{"id":"https://openalex.org/W2400505028","doi":"https://doi.org/10.21437/interspeech.2014-81","title":"Unfolded recurrent neural networks for speech recognition","display_name":"Unfolded recurrent neural networks for speech recognition","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2400505028","doi":"https://doi.org/10.21437/interspeech.2014-81","mag":"2400505028"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-81","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010878109","display_name":"Hagen Soltau","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hagen Soltau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080675607","display_name":"Ahmad Emami","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmad Emami","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.4186,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.98508926,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"343","last_page":"347"},"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":0.9991999864578247,"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":0.9990000128746033,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8499324917793274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7667174339294434},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6808964014053345},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6271367073059082},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.52397221326828},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5029165148735046},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4847840666770935},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4846978187561035},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47885584831237793},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.47498172521591187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4430842995643616},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.44134002923965454},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42925578355789185},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.428948312997818},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3669268488883972}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8499324917793274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667174339294434},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6808964014053345},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6271367073059082},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.52397221326828},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5029165148735046},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4847840666770935},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4846978187561035},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47885584831237793},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.47498172521591187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4430842995643616},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.44134002923965454},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42925578355789185},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.428948312997818},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3669268488883972},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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:10.21437/interspeech.2014-81","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1499864241","https://openalex.org/W1538131130","https://openalex.org/W2005708641","https://openalex.org/W2036317923","https://openalex.org/W2058641082","https://openalex.org/W2063224314","https://openalex.org/W2079623482","https://openalex.org/W2110871230","https://openalex.org/W2115730999","https://openalex.org/W2117671523","https://openalex.org/W2131774270","https://openalex.org/W2143612262","https://openalex.org/W2150355110","https://openalex.org/W2159505618","https://openalex.org/W2160306971","https://openalex.org/W2403195671","https://openalex.org/W2405787239","https://openalex.org/W2964335273"],"related_works":["https://openalex.org/W2109916967","https://openalex.org/W2950022897","https://openalex.org/W2890297197","https://openalex.org/W2101697354","https://openalex.org/W4255044973","https://openalex.org/W2890936991","https://openalex.org/W2499802997","https://openalex.org/W1538193578","https://openalex.org/W2112059504","https://openalex.org/W3206636855"],"abstract_inverted_index":{"We":[0],"introduce":[1],"recurrent":[2,38,161],"neural":[3,89,162],"networks":[4,26,90],"(RNNs)":[5],"for":[6,14,120],"acoustic":[7],"modeling":[8],"which":[9,34,116],"are":[10,24],"unfolded":[11,32,69],"in":[12,139],"time":[13,19],"a":[15,82,135],"fixed":[16],"number":[17,95],"of":[18,61,77,96],"steps.":[20],"The":[21,75],"proposed":[22],"models":[23],"feedforward":[25],"with":[27,92,150],"the":[28,31,37,48,68,72,93,126],"property":[29],"that":[30,84],"layers":[33,65,70],"correspond":[35],"to":[36,52,87],"layer":[39],"have":[40],"time-shifted":[41],"inputs":[42],"and":[43,71,154],"tied":[44],"weight":[45],"matrices.":[46],"Besides":[47],"temporal":[49],"depth":[50,56],"due":[51],"unfolding,":[53],"hierarchical":[54],"processing":[55],"is":[57,85],"added":[58],"by":[59],"means":[60],"several":[62],"non-recurrent":[63],"hidden":[64],"inserted":[66],"between":[67],"output":[73],"layer.":[74],"training":[76],"these":[78],"models:":[79],"(a)":[80],"has":[81],"complexity":[83],"comparable":[86],"deep":[88],"(DNNs)":[91],"same":[94],"layers;":[97],"(b)":[98],"can":[99,106],"be":[100,107],"done":[101],"on":[102,113,125,147],"frame-randomized":[103],"minibatches;":[104],"(c)":[105],"implemented":[108],"efficiently":[109],"through":[110],"matrix-matrix":[111],"operations":[112],"GPU":[114],"architectures":[115],"makes":[117],"it":[118],"scalable":[119],"large":[121],"tasks.":[122],"Experimental":[123],"results":[124],"Switchboard":[127],"300":[128],"hours":[129],"English":[130],"conversational":[131],"telephony":[132],"task":[133],"show":[134],"5%":[136],"relative":[137],"improvement":[138],"word":[140],"error":[141],"rate":[142],"over":[143],"state-of-the-art":[144],"DNNs":[145],"trained":[146],"FMLLR":[148],"features":[149],"i-vector":[151],"speaker":[152],"adaptation":[153],"hessianfree":[155],"sequence":[156],"discriminative":[157],"training.":[158],"Index":[159],"Terms:":[160],"networks,":[163],"speech":[164],"recognition":[165]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}