{"id":"https://openalex.org/W2743986694","doi":"https://doi.org/10.1109/taslp.2017.2738443","title":"Sound Event Recognition Using Auditory-Receptive-Field Binary Pattern and Hierarchical-Diving Deep Belief Network","display_name":"Sound Event Recognition Using Auditory-Receptive-Field Binary Pattern and Hierarchical-Diving Deep Belief Network","publication_year":2017,"publication_date":"2017-08-10","ids":{"openalex":"https://openalex.org/W2743986694","doi":"https://doi.org/10.1109/taslp.2017.2738443","mag":"2743986694"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2738443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2738443","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/A5072470661","display_name":"Chien-Yao Wang","orcid":"https://orcid.org/0000-0002-2946-8972"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Yao Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029325015","display_name":"Jia\u2010Ching Wang","orcid":"https://orcid.org/0000-0003-0024-6732"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jia-Ching Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039165098","display_name":"Andri Santoso","orcid":"https://orcid.org/0000-0002-3899-750X"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Andri Santoso","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043434615","display_name":"Chin-Chin Chiang","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chin-Chin Chiang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan City, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103251327","display_name":"Chung\u2010Hsien Wu","orcid":"https://orcid.org/0000-0002-3947-2123"},"institutions":[{"id":"https://openalex.org/I91807558","display_name":"National Cheng Kung University","ror":"https://ror.org/01b8kcc49","country_code":"TW","type":"education","lineage":["https://openalex.org/I91807558"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsien Wu","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan City, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan City, Taiwan","institution_ids":["https://openalex.org/I91807558"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7351,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94363314,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"26","issue":"8","first_page":"1336","last_page":"1351"},"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":0.9993000030517578,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.983299970626831,"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/spectrogram","display_name":"Spectrogram","score":0.7686914801597595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7228475213050842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.616847038269043},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.607166051864624},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5566478967666626},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5502076148986816},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5467303395271301},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5380996465682983},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48835083842277527},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4840535521507263},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.4578385353088379},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4494915008544922},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4413280487060547},{"id":"https://openalex.org/keywords/receptive-field","display_name":"Receptive field","score":0.4289422631263733},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4147590398788452},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07929334044456482}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7686914801597595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7228475213050842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.616847038269043},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.607166051864624},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5566478967666626},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5502076148986816},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5467303395271301},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5380996465682983},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48835083842277527},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4840535521507263},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.4578385353088379},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4494915008544922},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4413280487060547},{"id":"https://openalex.org/C19071747","wikidata":"https://www.wikidata.org/wiki/Q1755207","display_name":"Receptive field","level":2,"score":0.4289422631263733},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4147590398788452},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07929334044456482},{"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2017.2738443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2738443","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1618108441","https://openalex.org/W1650531274","https://openalex.org/W1929391603","https://openalex.org/W1953428116","https://openalex.org/W1964812476","https://openalex.org/W1970578576","https://openalex.org/W1973683601","https://openalex.org/W1974387177","https://openalex.org/W1981087263","https://openalex.org/W1991464521","https://openalex.org/W2013020033","https://openalex.org/W2034215399","https://openalex.org/W2054139811","https://openalex.org/W2086384421","https://openalex.org/W2089228878","https://openalex.org/W2090431713","https://openalex.org/W2098654823","https://openalex.org/W2103235956","https://openalex.org/W2103279261","https://openalex.org/W2118230268","https://openalex.org/W2118585731","https://openalex.org/W2119662931","https://openalex.org/W2120599713","https://openalex.org/W2126109423","https://openalex.org/W2137561966","https://openalex.org/W2141739745","https://openalex.org/W2145094598","https://openalex.org/W2153937809","https://openalex.org/W2160335114","https://openalex.org/W2160815625","https://openalex.org/W2161755617","https://openalex.org/W2163352848","https://openalex.org/W2163808566","https://openalex.org/W2167136086","https://openalex.org/W2168515119","https://openalex.org/W2182578244","https://openalex.org/W2187089797","https://openalex.org/W2245569228","https://openalex.org/W2285039657","https://openalex.org/W2312381234","https://openalex.org/W2313745396","https://openalex.org/W2566935005","https://openalex.org/W2622742434","https://openalex.org/W2997574889","https://openalex.org/W3148746558","https://openalex.org/W6677656871","https://openalex.org/W6678132999","https://openalex.org/W6681096077","https://openalex.org/W6682665746","https://openalex.org/W6690610466","https://openalex.org/W6739564277"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2324690303","https://openalex.org/W3101844402","https://openalex.org/W1494724239"],"abstract_inverted_index":{"Automatic":[0],"sound":[1,149,178,192],"event":[2,89,179,193],"recognition":[3,143,168],"(SER)":[4],"has":[5,14],"recently":[6],"attracted":[7],"renewed":[8],"interest.":[9],"Although":[10],"practical":[11],"SER":[12,21],"system":[13,105,125,140,159,183,208],"many":[15],"useful":[16],"applications":[17],"in":[18,32,151,191,195,213],"everyday":[19],"life,":[20],"is":[22,60,100,160],"challenging":[23],"owing":[24],"to":[25,46,87,116],"the":[26,33,48,56,64,68,72,95,109,117,135,138,157,176,181,206,210],"variations":[27],"among":[28],"sounds":[29],"and":[30,43,71,189,197],"noises":[31],"real-world":[34,148],"environment.":[35],"This":[36],"paper":[37],"presents":[38],"a":[39,85,101,142],"novel":[40],"feature":[41,114],"extraction":[42],"classification":[44],"method":[45],"solve":[47],"problem":[49],"of":[50,122,145,187],"SER.":[51],"An":[52],"audio-visual":[53],"descriptor,":[54],"called":[55,94],"auditory-receptive-field":[57],"binary":[58],"pattern,":[59],"designed":[61],"based":[62],"on":[63],"spectrogram":[65],"image":[66],"feature,":[67],"cepstral":[69],"features,":[70],"human":[73],"auditory":[74],"receptive":[75],"field":[76],"model.":[77],"The":[78,91,120,201],"extracted":[79],"features":[80],"are":[81],"then":[82],"fed":[83],"into":[84],"classifier":[86],"perform":[88],"classification.":[90],"proposed":[92,124,139,182,207],"classifier,":[93],"hierarchical-diving":[96],"deep":[97,102],"belief":[98],"network,":[99],"neural":[103],"network":[104],"that":[106,205],"hierarchically":[107],"learns":[108],"discriminative":[110],"characteristics":[111],"from":[112],"physical":[113],"representation":[115],"abstract":[118],"concept.":[119],"performance":[121],"our":[123],"was":[126],"verified":[127],"using":[128],"several":[129],"experiments":[130],"under":[131],"various":[132],"conditions.":[133],"Using":[134,175],"RWCP":[136],"dataset,":[137,180],"achieved":[141,166],"rate":[144,169],"99.27%":[146],"for":[147],"data":[150],"105":[152],"categories.":[153],"Under":[154],"noisy":[155],"conditions,":[156],"developed":[158],"very":[161],"robust,":[162],"with":[163,170],"which":[164],"it":[165],"95.06%":[167],"0":[171],"dB":[172],"signal-to-noise":[173],"ratio.":[174],"TUT":[177],"achieves":[184],"error":[185],"rates":[186],"0.81":[188],"0.73":[190],"detection":[194],"home":[196],"residential":[198],"area":[199],"scenes.":[200],"experimental":[202],"results":[203],"reveal":[204],"outperformed":[209],"other":[211],"systems":[212],"this":[214],"field.":[215]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}