{"id":"https://openalex.org/W1555696814","doi":"https://doi.org/10.1109/icassp.2015.7178920","title":"An analysis of convolutional neural networks for speech recognition","display_name":"An analysis of convolutional neural networks for speech recognition","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1555696814","doi":"https://doi.org/10.1109/icassp.2015.7178920","mag":"1555696814"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5045413298","display_name":"Jui-Ting Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jui-Ting Huang","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA","Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA","Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA","Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045413298"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":20.0971,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":{"value":0.9933541,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4989","last_page":"4993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.831886887550354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8265471458435059},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6668509244918823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6221049427986145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5786044597625732},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5165433287620544},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4941594898700714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45935535430908203},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.453429639339447},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.41625267267227173},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32096782326698303}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.831886887550354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8265471458435059},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6668509244918823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6221049427986145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5786044597625732},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5165433287620544},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4941594898700714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45935535430908203},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.453429639339447},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.41625267267227173},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32096782326698303},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W587565084","https://openalex.org/W1499864241","https://openalex.org/W1541452272","https://openalex.org/W1984541135","https://openalex.org/W1995562189","https://openalex.org/W2035424729","https://openalex.org/W2061305730","https://openalex.org/W2076794394","https://openalex.org/W2103088716","https://openalex.org/W2105728138","https://openalex.org/W2112739286","https://openalex.org/W2125496931","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2293634267","https://openalex.org/W2294059674","https://openalex.org/W2296516251","https://openalex.org/W2402040300","https://openalex.org/W2404068704","https://openalex.org/W2404926044","https://openalex.org/W2405787239","https://openalex.org/W2539797148","https://openalex.org/W2962719052","https://openalex.org/W2964138484","https://openalex.org/W6608710415","https://openalex.org/W6617215739","https://openalex.org/W6632326908","https://openalex.org/W6675897241","https://openalex.org/W6688428952","https://openalex.org/W6696761078","https://openalex.org/W6696934422","https://openalex.org/W6697811694","https://openalex.org/W6712847557","https://openalex.org/W6713450916","https://openalex.org/W6713989789","https://openalex.org/W6728770099"],"related_works":["https://openalex.org/W4312417841","https://openalex.org/W4321369474","https://openalex.org/W2731899572","https://openalex.org/W3133861977","https://openalex.org/W4200173597","https://openalex.org/W2915754718","https://openalex.org/W4299822940","https://openalex.org/W2279398222","https://openalex.org/W3000866861","https://openalex.org/W2955560448"],"abstract_inverted_index":{"Despite":[0],"the":[1,8,38,54,59,138,145,157,165,173],"fact":[2],"that":[3,64,156],"several":[4],"sites":[5],"have":[6],"reported":[7,143],"effectiveness":[9],"of":[10,40,50,113,129,175],"convolutional":[11,60],"neural":[12,89],"networks":[13,90],"(CNNs)":[14],"on":[15,110],"some":[16,47],"tasks,":[17],"there":[18],"is":[19,137,164],"no":[20],"deep":[21,88],"analysis":[22,49],"regarding":[23],"why":[24],"CNNs":[25,81,148],"perform":[26],"well":[27],"and":[28,100],"in":[29,58,67,144],"which":[30],"case":[31],"we":[32,62,79,154],"should":[33],"see":[34],"CNNs'":[35],"advantage.":[36],"In":[37],"light":[39],"this,":[41],"this":[42,136],"paper":[43],"aims":[44],"to":[45,149,179],"provide":[46,84],"detailed":[48],"CNNs.":[51],"By":[52],"visualizing":[53],"localized":[55],"filters":[56],"learned":[57],"layer,":[61],"show":[63,150],"edge":[65],"detectors":[66],"varying":[68],"directions":[69],"can":[70,82],"be":[71],"automatically":[72],"learned.":[73],"We":[74],"then":[75],"identify":[76],"four":[77],"domains":[78],"think":[80],"consistently":[83],"advantages":[85],"over":[86,126],"fully-connected":[87],"(DNNs):":[91],"channel-mismatched":[92],"training-test":[93],"conditions,":[94],"noise":[95],"robustness,":[96],"distant":[97,104,115],"speech":[98,105,116],"recognition,":[99,106],"low-footprint":[101],"models.":[102],"For":[103],"a":[107,127,130],"CNN":[108,158],"trained":[109],"1000":[111],"hours":[112],"Kinect":[114],"data":[117],"obtains":[118],"relative":[119,184],"4%":[120],"word":[121],"error":[122],"rate":[123],"reduction":[124],"(WERR)":[125],"DNN":[128],"similar":[131],"size.":[132],"To":[133],"our":[134],"knowledge,":[135],"largest":[139],"corpus":[140],"so":[141],"far":[142],"literature":[146],"for":[147,172],"its":[151],"effectiveness.":[152],"Lastly,":[153],"establish":[155],"structure":[159],"combined":[160],"with":[161,189],"maxout":[162],"units":[163],"most":[166],"effective":[167],"model":[168],"under":[169],"small-sizing":[170],"constraints":[171],"purpose":[174],"deploying":[176],"small-footprint":[177],"models":[178],"devices.":[180],"This":[181],"setup":[182],"gives":[183],"9.3%":[185],"WERR":[186],"from":[187],"DNNs":[188],"sigmoid":[190],"units.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":6}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}