{"id":"https://openalex.org/W2103088716","doi":"https://doi.org/10.1109/lsp.2014.2325781","title":"Convolutional Neural Networks for Distant Speech Recognition","display_name":"Convolutional Neural Networks for Distant Speech Recognition","publication_year":2014,"publication_date":"2014-05-20","ids":{"openalex":"https://openalex.org/W2103088716","doi":"https://doi.org/10.1109/lsp.2014.2325781","mag":"2103088716"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2014.2325781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2014.2325781","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/002c63f3-cf09-4802-a251-b544033a0379","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084169592","display_name":"Pawe\u0142 \u015awi\u0119toja\u0144ski","orcid":"https://orcid.org/0000-0001-5896-4505"},"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":"Pawel Swietojanski","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016623654","display_name":"Arnab Ghoshal","orcid":"https://orcid.org/0000-0003-1272-2599"},"institutions":[{"id":"https://openalex.org/I1311269955","display_name":"Apple (Israel)","ror":"https://ror.org/04ehjr030","country_code":"IL","type":"company","lineage":["https://openalex.org/I1311269955","https://openalex.org/I4210153776"]},{"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","IL"],"is_corresponding":false,"raw_author_name":"Arnab Ghoshal","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom","Apple Inc., Cambridge, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Apple Inc., Cambridge, United States","institution_ids":["https://openalex.org/I1311269955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027442277","display_name":"Steve Renals","orcid":"https://orcid.org/0000-0002-8790-3389"},"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":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, United Kingdom","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":24.7596,"has_fulltext":true,"cited_by_count":260,"citation_normalized_percentile":{"value":0.9975612,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"21","issue":"9","first_page":"1120","last_page":"1124"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9987000226974487,"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":0.839802622795105},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7092156410217285},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6858963966369629},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6246030330657959},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5906574726104736},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5482174158096313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5477558374404907},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5425875186920166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5289307236671448},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.46477511525154114},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.43562716245651245},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38322713971138},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06373617053031921}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.839802622795105},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7092156410217285},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6858963966369629},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6246030330657959},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5906574726104736},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5482174158096313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5477558374404907},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5425875186920166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5289307236671448},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.46477511525154114},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.43562716245651245},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38322713971138},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06373617053031921},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/lsp.2014.2325781","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2014.2325781","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"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 Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/002c63f3-cf09-4802-a251-b544033a0379","is_oa":true,"landing_page_url":null,"pdf_url":"http://hdl.handle.net/20.500.11820/002c63f3-cf09-4802-a251-b544033a0379","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.ed.ac.uk:publications/002c63f3-cf09-4802-a251-b544033a0379","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/002c63f3-cf09-4802-a251-b544033a0379","pdf_url":"https://www.research.ed.ac.uk/files/20099575/psspl.pdf","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Swietojanski, P, Ghoshal, A & Renals, S 2014, 'Convolutional Neural Networks for Distant Speech Recognition', IEEE Signal Processing Letters, vol. 21, no. 9, pp. 1120-1124. https://doi.org/10.1109/LSP.2014.2325781","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:ec_fundedresources/002c63f3-cf09-4802-a251-b544033a0379","is_oa":true,"landing_page_url":null,"pdf_url":"http://hdl.handle.net/20.500.11820/002c63f3-cf09-4802-a251-b544033a0379","source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"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"},{"id":"https://openalex.org/G4263088022","display_name":"Accessing Dynamic Networked Multimedia Events","funder_award_id":"287872","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"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/W2103088716.pdf","grobid_xml":"https://content.openalex.org/works/W2103088716.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W11314411","https://openalex.org/W37458164","https://openalex.org/W102482883","https://openalex.org/W177307080","https://openalex.org/W811578723","https://openalex.org/W1524333225","https://openalex.org/W1536929369","https://openalex.org/W1538131130","https://openalex.org/W1553004968","https://openalex.org/W1872489089","https://openalex.org/W1980501707","https://openalex.org/W1982728343","https://openalex.org/W2012897754","https://openalex.org/W2013598660","https://openalex.org/W2048060899","https://openalex.org/W2070725064","https://openalex.org/W2076794394","https://openalex.org/W2083751884","https://openalex.org/W2100772283","https://openalex.org/W2105099419","https://openalex.org/W2106554350","https://openalex.org/W2107789863","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2117671523","https://openalex.org/W2119203697","https://openalex.org/W2125234026","https://openalex.org/W2134533334","https://openalex.org/W2136922672","https://openalex.org/W2139427956","https://openalex.org/W2147768505","https://openalex.org/W2148613904","https://openalex.org/W2149194912","https://openalex.org/W2152386803","https://openalex.org/W2155273149","https://openalex.org/W2158195707","https://openalex.org/W2160815625","https://openalex.org/W2165712214","https://openalex.org/W2169189000","https://openalex.org/W2616139854","https://openalex.org/W2757672955","https://openalex.org/W2962719052","https://openalex.org/W2963175699","https://openalex.org/W4206633762","https://openalex.org/W4293460823","https://openalex.org/W6601546354","https://openalex.org/W6607143959","https://openalex.org/W6631362777","https://openalex.org/W6639260565","https://openalex.org/W6676071220","https://openalex.org/W6678409544"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W2032826752"],"abstract_inverted_index":{"We":[0,54],"investigate":[1],"convolutional":[2],"neural":[3,92],"networks":[4],"(CNNs)":[5],"for":[6],"large":[7],"vocabulary":[8],"distant":[9,19,24],"speech":[10,14],"recognition,":[11],"trained":[12,101],"using":[13,71],"recorded":[15],"from":[16],"a":[17,33,48,63,99,142],"single":[18],"microphone":[20],"(SDM)":[21],"and":[22,61,96,137],"multiple":[23,44],"microphones":[25],"(MDM).":[26],"In":[27],"the":[28,40,52,72,80,111,118,124,132,139],"MDM":[29],"case":[30],"we":[31],"explore":[32],"beamformed":[34,126,143],"signal":[35],"input":[36,50],"representation":[37],"compared":[38,88],"with":[39,66,123],"direct":[41],"use":[42],"of":[43,141],"acoustic":[45],"channels":[46],"as":[47],"parallel":[49],"to":[51,89],"CNN.":[53],"have":[55],"explored":[56],"different":[57],"weight":[58],"sharing":[59],"approaches,":[60],"propose":[62],"channel-wise":[64],"convolution":[65,130],"two-way":[67],"pooling.":[68],"Our":[69],"experiments,":[70],"AMI":[73],"meeting":[74],"corpus,":[75],"found":[76],"that":[77],"CNNs":[78],"improve":[79],"word":[81],"error":[82],"rate":[83],"(WER)":[84],"by":[85,114,134],"6.5%":[86],"relative":[87,116],"conventional":[90],"deep":[91],"network":[93],"(DNN)":[94],"models":[95],"15.7%":[97],"over":[98,117],"discriminatively":[100],"Gaussian":[102],"mixture":[103],"model":[104],"(GMM)":[105],"baseline.":[106],"For":[107],"cross-channel":[108,129],"CNN":[109],"training,":[110],"WER":[112,133],"improves":[113],"3.5%":[115],"comparable":[119],"DNN":[120],"structure.":[121],"Compared":[122],"best":[125],"GMM":[127],"system,":[128],"reduces":[131],"9.7%":[135],"relative,":[136],"matches":[138],"accuracy":[140],"DNN.":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":30},{"year":2018,"cited_by_count":34},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":7}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}