{"id":"https://openalex.org/W2786215303","doi":"https://doi.org/10.1109/apsipa.2017.8281995","title":"Acoustic scene classification using self-determination convolutional neural network","display_name":"Acoustic scene classification using self-determination convolutional neural network","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786215303","doi":"https://doi.org/10.1109/apsipa.2017.8281995","mag":"2786215303"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8281995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8281995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/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":true,"raw_author_name":"Chien-Yao Wang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, 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, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","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, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072470661"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60822466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1312 4400","issue":null,"first_page":"019","last_page":"022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987999796867371,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8586162328720093},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.621128261089325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5812812447547913},{"id":"https://openalex.org/keywords/scene-statistics","display_name":"Scene statistics","score":0.5388097763061523},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.48401519656181335},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.4815381169319153},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4505701959133148},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4262346029281616},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36475899815559387},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35130083560943604},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.07848775386810303},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.07318219542503357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586162328720093},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.621128261089325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5812812447547913},{"id":"https://openalex.org/C197654239","wikidata":"https://www.wikidata.org/wiki/Q7430757","display_name":"Scene statistics","level":3,"score":0.5388097763061523},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.48401519656181335},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.4815381169319153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4505701959133148},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4262346029281616},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36475899815559387},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35130083560943604},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.07848775386810303},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.07318219542503357},{"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/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8281995","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8281995","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.699999988079071,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2100495367","https://openalex.org/W2107034620","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2125574651","https://openalex.org/W2127807804","https://openalex.org/W2130640900","https://openalex.org/W2200864288","https://openalex.org/W2403172465","https://openalex.org/W2566935005","https://openalex.org/W2963911037","https://openalex.org/W6638444622"],"related_works":["https://openalex.org/W2348837382","https://openalex.org/W746329893","https://openalex.org/W4205872570","https://openalex.org/W4245971243","https://openalex.org/W1922805944","https://openalex.org/W4253588120","https://openalex.org/W2383732295","https://openalex.org/W2942717012","https://openalex.org/W4248716494","https://openalex.org/W2162226802"],"abstract_inverted_index":{"A":[0],"practical":[1],"acoustic":[2,140],"scene":[3,9,62,76],"classification":[4,97],"(ASC)":[5],"system":[6,27,98,114,162],"identifies":[7],"the":[8,14,21,31,41,69,72,81,102,127,138,153,158],"of":[10,16,74,83,107,160],"environment":[11,35,91],"by":[12,94,126],"analyzing":[13],"properties":[15],"audio":[17,38,56,109],"data":[18,57,103],"that":[19,99,166],"characterize":[20],"surroundings.":[22],"Proposing":[23],"a":[24,47,96],"robust":[25],"ASC":[26,113,145],"is":[28,92,115,124,135],"challenging":[29],"as":[30],"sound":[32],"from":[33,54,86],"natural":[34,90],"compromises":[36],"various":[37,75,87],"sources":[39,88],"and":[40,123,150],"microphones":[42],"are":[43,58],"not":[44,51],"arranged":[45],"in":[46,89,129,152,170],"controlled":[48],"condition.":[49],"Furthermore,":[50],"all":[52],"sounds":[53,65],"long-duration":[55,108],"relevant":[59],"for":[60,104],"identifying":[61],"label.":[63],"Some":[64],"may":[66],"contribute":[67],"to":[68,101],"noises":[70],"or":[71],"mix":[73],"labels.":[77],"In":[78],"this":[79,171],"work,":[80],"problem":[82],"mixed":[84],"information":[85],"addressed":[93],"proposing":[95],"adapts":[100],"each":[105],"frames":[106],"data.":[110],"The":[111,155],"proposed":[112,161],"designed":[116],"based":[117,121],"on":[118,137],"deep":[119],"learning":[120],"approach,":[122],"motivated":[125],"researches":[128],"computer":[130],"vision":[131],"field.":[132],"Our":[133],"method":[134],"evaluated":[136],"TUT":[139],"scenes":[141],"2016":[142],"dataset.":[143],"Several":[144],"systems":[146,165],"have":[147,167],"been":[148,168],"implemented":[149],"discussed":[151,169],"experiments.":[154],"results":[156],"show":[157],"superiority":[159],"versus":[163],"another":[164],"work.":[172]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}