02-15","ids":{"openalex":"https://openalex.org/W2295707189","doi":"https://doi.org/10.1109/taslp.2016.2530401","mag":"2295707189"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2016.2530401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2530401","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":["Graduate School for Computing in Medicine and Life Sciences, University of L\u00fcbeck, L\u00fcbeck, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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/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":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5736,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93509235,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"4","first_page":"807","last_page":"822"},"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":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7791343331336975},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6426061391830444},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6405851244926453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4555954933166504},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4337959587574005},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4294564723968506},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.4151194989681244},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.4137878119945526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3750126361846924},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3485507369041443},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.24711361527442932},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09761437773704529}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791343331336975},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6426061391830444},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6405851244926453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4555954933166504},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4337959587574005},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4294564723968506},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.4151194989681244},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.4137878119945526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3750126361846924},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3485507369041443},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.24711361527442932},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09761437773704529},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2016.2530401","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2016.2530401","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:72684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/TASLP.2016.2530401>)","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":95,"referenced_works":["https://openalex.org/W273093436","https://openalex.org/W795299307","https://openalex.org/W811578723","https://openalex.org/W837720621","https://openalex.org/W1553004968","https://openalex.org/W1622490909","https://openalex.org/W1837649128","https://openalex.org/W1964442016","https://openalex.org/W1964538581","https://openalex.org/W1966273763","https://openalex.org/W1970578576","https://openalex.org/W1979447841","https://openalex.org/W1985242443","https://openalex.org/W1987011838","https://openalex.org/W1995562189","https://openalex.org/W2005122913","https://openalex.org/W2008415856","https://openalex.org/W2009504845","https://openalex.org/W2021096090","https://openalex.org/W2024490156","https://openalex.org/W2046972719","https://openalex.org/W2048174296","https://openalex.org/W2052711563","https://openalex.org/W2062340927","https://openalex.org/W2065529590","https://openalex.org/W2077159900","https://openalex.org/W2077804127","https://openalex.org/W2084534958","https://openalex.org/W2089390156","https://openalex.org/W2090431713","https://openalex.org/W2092216166","https://openalex.org/W2100551412","https://openalex.org/W2102381086","https://openalex.org/W2102381657","https://openalex.org/W2103235956","https://openalex.org/W2105068979","https://openalex.org/W2107789863","https://openalex.org/W2109743529","https://openalex.org/W2112020727","https://openalex.org/W2119662931","https://openalex.org/W2127612600","https://openalex.org/W2129634963","https://openalex.org/W2130640900","https://openalex.org/W2133824856","https://openalex.org/W2137919539","https://openalex.org/W2142194269","https://openalex.org/W2142416747","https://openalex.org/W2151316819","https://openalex.org/W2151941172","https://openalex.org/W2154221499","https://openalex.org/W2155144632","https://openalex.org/W2157821739","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2162915993","https://openalex.org/W2164535072","https://openalex.org/W2165712214","https://openalex.org/W2165874743","https://openalex.org/W2165880886","https://openalex.org/W2166435644","https://openalex.org/W2166637769","https://openalex.org/W2179324675","https://openalex.org/W2184045248","https://openalex.org/W2184687474","https://openalex.org/W2186582651","https://openalex.org/W2296610835","https://openalex.org/W2315268655","https://openalex.org/W2396889081","https://openalex.org/W2398456099","https://openalex.org/W2398880078","https://openalex.org/W2404382656","https://openalex.org/W2408491073","https://openalex.org/W2561557072","https://openalex.org/W2911964244","https://openalex.org/W2963922351","https://openalex.org/W3103385400","https://openalex.org/W3215500402","https://openalex.org/W4298018175","https://openalex.org/W4300939116","https://openalex.org/W6622761867","https://openalex.org/W6623298498","https://openalex.org/W6639003370","https://openalex.org/W6676071220","https://openalex.org/W6678951767","https://openalex.org/W6682352165","https://openalex.org/W6682939927","https://openalex.org/W6684067080","https://openalex.org/W6684578312","https://openalex.org/W6686280200","https://openalex.org/W6697451111","https://openalex.org/W6712356201","https://openalex.org/W6712405843","https://openalex.org/W6712469065","https://openalex.org/W6713358509","https://openalex.org/W6714426239"],"related_works":["https://openalex.org/W2312675527","https://openalex.org/W3159882232","https://openalex.org/W4241650944","https://openalex.org/W4243125559","https://openalex.org/W4241778367","https://openalex.org/W2752054555","https://openalex.org/W2527828870","https://openalex.org/W2184127972","https://openalex.org/W4238262908","https://openalex.org/W4214489098"],"abstract_inverted_index":{"The":[0,97,224],"human":[1,10,20],"auditory":[2],"system":[3],"is":[4,70,247],"very":[5],"well":[6],"matched":[7],"to":[8,42,71,89,93,106,123,165,205,260],"both":[9],"speech":[11,21,48,82,95,98,126,142,182,203],"and":[12,56,84,222],"environmental":[13],"sounds.":[14],"Therefore,":[15],"the":[16,58,67,81,86,91,94,108,125,141,177,188,197,207,228,252,265],"question":[17],"arises":[18],"whether":[19],"material":[22],"may":[23],"provide":[24],"useful":[25],"information":[26],"for":[27,30,155,187,209],"training":[28],"systems":[29],"analyzing":[31],"nonspeech":[32,60,68],"audio":[33,191,210],"signals,":[34],"e.g.,":[35],"in":[36],"a":[37,77,104,115,130,152,167,234,243],"classification":[38,87,230],"task.":[39],"In":[40],"order":[41],"answer":[43],"this":[44],"question,":[45],"we":[46,73,161],"consider":[47],"patterns":[49,83,204],"as":[50,103,151,202,255],"basic":[51],"acoustic":[52],"concepts,":[53],"which":[54,170],"embody":[55],"represent":[57,90,107],"target":[59,109,267],"signal.":[61,110],"To":[62],"find":[63],"out":[64],"how":[65],"similar":[66],"signal":[69],"speech,":[72],"classify":[74],"it":[75,147],"with":[76,129,216],"classifier":[78,143,246],"trained":[79],"on":[80,227,263],"use":[85],"posteriors":[88],"closeness":[92],"bases.":[96],"similarities":[99],"are":[100,136],"finally":[101],"employed":[102,150],"descriptor":[105,117],"We":[111,184],"further":[112],"show":[113,232],"that":[114,233],"better":[116],"can":[118,148,237],"be":[119,149,238],"obtained":[120,240],"by":[121],"learning":[122],"organize":[124],"categories":[127],"hierarchically":[128],"tree":[131],"structure.":[132],"Furthermore,":[133,249],"these":[134],"descriptors":[135,208,254],"generic.":[137],"That":[138],"is,":[139],"once":[140],"has":[144],"been":[145],"learned,":[146],"feature":[153],"extractor":[154],"different":[156,214,217],"datasets":[157,215],"without":[158],"retraining.":[159],"Lastly,":[160],"propose":[162],"an":[163,172,256],"algorithm":[164],"select":[166],"sufficient":[168],"subset,":[169],"provides":[171],"approximate":[173],"representation":[174],"capability":[175],"of":[176,180,190,212,251],"entire":[178],"set":[179],"available":[181],"patterns.":[183],"conduct":[185],"experiments":[186],"application":[189],"event":[192,229],"analysis.":[193],"Phone":[194],"triplets":[195],"from":[196],"TIMIT":[198],"dataset":[199],"were":[200],"used":[201],"learn":[206],"events":[211],"three":[213,266],"complexity,":[218],"including":[219],"UPC-TALP,":[220],"Freiburg-106,":[221],"NAR.":[223],"experimental":[225],"results":[226],"task":[231],"good":[235],"performance":[236,262],"easily":[239],"even":[241],"if":[242],"simple":[244],"linear":[245],"used.":[248],"fusion":[250],"learned":[253],"additional":[257],"source":[258],"leads":[259],"state-of-the-art":[261],"all":[264],"datasets.":[268]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}