{"id":"https://openalex.org/W2404382656","doi":"https://doi.org/10.21437/interspeech.2015-682","title":"Representing nonspeech audio signals through speech classification models","display_name":"Representing nonspeech audio signals through speech classification models","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2404382656","doi":"https://doi.org/10.21437/interspeech.2015-682","mag":"2404382656"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-682","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huy Phan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044379875","display_name":"Lars Hertel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lars Hertel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048584044","display_name":"Marco Maa\u00df","orcid":"https://orcid.org/0000-0001-7422-147X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marco Maass","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074089177","display_name":"Radoslaw Mazur","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Radoslaw Mazur","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063948113","display_name":"Alfred Mertins","orcid":"https://orcid.org/0000-0001-5718-577X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alfred Mertins","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7398,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.86134913,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3441","last_page":"3445"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.790318489074707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7262076139450073},{"id":"https://openalex.org/keywords/closeness","display_name":"Closeness","score":0.5466998815536499},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5210503935813904},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5017096996307373},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.49860548973083496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47832322120666504},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44647303223609924},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4463476538658142},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4392598867416382},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4243183434009552},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3201982378959656},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2514187693595886},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08236199617385864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.790318489074707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7262076139450073},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.5466998815536499},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5210503935813904},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5017096996307373},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.49860548973083496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47832322120666504},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44647303223609924},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4463476538658142},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4392598867416382},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4243183434009552},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3201982378959656},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2514187693595886},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08236199617385864},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2015-682","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-682","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:72688","is_oa":false,"landing_page_url":null,"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":28,"referenced_works":["https://openalex.org/W273093436","https://openalex.org/W1964442016","https://openalex.org/W1964538581","https://openalex.org/W2005122913","https://openalex.org/W2009504845","https://openalex.org/W2021096090","https://openalex.org/W2065529590","https://openalex.org/W2084534958","https://openalex.org/W2089390156","https://openalex.org/W2092216166","https://openalex.org/W2102381086","https://openalex.org/W2107789863","https://openalex.org/W2112020727","https://openalex.org/W2130640900","https://openalex.org/W2133824856","https://openalex.org/W2142194269","https://openalex.org/W2155144632","https://openalex.org/W2157821739","https://openalex.org/W2165874743","https://openalex.org/W2165880886","https://openalex.org/W2166435644","https://openalex.org/W2184687474","https://openalex.org/W2186582651","https://openalex.org/W2296610835","https://openalex.org/W2315268655","https://openalex.org/W2396889081","https://openalex.org/W2408491073","https://openalex.org/W2561557072"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W2071828724","https://openalex.org/W2015876361","https://openalex.org/W642007152","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2009814707"],"abstract_inverted_index":{"The":[0,69],"human":[1,10,20],"auditory":[2],"system":[3,147],"is":[4,154],"very":[5],"well":[6],"matched":[7],"to":[8,49,78,95,122,166],"both":[9],"speech":[11,21,62,66,70,98,116],"and":[12,59],"environmental":[13],"sounds.":[14],"Therefore,":[15],"the":[16,53,80,97,109,119,124,127,131,137,145,158],"question":[17],"arises":[18],"whether":[19],"material":[22],"may":[23],"provide":[24],"useful":[25],"information":[26],"for":[27,30,108,126],"training":[28],"systems":[29],"analyzing":[31],"nonspeech":[32,46,57],"audio":[33,110,128],"signals,":[34],"such":[35],"as":[36,75,161],"in":[37],"a":[38,65,76,87,102,150],"recognition":[39,139],"task.":[40],"To":[41],"find":[42],"out":[43],"how":[44],"similar":[45],"signals":[47,58],"are":[48,72],"speech,":[50],"we":[51],"measure":[52],"closeness":[54],"between":[55],"target":[56,81],"different":[60],"basis":[61],"categories":[63,99],"via":[64],"classification":[67],"model.":[68],"similarities":[71],"finally":[73],"employed":[74],"descriptor":[77,89],"represent":[79],"signal.":[82],"We":[83,105],"further":[84],"show":[85],"that":[86],"better":[88],"can":[90],"be":[91],"obtained":[92],"by":[93,114,144],"learning":[94],"organize":[96],"hierarchically":[100],"with":[101],"tree":[103],"structure.":[104],"conduct":[106],"experiments":[107],"event":[111,138],"analysis":[112],"application":[113],"using":[115],"words":[117],"from":[118],"TIMIT":[120],"dataset":[121],"learn":[123],"descriptors":[125,160],"events":[129],"of":[130],"Freiburg-106":[132],"dataset.":[133],"Our":[134],"results":[135],"on":[136],"task":[140],"outperform":[141],"those":[142],"achieved":[143],"best":[146],"even":[148],"though":[149],"simple":[151],"linear":[152],"classifier":[153],"used.":[155],"Furthermore,":[156],"integrating":[157],"learned":[159],"an":[162],"additional":[163],"source":[164],"leads":[165],"improved":[167],"performance.":[168]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}