{"id":"https://openalex.org/W2063224314","doi":"https://doi.org/10.1109/icassp.2014.6854661","title":"Recurrent deep neural networks for robust speech recognition","display_name":"Recurrent deep neural networks for robust speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2063224314","doi":"https://doi.org/10.1109/icassp.2014.6854661","mag":"2063224314"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":"Dong Yu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","[Microsoft Research,Redmond,WA,USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"[Microsoft Research,Redmond,WA,USA]","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I1306287861","display_name":"Mitsubishi Group (Japan)","ror":"https://ror.org/0234cd281","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","Mitsubishi Electr. Res. Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"Mitsubishi Electr. Res. Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306287861"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110122094","display_name":"Biing-Hwang Juang","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biing-Hwang Fred Juang","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA, USA","Georgia Institute of Technology Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.0604,"has_fulltext":false,"cited_by_count":129,"citation_normalized_percentile":{"value":0.9934252,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5532","last_page":"5536"},"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":0.9987000226974487,"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":0.7869151830673218},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6850102543830872},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5985246300697327},{"id":"https://openalex.org/keywords/stochastic-gradient-descent","display_name":"Stochastic gradient descent","score":0.559266984462738},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.5502080321311951},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5326893329620361},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261468291282654},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.510662853717804},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48565828800201416},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47041940689086914},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.45434093475341797},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.420124888420105},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36367160081863403},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17039525508880615}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869151830673218},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6850102543830872},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5985246300697327},{"id":"https://openalex.org/C206688291","wikidata":"https://www.wikidata.org/wiki/Q7617819","display_name":"Stochastic gradient descent","level":3,"score":0.559266984462738},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.5502080321311951},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5326893329620361},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261468291282654},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.510662853717804},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48565828800201416},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47041940689086914},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.45434093475341797},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.420124888420105},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36367160081863403},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17039525508880615},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1665196592","https://openalex.org/W1950777589","https://openalex.org/W1997418877","https://openalex.org/W2000949213","https://openalex.org/W2002342963","https://openalex.org/W2045036776","https://openalex.org/W2062164080","https://openalex.org/W2090861223","https://openalex.org/W2101045344","https://openalex.org/W2113911479","https://openalex.org/W2114016253","https://openalex.org/W2115086266","https://openalex.org/W2115730999","https://openalex.org/W2131342762","https://openalex.org/W2136439176","https://openalex.org/W2137075158","https://openalex.org/W2137401359","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2167191127","https://openalex.org/W2290318471","https://openalex.org/W2328757576","https://openalex.org/W2336741987","https://openalex.org/W2914008274","https://openalex.org/W2964138484","https://openalex.org/W6631362777","https://openalex.org/W6640738657","https://openalex.org/W6649671159","https://openalex.org/W6677416784","https://openalex.org/W6702079475","https://openalex.org/W6703444193"],"related_works":["https://openalex.org/W2286391053","https://openalex.org/W2982600058","https://openalex.org/W2088845016","https://openalex.org/W589102260","https://openalex.org/W1966421350","https://openalex.org/W1963486701","https://openalex.org/W4402471162","https://openalex.org/W4211135130","https://openalex.org/W4287755480","https://openalex.org/W2785875001"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3],"propose":[4],"recurrent":[5,17,62,72],"deep":[6,40],"neural":[7],"networks":[8],"(DNNs)":[9],"for":[10],"robust":[11],"automatic":[12],"speech":[13],"recognition":[14],"(ASR).":[15],"Full":[16],"connections":[18],"are":[19],"added":[20],"to":[21,34,51],"certain":[22],"hidden":[23],"layer":[24],"of":[25],"a":[26,139],"conventional":[27],"feedforward":[28],"DNN":[29,73,110,141],"and":[30,66,86],"allow":[31],"the":[32,36,53,60,70,76,81,92,98,109,126,130],"model":[33],"capture":[35],"temporal":[37],"dependency":[38],"in":[39],"representations.":[41],"A":[42],"new":[43],"backpropagation":[44],"through":[45],"time":[46],"(BPTT)":[47],"algorithm":[48],"is":[49],"introduced":[50],"make":[52],"minibatch":[54],"stochastic":[55],"gradient":[56],"descent":[57],"(SGD)":[58],"on":[59,79,91,128],"proposed":[61,71,99,131],"DNNs":[63],"more":[64],"efficient":[65],"effective.":[67],"We":[68],"evaluate":[69],"architecture":[74],"under":[75],"hybrid":[77],"setup":[78],"both":[80],"2ndCHiME":[82],"challenge":[83,94],"(track":[84],"2)":[85],"Aurora-4":[87],"tasks.":[88],"Experimental":[89],"results":[90],"CHiME":[93],"data":[95],"show":[96],"that":[97],"system":[100,132],"can":[101],"obtain":[102],"consistent":[103],"7%":[104],"relative":[105,135],"WER":[106,136],"improvements":[107],"over":[108,138],"systems,":[111],"achieving":[112],"state-of-the-art":[113],"performance":[114],"without":[115],"front-end":[116],"preprocessing,":[117],"speaker":[118],"adaptive":[119],"training":[120],"or":[121],"multiple":[122],"decoding":[123],"passes.":[124],"For":[125],"experiments":[127],"Aurora-4,":[129],"achieves":[133],"4%":[134],"improvement":[137],"strong":[140],"baseline":[142],"system.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":20},{"year":2015,"cited_by_count":26},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}