{"id":"https://openalex.org/W2735380212","doi":"https://doi.org/10.1109/ijcnn.2017.7966232","title":"An investigation of high-resolution modeling units of deep neural networks for acoustic scene classification","display_name":"An investigation of high-resolution modeling units of deep neural networks for acoustic scene classification","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2735380212","doi":"https://doi.org/10.1109/ijcnn.2017.7966232","mag":"2735380212"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7966232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","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/A5044224230","display_name":"Xiao Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Bao","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590046","display_name":"Tian Gao","orcid":"https://orcid.org/0000-0002-9523-5560"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Gao","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044224230"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3698,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.5646174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3028","last_page":"3035"},"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":0.9995999932289124,"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":0.9983999729156494,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8607136011123657},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.8116006851196289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7428584098815918},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6322540044784546},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6177259087562561},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5390315651893616},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46410831809043884},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45622238516807556},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4555680453777313},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.44502684473991394},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44192183017730713},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.2711016535758972},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.14732813835144043}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8607136011123657},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.8116006851196289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428584098815918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6322540044784546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6177259087562561},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5390315651893616},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46410831809043884},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45622238516807556},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4555680453777313},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.44502684473991394},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44192183017730713},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2711016535758972},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.14732813835144043},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2017.7966232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7966232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W330298975","https://openalex.org/W1524333225","https://openalex.org/W1837649128","https://openalex.org/W2086384421","https://openalex.org/W2100495367","https://openalex.org/W2103235956","https://openalex.org/W2107456423","https://openalex.org/W2136922672","https://openalex.org/W2137343183","https://openalex.org/W2160815625","https://openalex.org/W2165409492","https://openalex.org/W2212106655","https://openalex.org/W2396495723","https://openalex.org/W2528286866","https://openalex.org/W2566935005","https://openalex.org/W2604293017","https://openalex.org/W3103385400","https://openalex.org/W4205947740","https://openalex.org/W4233392025","https://openalex.org/W4256161595","https://openalex.org/W4256399001","https://openalex.org/W6631362777","https://openalex.org/W6639003370","https://openalex.org/W6712515972","https://openalex.org/W6727629558","https://openalex.org/W6736350746"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W2121652828","https://openalex.org/W3033124456","https://openalex.org/W2735380212","https://openalex.org/W2018887914","https://openalex.org/W2785476196"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,121,197,204],"investigate":[4],"high-resolution":[5,206],"modeling":[6,35,132,195,207,232],"units":[7,208],"of":[8,49,74,105,116,126,161,167,188,227,230,240],"deep":[9],"neural":[10],"networks":[11],"(DNNs)":[12],"from":[13,153],"concrete":[14],"to":[15,39,44,52,84,134,163,176,184,224],"abstract":[16,131],"for":[17,37,149],"acoustic":[18,41,87,179,236],"scene":[19,54,88,118,140,189,237],"classification":[20,238],"based":[21],"on":[22,235,259],"Gaussian":[23,109],"mixture":[24],"model":[25,31,85,101,162,177],"(GMM)":[26],"and":[27,107],"ergodic":[28],"hidden":[29],"Markov":[30],"(HMM).":[32],"A":[33],"direct":[34,213],"strategy":[36],"DNN":[38],"classify":[40],"scenes":[42,180],"is":[43,77,80,142,218],"map":[45],"each":[46,86,108,150],"frame":[47],"feature":[48],"an":[50,75],"audio":[51,76],"one":[53,159],"category.":[55],"However,":[56],"all":[57],"frames":[58],"tagged":[59],"with":[60,255],"the":[61,67,71,95,117,124,165,178,185,228],"same":[62],"label":[63],"may":[64],"not":[65],"be":[66,111,173],"best":[68],"choice":[69],"because":[70],"representative":[72,168],"pattern":[73],"sparse.":[78],"GMM":[79,100,127,182,257],"also":[81],"often":[82],"employed":[83],"directly":[89],"as":[90,113,128,158,194],"a":[91,99,114,129,256],"generative":[92],"model.":[93],"Because":[94],"multiple":[96],"Gaussians":[97],"in":[98],"have":[102],"different":[103],"levels":[104],"contribution,":[106],"can":[110,122],"seen":[112],"subclass":[115,125,151],"category,":[119],"so":[120],"utilize":[123],"bit":[130],"unit":[133],"adopt":[135],"DNN-GMM":[136],"system.":[137,201],"When":[138],"single":[139],"category":[141],"subdivided":[143],"into":[144],"various":[145],"subclasses,":[146],"prior":[147],"scores":[148],"calculated":[152],"training":[154],"set":[155],"are":[156,209],"stored":[157],"part":[160],"response":[164],"sparseness":[166],"pattern.":[169],"Ergodic":[170],"HMM":[171,192],"should":[172],"more":[174,210],"appropriate":[175],"than":[181,212],"due":[183],"uncertain":[186],"structure":[187],"audio.":[190],"Using":[191],"states":[193],"units,":[196],"build":[198],"DNN-HMM":[199],"hybrid":[200],"By":[202],"comparison,":[203],"find":[205],"effective":[211],"modeling.":[214],"The":[215],"final":[216,246],"system":[217,222,247],"obtained":[219],"by":[220],"performing":[221],"combination":[223],"take":[225],"advantage":[226],"complementarity":[229],"different-level":[231],"units.":[233],"Experiments":[234],"task":[239],"DCASE2016":[241],"challenge":[242],"show":[243],"that":[244],"our":[245],"yields":[248],"25.9%":[249],"relative":[250],"error":[251],"rate":[252],"reduction":[253],"compared":[254],"baseline":[258],"evaluation":[260],"set.":[261]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}