{"id":"https://openalex.org/W2288817436","doi":"https://doi.org/10.1109/asru.2015.7404842","title":"JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS","display_name":"JHU ASpIRE system: Robust LVCSR with TDNNS, iVector adaptation and RNN-LMS","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2288817436","doi":"https://doi.org/10.1109/asru.2015.7404842","mag":"2288817436"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/A5081105332","display_name":"Vijayaditya Peddinti","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vijayaditya Peddinti","raw_affiliation_strings":["Center for language and speech processing, The Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for language and speech processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081371370","display_name":"Guoguo Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoguo Chen","raw_affiliation_strings":["Center for language and speech processing, The Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for language and speech processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028956985","display_name":"Vimal Manohar","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vimal Manohar","raw_affiliation_strings":["Center for language and speech processing, The Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for language and speech processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038062913","display_name":"Tom Ko","orcid":"https://orcid.org/0000-0002-5324-8961"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tom Ko","raw_affiliation_strings":["Huawei Noah's Ark Research Lab, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Research Lab, Hong Kong, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"539","last_page":"546"},"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":0.9998999834060669,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8738675713539124},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.685833752155304},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6215642094612122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6143255233764648},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5825457572937012},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5436193346977234},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4958847463130951},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.479190468788147},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.45235684514045715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3236069679260254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3218168616294861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738675713539124},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.685833752155304},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6215642094612122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6143255233764648},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5825457572937012},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5436193346977234},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4958847463130951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.479190468788147},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.45235684514045715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3236069679260254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3218168616294861},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2015.7404842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404842","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W97072897","https://openalex.org/W1494198834","https://openalex.org/W1631260214","https://openalex.org/W1762484328","https://openalex.org/W1965154800","https://openalex.org/W1973669708","https://openalex.org/W1988540447","https://openalex.org/W1989314204","https://openalex.org/W2026149468","https://openalex.org/W2026369565","https://openalex.org/W2079623482","https://openalex.org/W2100734170","https://openalex.org/W2112021726","https://openalex.org/W2117671523","https://openalex.org/W2128022332","https://openalex.org/W2130086010","https://openalex.org/W2131342762","https://openalex.org/W2136682440","https://openalex.org/W2148154194","https://openalex.org/W2150769028","https://openalex.org/W2164240571","https://openalex.org/W2245569228","https://openalex.org/W2400997536","https://openalex.org/W2402146185","https://openalex.org/W2404463488","https://openalex.org/W2404568753","https://openalex.org/W2407080277","https://openalex.org/W2474824677","https://openalex.org/W2766736793","https://openalex.org/W6603931906","https://openalex.org/W6629717138","https://openalex.org/W6636811518","https://openalex.org/W6637956674","https://openalex.org/W6676587989","https://openalex.org/W6679469920","https://openalex.org/W6682610290","https://openalex.org/W6690610466","https://openalex.org/W6712930963","https://openalex.org/W6713140504","https://openalex.org/W6713346354","https://openalex.org/W6713570806","https://openalex.org/W6713762819","https://openalex.org/W6720877245"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W3032952384","https://openalex.org/W2109916967","https://openalex.org/W2890297197","https://openalex.org/W2101697354","https://openalex.org/W1538193578","https://openalex.org/W3206636855","https://openalex.org/W1538606284","https://openalex.org/W2373874059"],"abstract_inverted_index":{"Multi-style":[0],"training,":[1],"using":[2,52,111],"data":[3,30],"which":[4,66],"emulates":[5],"a":[6,13,32],"variety":[7],"of":[8,24,28,36,48,55,69],"possible":[9],"test":[10],"scenarios,":[11],"is":[12,67,93,152],"popular":[14],"approach":[15],"towards":[16],"robust":[17],"acoustic":[18,21],"modeling.":[19],"However":[20],"models":[22,139],"capable":[23,68],"exploiting":[25],"large":[26],"amounts":[27],"training":[29,37,91],"in":[31,78,108,158],"comparatively":[33],"short":[34],"amount":[35],"time":[38,89,92],"are":[39,118,140],"essential.":[40],"In":[41],"this":[42,97],"paper":[43],"we":[44,100],"tackle":[45],"the":[46,83,103,124,143,148,159,167],"problem":[47],"reverberant":[49,57,79],"speech":[50,74],"recognition":[51],"5500":[53],"hours":[54],"simulated":[56],"data.":[58],"We":[59],"use":[60],"time-delay":[61],"neural":[62,125,136],"network":[63,126,137],"(TDNN)":[64],"architecture,":[65],"tackling":[70],"long-term":[71],"interactions":[72],"between":[73],"and":[75,131],"corrupting":[76],"sources":[77],"environments.":[80],"By":[81],"sub-sampling":[82],"outputs":[84],"at":[85],"TDNN":[86,104],"layers":[87],"across":[88],"steps,":[90],"substantially":[94],"reduced.":[95],"Combining":[96],"with":[98,163],"distributed-optimization":[99],"show":[101],"that":[102],"can":[105],"be":[106],"trained":[107],"3":[109],"days":[110],"up":[112],"to":[113,123,127,142,145,154],"32":[114],"GPUs.":[115],"Further,":[116],"iVectors":[117],"used":[119],"as":[120],"an":[121],"input":[122],"perform":[128],"instantaneous":[129],"speaker":[130],"environment":[132],"adaptation.":[133],"Finally,":[134],"recurrent":[135],"language":[138],"applied":[141],"lattices":[144],"further":[146],"improve":[147],"performance.":[149],"Our":[150],"system":[151],"shown":[153],"provide":[155],"state-of-the-art":[156],"results":[157],"IARPA":[160],"ASpIRE":[161],"challenge,":[162],"26.5%":[164],"WER":[165],"on":[166],"dev":[168],"Jest":[169],"set.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}