{"id":"https://openalex.org/W2534495290","doi":"https://doi.org/10.1109/taslp.2017.2698723","title":"Small-Footprint Highway Deep Neural Networks for Speech Recognition","display_name":"Small-Footprint Highway Deep Neural Networks for Speech Recognition","publication_year":2017,"publication_date":"2017-04-27","ids":{"openalex":"https://openalex.org/W2534495290","doi":"https://doi.org/10.1109/taslp.2017.2698723","mag":"2534495290"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2017.2698723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2698723","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/932fcb81-7cc6-475a-9e9c-a70d88bb0222","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liang Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":null,"display_name":"Steve Renals","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Renals","raw_affiliation_strings":["The University of Edinburgh, Edinburgh, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Edinburgh, Edinburgh, U.K","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9938,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.89371444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"25","issue":"7","first_page":"1502","last_page":"1511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8726000189781189,"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":0.8726000189781189,"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":0.02889999933540821,"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":0.023499999195337296,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.7448999881744385},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.5867999792098999},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4925999939441681},{"id":"https://openalex.org/keywords/feedforward-neural-network","display_name":"Feedforward neural network","score":0.47189998626708984},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.45579999685287476},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.44269999861717224},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4099000096321106},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.38999998569488525}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7448999881744385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741100013256073},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6345000267028809},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5867999792098999},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4925999939441681},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.47189998626708984},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.45579999685287476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45170000195503235},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.38999998569488525},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3292999863624573},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2017.2698723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2017.2698723","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/932fcb81-7cc6-475a-9e9c-a70d88bb0222","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/932fcb81-7cc6-475a-9e9c-a70d88bb0222","pdf_url":"http://hdl.handle.net/20.500.11820/932fcb81-7cc6-475a-9e9c-a70d88bb0222","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"LU, L & Renals, S 2017, 'Small-footprint highway deep neural networks for speech recognition', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 25, no. 7, pp. 1502-1511. https://doi.org/10.1109/TASLP.2017.2698723","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:arXiv.org:1610.05812","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.05812","pdf_url":"https://arxiv.org/pdf/1610.05812","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/932fcb81-7cc6-475a-9e9c-a70d88bb0222","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/932fcb81-7cc6-475a-9e9c-a70d88bb0222","pdf_url":"http://hdl.handle.net/20.500.11820/932fcb81-7cc6-475a-9e9c-a70d88bb0222","source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"LU, L & Renals, S 2017, 'Small-footprint highway deep neural networks for speech recognition', IEEE/ACM Transactions on Audio, Speech and Language Processing, vol. 25, no. 7, pp. 1502-1511. https://doi.org/10.1109/TASLP.2017.2698723","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3790594077","display_name":"Natural Speech Technology","funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2534495290.pdf","grobid_xml":"https://content.openalex.org/works/W2534495290.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1987238397","https://openalex.org/W1995562189","https://openalex.org/W2035846950","https://openalex.org/W2058641082","https://openalex.org/W2064675550","https://openalex.org/W2094147890","https://openalex.org/W2095705004","https://openalex.org/W2100495367","https://openalex.org/W2114016253","https://openalex.org/W2131342762","https://openalex.org/W2153773386","https://openalex.org/W2160815625","https://openalex.org/W2169189000","https://openalex.org/W2194775991","https://openalex.org/W2239847623","https://openalex.org/W2507699225","https://openalex.org/W2508418541","https://openalex.org/W2515753980","https://openalex.org/W2963124866","https://openalex.org/W2963217176","https://openalex.org/W2963864497","https://openalex.org/W2964084166","https://openalex.org/W2964233848","https://openalex.org/W6601546718","https://openalex.org/W6626481562","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6638667902","https://openalex.org/W6640036494","https://openalex.org/W6676481782","https://openalex.org/W6677604277","https://openalex.org/W6677614981","https://openalex.org/W6679909955","https://openalex.org/W6680549991","https://openalex.org/W6684665197","https://openalex.org/W6685298420","https://openalex.org/W6686045668","https://openalex.org/W6686067075","https://openalex.org/W6696912008","https://openalex.org/W6696934422","https://openalex.org/W6711962127","https://openalex.org/W6712847557","https://openalex.org/W6713280142","https://openalex.org/W6720905350","https://openalex.org/W6745690006"],"related_works":[],"abstract_inverted_index":{"State-of-the-art":[0],"speech":[1],"recognition":[2,106],"systems":[3],"typically":[4],"employ":[5],"neural":[6,17,57,70],"network":[7,18,58,133],"acoustic":[8,21,63,99],"models.":[9,64],"However,":[10],"compared":[11],"to":[12,34,79],"Gaussian":[13],"mixture":[14],"models,":[15],"deep":[16,56],"(DNN)":[19],"based":[20],"models":[22],"often":[23],"have":[24],"many":[25,109],"more":[26,93,116,148],"model":[27,111,140],"parameters,":[28],"making":[29],"it":[30],"challenging":[31],"for":[32,60,98],"them":[33],"be":[35],"deployed":[36],"on":[37],"resource-constrained":[38],"platforms,":[39],"such":[40],"as":[41],"mobile":[42],"devices.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,143],"study":[48,88],"the":[49,52,81,128,131,156,176],"application":[50],"of":[51,76,123,130,139,186],"recently":[53],"proposed":[54],"highway":[55],"(HDNN)":[59],"training":[61,187],"small-footprint":[62],"HDNNs":[65,91,114,146],"are":[66,92,115,147],"a":[67,135],"depth-gated":[68],"feedforward":[69],"network,":[71],"which":[72,181],"include":[73],"two":[74],"types":[75],"gate":[77,121,157],"functions":[78,122,158],"facilitate":[80],"information":[82],"flow":[83],"through":[84],"different":[85],"layers.":[86],"Our":[87],"demonstrates":[89],"that":[90,145],"compact":[94],"than":[95,118,150],"regular":[96],"DNNs":[97],"modeling,":[100],"i.e.,":[101],"they":[102],"can":[103,126,162],"achieve":[104],"comparable":[105],"accuracy":[107],"with":[108],"fewer":[110],"parameters.":[112,141],"Furthermore,":[113],"controllable":[117],"DNNs:":[119],"The":[120],"an":[124],"HDNN":[125],"control":[127],"behavior":[129],"whole":[132],"using":[134,159,175],"very":[136],"small":[137],"number":[138],"Finally,":[142],"show":[144],"adaptable":[149],"DNNs.":[151],"For":[152],"example,":[153],"simply":[154],"updating":[155],"adaptation":[160],"data":[161],"result":[163],"in":[164,167],"considerable":[165],"gains":[166],"accuracy.":[168],"We":[169],"demonstrate":[170],"these":[171],"aspects":[172],"by":[173],"experiments":[174],"publicly":[177],"available":[178],"AMI":[179],"corpus,":[180],"has":[182],"around":[183],"80":[184],"h":[185],"data.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-10-28T00:00:00"}