{"id":"https://openalex.org/W1988052084","doi":"https://doi.org/10.1109/slt.2014.7078632","title":"Variable-activation and variable-input deep neural network for robust speech recognition","display_name":"Variable-activation and variable-input deep neural network for robust speech recognition","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1988052084","doi":"https://doi.org/10.1109/slt.2014.7078632","mag":"1988052084"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5101987526","display_name":"Rui Zhao","orcid":"https://orcid.org/0000-0002-9699-9984"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rui Zhao","raw_affiliation_strings":["Microsoft Search Technology Center Asia, Beijing, China","Microsoft Search Technol. Center Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Search Technology Center Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Search Technol. Center Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"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":["One Microsoft Way, Microsoft Corporation, Redmond, WA","Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, 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/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"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":["One Microsoft Way, Microsoft Corporation, Redmond, WA","Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA"],"affiliations":[{"raw_affiliation_string":"One Microsoft Way, 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":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101987526"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":2.045,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.88806921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"9","issue":null,"first_page":"542","last_page":"547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9997000098228455,"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":0.9980999827384949,"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/robustness","display_name":"Robustness (evolution)","score":0.6559199690818787},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6375206112861633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.603060781955719},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5859674215316772},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5519499182701111},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5393834114074707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5357640385627747},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.42085063457489014},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.406546950340271},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35817307233810425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2922847270965576}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6559199690818787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6375206112861633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.603060781955719},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5859674215316772},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5519499182701111},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5393834114074707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5357640385627747},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.42085063457489014},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.406546950340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35817307233810425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2922847270965576},{"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},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2014.7078632","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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":27,"referenced_works":["https://openalex.org/W217970951","https://openalex.org/W1984541135","https://openalex.org/W1988843652","https://openalex.org/W1992475611","https://openalex.org/W2012897754","https://openalex.org/W2035576074","https://openalex.org/W2062164080","https://openalex.org/W2076794394","https://openalex.org/W2125562481","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2187089797","https://openalex.org/W2187519021","https://openalex.org/W2213952365","https://openalex.org/W2296748324","https://openalex.org/W2394967684","https://openalex.org/W2401131605","https://openalex.org/W2408592723","https://openalex.org/W2964138484","https://openalex.org/W4232737908","https://openalex.org/W6608710415","https://openalex.org/W6687075232","https://openalex.org/W6688428952","https://openalex.org/W6711908631","https://openalex.org/W6713796627","https://openalex.org/W6814791301"],"related_works":["https://openalex.org/W2180954594","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"In":[0,98],"a":[1,30,144],"previous":[2],"study,":[3,100],"we":[4,101],"proposed":[5],"variable-component":[6],"deep":[7,17],"neural":[8,18],"network":[9,19],"(VCDNN)":[10],"to":[11,123,135,150],"improve":[12],"the":[13,26,58,82,87,94,124,136,151,181,185],"robustness":[14],"of":[15,28,32,35,49,60,89,106,147,172,190],"context-dependent":[16],"hidden":[20,125],"Markov":[21],"model":[22,25],"(CD-DNN-HMM).":[23],"We":[24,43],"components":[27],"DNN":[29,50,69,73,111,116,183],"set":[31],"polynomial":[33],"functions":[34],"environmental":[36],"variables,":[37],"more":[38],"specifically":[39],"signal-to-noise":[40],"ratio":[41],"(SNR).":[42],"refined":[44],"VCDNN":[45,173],"on":[46,156],"two":[47,64,103],"types":[48,105],"components:":[51],"(1)":[52],"weighting":[53],"matrix":[54],"and":[55,71,113,131,165],"bias":[56],"(2)":[57],"output":[59],"each":[61],"layer.":[62],"These":[63],"methods":[65,77,162],"are":[66,163],"called":[67],"variable-parameter":[68],"(VPDNN)":[70],"variable-output":[72],"(VODNN).":[74],"Although":[75],"both":[76,161],"got":[78],"good":[79],"gain":[80],"over":[81],"standard":[83,152,182],"DNN,":[84],"they":[85],"doubled":[86],"number":[88,146,189],"parameters":[90,148],"even":[91],"with":[92,174,184],"only":[93,142],"first-order":[95],"environment":[96,119],"variable.":[97],"this":[99],"propose":[102],"new":[104],"VCDNN,":[107],"namely":[108],"variable":[109,114,120],"activation":[110,127],"(VADNN)":[112],"input":[115,137],"(VIDNN).":[117],"The":[118],"is":[121,132],"applied":[122,133],"layer":[126],"function":[128],"in":[129,138,188],"VADNN,":[130],"directly":[134],"VIDNN.":[139],"Both":[140],"DNNs":[141],"increase":[143,187],"negligible":[145],"compared":[149],"DNN.":[153],"Experimental":[154],"results":[155],"Aurora4":[157],"task":[158],"show":[159],"that":[160],"effective,":[164],"VIDNN":[166],"can":[167],"beat":[168],"all":[169],"other":[170],"variations":[171],"relative":[175],"7.69%":[176],"word":[177],"error":[178],"reduction":[179],"from":[180],"least":[186],"parameters.":[191]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}