{"id":"https://openalex.org/W2964084166","doi":"https://doi.org/10.1109/icassp.2016.7472780","title":"Highway long short-term memory RNNS for distant speech recognition","display_name":"Highway long short-term memory RNNS for distant speech recognition","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2964084166","doi":"https://doi.org/10.1109/icassp.2016.7472780","mag":"2964084166"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5100707101","display_name":"Yu Zhang","orcid":"https://orcid.org/0000-0002-2842-6340"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081371370","display_name":"Guoguo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guoguo Chen","raw_affiliation_strings":["JHU CLSP"],"affiliations":[{"raw_affiliation_string":"JHU CLSP","institution_ids":[]}]},{"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/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103119755","display_name":"Kaisheng Yao","orcid":"https://orcid.org/0000-0002-8949-9367"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kaisheng Yao","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["JHU CLSP"],"affiliations":[{"raw_affiliation_string":"JHU CLSP","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["MIT CSAIL"],"affiliations":[{"raw_affiliation_string":"MIT CSAIL","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100707101"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":75.843,"has_fulltext":false,"cited_by_count":301,"citation_normalized_percentile":{"value":0.99904996,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5755","last_page":"5759"},"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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.8707444667816162},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8003640174865723},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.7778589725494385},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7694286108016968},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.688388466835022},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5948468446731567},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5919241309165955},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5561783313751221},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5504593849182129},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5350120663642883},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5152216553688049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47957366704940796},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4232596755027771},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.42025986313819885},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11504757404327393},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09573835134506226},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08303585648536682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8707444667816162},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8003640174865723},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.7778589725494385},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7694286108016968},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.688388466835022},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5948468446731567},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5919241309165955},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5561783313751221},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5504593849182129},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5350120663642883},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5152216553688049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47957366704940796},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4232596755027771},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.42025986313819885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11504757404327393},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09573835134506226},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08303585648536682},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1771459135","https://openalex.org/W1904365287","https://openalex.org/W1916589227","https://openalex.org/W1982728343","https://openalex.org/W2005708641","https://openalex.org/W2035846950","https://openalex.org/W2057653135","https://openalex.org/W2062164080","https://openalex.org/W2064675550","https://openalex.org/W2083751884","https://openalex.org/W2103088716","https://openalex.org/W2119203697","https://openalex.org/W2134533334","https://openalex.org/W2143612262","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2181607856","https://openalex.org/W2293634267","https://openalex.org/W2329068866","https://openalex.org/W2394932179","https://openalex.org/W2397424575","https://openalex.org/W2616139854","https://openalex.org/W2962965465","https://openalex.org/W3038058348","https://openalex.org/W6631362777","https://openalex.org/W6638205174","https://openalex.org/W6640036494","https://openalex.org/W6640218462","https://openalex.org/W6686045668","https://openalex.org/W6696934422","https://openalex.org/W6701770434","https://openalex.org/W6711962127","https://openalex.org/W6780493881"],"related_works":["https://openalex.org/W4385280324","https://openalex.org/W2912153778","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2973430807","https://openalex.org/W2984436043","https://openalex.org/W2912831041","https://openalex.org/W2890685186","https://openalex.org/W2904359912","https://openalex.org/W2796130100"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,96],"extend":[4],"the":[5,41,52,60,65,87,131],"deep":[6],"long":[7],"short-term":[8],"memory":[9,20],"(DL-STM)":[10],"recurrent":[11],"neural":[12],"networks":[13,77],"by":[14],"introducing":[15],"gated":[16],"direct":[17,26],"connections":[18],"between":[19],"cells":[21],"in":[22],"adjacent":[23],"layers.":[24],"These":[25],"links,":[27],"called":[28],"highway":[29,109],"connections,":[30],"enable":[31],"unimpeded":[32],"information":[33],"flow":[34],"across":[35],"different":[36],"layers":[37],"and":[38,81,101,122,134,139],"thus":[39],"alleviate":[40],"gradient":[42],"vanishing":[43],"problem":[44],"when":[45],"building":[46],"deeper":[47,99],"LSTMs.":[48],"We":[49],"further":[50],"introduce":[51],"latency-controlled":[53],"bidirectional":[54],"LSTMs":[55,100,110],"(BLSTMs)":[56],"which":[57],"can":[58,97],"exploit":[59],"whole":[61],"history":[62],"while":[63],"keeping":[64],"latency":[66],"under":[67],"control.":[68],"Efficient":[69],"algorithms":[70],"are":[71],"proposed":[72],"to":[73],"train":[74,98],"these":[75],"novel":[76,113],"using":[78],"both":[79],"frame":[80],"sequence":[82,106],"discriminative":[83],"criteria.":[84],"Experiments":[85],"on":[86,118],"AMI":[88,119],"distant":[89],"speech":[90],"recognition":[91],"(DSR)":[92],"task":[93],"indicate":[94],"that":[95],"achieve":[102],"better":[103],"improvement":[104,142],"from":[105],"training":[107],"with":[108,137],"(HLSTMs).":[111],"Our":[112],"model":[114],"obtains":[115],"43.9/47.7%":[116],"WER":[117],"(SDM)":[120],"dev":[121],"eval":[123],"sets,":[124],"outperforming":[125],"all":[126],"previous":[127],"works.":[128],"It":[129],"beats":[130],"strong":[132],"DNN":[133],"DLSTM":[135],"baselines":[136],"15.7%":[138],"5.3%":[140],"relative":[141],"respectively.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":41},{"year":2019,"cited_by_count":46},{"year":2018,"cited_by_count":64},{"year":2017,"cited_by_count":40},{"year":2016,"cited_by_count":20}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}