{"id":"https://openalex.org/W2921767328","doi":"https://doi.org/10.23919/apsipa.2018.8659707","title":"Stochastic DNN-HMM Training for Robust ASR","display_name":"Stochastic DNN-HMM Training for Robust ASR","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2921767328","doi":"https://doi.org/10.23919/apsipa.2018.8659707","mag":"2921767328"},"language":"en","primary_location":{"id":"doi:10.23919/apsipa.2018.8659707","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5055008722","display_name":"Kang Hyun Lee","orcid":"https://orcid.org/0000-0001-9664-9186"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kang Hyun Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082739860","display_name":"Woo Hyun Kang","orcid":"https://orcid.org/0000-0001-8739-9349"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woo Hyun Kang","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103052875","display_name":"Hyeonseung Lee","orcid":"https://orcid.org/0000-0001-6997-205X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonseung Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and INMC, Seoul National University, Seoul, Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055008722"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.1629,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62168734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1301 3605","issue":null,"first_page":"177","last_page":"182"},"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":0.9998000264167786,"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/computer-science","display_name":"Computer science","score":0.784539520740509},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.594851016998291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5905225276947021},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5884450674057007},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5697796940803528},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5672838091850281},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5596470832824707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5028321146965027},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4790283739566803},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.47442951798439026},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4505794048309326},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4446307122707367},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41889074444770813},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4026067852973938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3451184034347534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784539520740509},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.594851016998291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5905225276947021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5884450674057007},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5697796940803528},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5672838091850281},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5596470832824707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5028321146965027},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4790283739566803},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.47442951798439026},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4505794048309326},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4446307122707367},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41889074444770813},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4026067852973938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3451184034347534},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/apsipa.2018.8659707","is_oa":false,"landing_page_url":"https://doi.org/10.23919/apsipa.2018.8659707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1524333225","https://openalex.org/W1598508708","https://openalex.org/W1973681148","https://openalex.org/W1993882792","https://openalex.org/W2035576074","https://openalex.org/W2050091530","https://openalex.org/W2054566816","https://openalex.org/W2057826000","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2095705004","https://openalex.org/W2113981416","https://openalex.org/W2115630042","https://openalex.org/W2118380238","https://openalex.org/W2121973264","https://openalex.org/W2147768505","https://openalex.org/W2213952365","https://openalex.org/W2296167893","https://openalex.org/W2397725648","https://openalex.org/W2403195671","https://openalex.org/W2665095164","https://openalex.org/W2964138484","https://openalex.org/W3147539069","https://openalex.org/W6631362777","https://openalex.org/W6674330103"],"related_works":["https://openalex.org/W4377865163","https://openalex.org/W2002739602","https://openalex.org/W3193857078","https://openalex.org/W1968042686","https://openalex.org/W2897881820","https://openalex.org/W2345647014","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2201192772"],"abstract_inverted_index":{"Since":[0],"the":[1,32,35,40,45,67,77,80,97,103,107,119,145,149],"introduction":[2],"of":[3,31,34,66,106],"deep":[4,56],"neural":[5],"network":[6],"(DNN)-based":[7],"acoustic":[8,58,99],"model":[9,100],"to":[10,96],"automatic":[11],"speech":[12,109],"recognition":[13],"(ASR),":[14],"robust":[15],"ASR":[16,41],"using":[17,69],"DNN":[18],"are":[19,27],"being":[20],"in":[21,44,101,124],"research.":[22],"However,":[23],"most":[24],"DNN-based":[25,98,151],"techniques":[26,152],"performed":[28],"without":[29],"consideration":[30],"reliability":[33,68],"estimates":[36],"and":[37,63,83,156],"this":[38,50],"degrades":[39],"performance":[42],"especially":[43],"training-test":[46],"mismatch":[47],"conditions.":[48,139,159],"In":[49],"paper,":[51],"we":[52,129],"propose":[53],"a":[54,70,87,91,112],"novel":[55],"learning-based":[57],"modeling":[59,93],"technique":[60,147],"which":[61,131],"measures":[62],"takes":[64],"account":[65],"single":[71],"DNN.":[72],"The":[73],"proposed":[74,146],"approach":[75],"describes":[76],"mapping":[78],"between":[79],"noisy":[81],"input":[82,114],"clean":[84,108,125],"features":[85,110],"as":[86],"stochastic":[88],"process.":[89],"Therefore,":[90],"statistical":[92],"is":[94,133],"applied":[95],"predicting":[102],"posterior":[104],"distribution":[105,127,132],"given":[111],"distorted":[113],"data.":[115],"Also,":[116],"by":[117],"attempting":[118],"two":[120],"different":[121],"probabilistic":[122],"models":[123],"feature":[126],"assumption,":[128],"investigate":[130],"more":[134],"proper":[135],"on":[136,153],"various":[137],"environment":[138],"It":[140],"has":[141],"been":[142],"shown":[143],"that":[144],"outperforms":[148],"conventional":[150],"Aurora-4":[154],"DB":[155],"mismatched":[157],"noise":[158]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}