{"id":"https://openalex.org/W2398187210","doi":"https://doi.org/10.1109/icassp.2016.7472646","title":"Linearly augmented deep neural network","display_name":"Linearly augmented deep neural network","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398187210","doi":"https://doi.org/10.1109/icassp.2016.7472646","mag":"2398187210"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472646","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":"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/A5029777844","display_name":"Pegah Ghahremani","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":"Pegah Ghahremani","raw_affiliation_strings":["Johns Hopkins University, Baltimore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University, Baltimore","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"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":"Jasha Droppo","raw_affiliation_strings":["Microsoft Research, Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041313589","display_name":"Michael L. Seltzer","orcid":"https://orcid.org/0000-0003-3474-2451"},"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":"Michael L. Seltzer","raw_affiliation_strings":["Microsoft Research, Redmond"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4943,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.94704829,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"19","issue":null,"first_page":"5085","last_page":"5089"},"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":0.9991999864578247,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980999827384949,"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/timit","display_name":"TIMIT","score":0.9029891490936279},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.833540678024292},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6886031627655029},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6670089364051819},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5555353164672852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5061904788017273},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4660108685493469},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4618128538131714},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4545057415962219},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.41120344400405884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33001095056533813},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2831602096557617}],"concepts":[{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.9029891490936279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833540678024292},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6886031627655029},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6670089364051819},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5555353164672852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5061904788017273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4660108685493469},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4618128538131714},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4545057415962219},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.41120344400405884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33001095056533813},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2831602096557617},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472646","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":[{"display_name":"Quality Education","score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1635512741","https://openalex.org/W1665214252","https://openalex.org/W1690739335","https://openalex.org/W1876378865","https://openalex.org/W1978516841","https://openalex.org/W2110798204","https://openalex.org/W2112984492","https://openalex.org/W2119203697","https://openalex.org/W2136922672","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2168894214","https://openalex.org/W2181607856","https://openalex.org/W2294543795","https://openalex.org/W2616139854","https://openalex.org/W2963606038","https://openalex.org/W2964118293","https://openalex.org/W6631943919","https://openalex.org/W6637242042","https://openalex.org/W6637551013","https://openalex.org/W6676481782","https://openalex.org/W6684665197","https://openalex.org/W6686045668","https://openalex.org/W6696761078","https://openalex.org/W6696912008"],"related_works":["https://openalex.org/W36113703","https://openalex.org/W4377865163","https://openalex.org/W2038050265","https://openalex.org/W3193857078","https://openalex.org/W1694601526","https://openalex.org/W2888956734","https://openalex.org/W3000197790","https://openalex.org/W4315865067","https://openalex.org/W2979433843","https://openalex.org/W3208304128"],"abstract_inverted_index":{"Deep":[0,51],"neural":[1],"networks":[2],"(DNN)":[3],"are":[4,29],"a":[5,18,23,43,64,136],"powerful":[6],"tool":[7],"for":[8,80,87],"many":[9],"large":[10],"vocabulary":[11],"continuous":[12],"speech":[13,120],"recognition":[14,117,121,146],"(LVCSR)":[15],"tasks.":[16,122],"Training":[17],"very":[19],"deep":[20,88],"network":[21,47,58],"is":[22],"challenging":[24],"problem":[25,86],"and":[26,103,118,159],"pre-training":[27],"techniques":[28],"needed":[30],"in":[31,93],"order":[32],"to":[33,70],"achieve":[34],"the":[35,78,83,127,143,148],"best":[36],"results.":[37],"In":[38],"this":[39],"paper,":[40],"we":[41],"propose":[42],"new":[44],"type":[45,56],"of":[46,57],"architecture,":[48],"Linear":[49],"Augmented":[50],"Neural":[52],"Network":[53],"(LA-DNN).":[54],"This":[55],"augments":[59],"each":[60],"non-linear":[61],"layer":[62,68,71],"with":[63],"linear":[65,95],"connection":[66],"from":[67],"input":[69],"output.":[72],"The":[73,108],"resulting":[74],"LA-DNN":[75,128,150],"model":[76,110,151],"eliminates":[77],"need":[79],"pre-training,":[81],"addresses":[82],"gradient":[84],"vanishing":[85],"networks,":[89],"has":[90,111],"higher":[91],"capacity":[92],"modeling":[94],"transformations,":[96],"trains":[97],"significantly":[98],"faster":[99],"than":[100,135],"normal":[101],"DNN,":[102,137],"produces":[104],"better":[105],"acoustic":[106],"models.":[107],"proposed":[109],"been":[112],"evaluated":[113],"on":[114],"TIMIT":[115,144,153],"phoneme":[116,145],"AMI":[119,160],"Experimental":[123],"results":[124],"show":[125],"that":[126],"models":[129],"can":[130],"have":[131],"70%":[132],"fewer":[133],"parameters":[134],"while":[138],"still":[139],"improving":[140],"accuracy.":[141],"On":[142],"task,":[147],"smaller":[149],"improves":[152],"phone":[154],"accuracy":[155,162],"by":[156,163],"2%":[157],"absolute,":[158],"word":[161],"1.7%":[164],"absolute.":[165]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}