{"id":"https://openalex.org/W2188612176","doi":"https://doi.org/10.1109/mmsp.2015.7340807","title":"Audio event recognition based on DBN features from multiple filter-bank representations","display_name":"Audio event recognition based on DBN features from multiple filter-bank representations","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2188612176","doi":"https://doi.org/10.1109/mmsp.2015.7340807","mag":"2188612176"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2015.7340807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2015.7340807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)","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/A5023315591","display_name":"Feng Guo","orcid":"https://orcid.org/0000-0002-7468-5634"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feng Guo","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, 128 Zhongguancun North Street, Haidian District, Beijing 100871, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, 128 Zhongguancun North Street, Haidian District, Beijing 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017207620","display_name":"Xiaoou Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoou Chen","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, 128 Zhongguancun North Street, Haidian District, Beijing 100871, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, 128 Zhongguancun North Street, Haidian District, Beijing 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100885747","display_name":"Deshun Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deshun Yang","raw_affiliation_strings":["Institute of Computer Science & Technology, Peking University, 128 Zhongguancun North Street, Haidian District, Beijing 100871, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science & Technology, Peking University, 128 Zhongguancun North Street, Haidian District, Beijing 100871, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5023315591"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10873368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9879999756813049,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9854000210762024,"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":0.7353106737136841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6600005626678467},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5960180759429932},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.5856305360794067},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.541500449180603},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5393438339233398},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.5370515584945679},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5288066864013672},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5050047039985657},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4656537175178528},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.45450761914253235},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.43946096301078796},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43319615721702576},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4301994740962982},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.39845216274261475},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.27079612016677856},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.17269733548164368},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15452519059181213},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08828678727149963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353106737136841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6600005626678467},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5960180759429932},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.5856305360794067},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.541500449180603},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5393438339233398},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.5370515584945679},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5288066864013672},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5050047039985657},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4656537175178528},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.45450761914253235},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43946096301078796},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43319615721702576},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4301994740962982},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.39845216274261475},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27079612016677856},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.17269733548164368},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15452519059181213},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08828678727149963},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2015.7340807","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2015.7340807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W285519105","https://openalex.org/W1984541135","https://openalex.org/W1988790447","https://openalex.org/W2107789863","https://openalex.org/W2118230268","https://openalex.org/W2125610452","https://openalex.org/W2130325614","https://openalex.org/W2136922672","https://openalex.org/W2158762315","https://openalex.org/W2160860215","https://openalex.org/W2166661046","https://openalex.org/W2172213580","https://openalex.org/W2295991281","https://openalex.org/W2398456099","https://openalex.org/W2963399116"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2088690926","https://openalex.org/W2098934641"],"abstract_inverted_index":{"In":[0,101,114,156],"the":[1,9,12,31,48,53,56,62,75,79,84,112,115,123,136,141,157,164,169,178,186,196,220],"audio":[2,13,54,81,99,137,174,202],"event":[3,138,203],"classification":[4,166,204],"or":[5],"detection":[6],"research":[7],"field,":[8],"representation":[10,51,77],"of":[11,30,52,59,78,122,128,143,168,216,226],"itself":[14],"is":[15,38,44],"important.":[16],"Many":[17],"researchers":[18],"tried":[19],"to":[20,26,96,108,131,162,181],"apply":[21],"Deep":[22],"Belief":[23],"Network":[24],"(DBN)":[25],"learn":[27,97],"new":[28],"representations":[29],"audio.":[32],"The":[33],"mel":[34,42,63,67,147],"filter-bank":[35,68],"feature,":[36],"which":[37,206],"obtained":[39],"based":[40],"on":[41,172,188],"scale,":[43],"commonly":[45],"used":[46,65],"as":[47],"low":[49],"level":[50],"in":[55,66,83,135,160],"pre-processing":[57],"procedure":[58],"DBN.":[60],"However,":[61],"bands":[64,130,145,152],"feature":[69,133,228],"may":[70],"not":[71],"be":[72],"sufficient":[73],"for":[74,94],"comprehensive":[76],"diverse":[80,208],"events":[82],"real":[85,189],"world":[86],"and":[87,110,153,195],"then":[88],"it":[89,92],"will":[90],"make":[91],"difficult":[93],"DBN":[95,132,170,217,227],"good":[98],"features.":[100],"this":[102],"paper,":[103],"two":[104],"steps":[105],"are":[106],"taken":[107],"explore":[109],"tackle":[111],"problem.":[113],"first":[116],"step,":[117,159],"we":[118,176],"conduct":[119,185],"a":[120],"comparison":[121],"effects":[124],"among":[125],"different":[126,165,173],"arrangements":[127,142],"frequency":[129,144],"learning":[134],"recognition.":[139],"Here":[140],"include":[146],"bands,":[148,150],"bark":[149],"linear":[151],"pyramid":[154],"bands.":[155],"second":[158],"order":[161],"utilize":[163],"capabilities":[167],"features":[171,209],"events,":[175],"adopt":[177],"Adaboost":[179,212],"algorithm":[180],"fuse":[182],"them.":[183],"We":[184],"experiments":[187],"datasets":[190],"collected":[191],"from":[192,213],"findsound":[193],"website,":[194],"results":[197],"verifies":[198],"that":[199],"our":[200],"proposed":[201],"system,":[205],"uses":[207],"selected":[210],"by":[211],"all":[214],"sets":[215],"features,":[218],"outperforms":[219],"one":[221,224],"using":[222],"only":[223],"kind":[225],"set.":[229]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}