{"id":"https://openalex.org/W2616139854","doi":"https://doi.org/10.1109/asru.2013.6707744","title":"Hybrid acoustic models for distant and multichannel large vocabulary speech recognition","display_name":"Hybrid acoustic models for distant and multichannel large vocabulary speech recognition","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2616139854","doi":"https://doi.org/10.1109/asru.2013.6707744","mag":"2616139854"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2013.6707744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/3948a465-8e9c-46b9-81b3-f9d10f33655b","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":true,"raw_author_name":"Pawel Swietojanski","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh","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/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":"Arnab Ghoshal","raw_affiliation_strings":["Centre for Speech Technology Research, University of Edinburgh, Edinburgh"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084169592"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":16.7212,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.99509945,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"285","last_page":"290"},"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":0.9997000098228455,"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":0.9990000128746033,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.819075345993042},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.7969096302986145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7956557273864746},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7482062578201294},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6499319076538086},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6145959496498108},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5205243825912476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4865352213382721},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.4472914934158325},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.44496750831604004},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43187642097473145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42197859287261963},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4206637442111969},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.42012113332748413},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2705845236778259},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09674510359764099},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07100975513458252},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.06280550360679626}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.819075345993042},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7969096302986145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7956557273864746},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7482062578201294},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6499319076538086},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6145959496498108},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5205243825912476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4865352213382721},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.4472914934158325},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.44496750831604004},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43187642097473145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42197859287261963},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4206637442111969},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.42012113332748413},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2705845236778259},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09674510359764099},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07100975513458252},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.06280550360679626},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru.2013.6707744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2013.6707744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE Workshop on Automatic Speech Recognition and Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.396.326","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.396.326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cstr.ed.ac.uk/downloads/publications/2013/Swietojanski_ASRU2013.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/3948a465-8e9c-46b9-81b3-f9d10f33655b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/3948a465-8e9c-46b9-81b3-f9d10f33655b","pdf_url":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Swietojanski, P, Ghoshal, A & Renals, S 2013, Hybrid acoustic models for distant and multichannel large vocabulary speech recognition. in Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on. Institute of Electrical and Electronics Engineers, pp. 285-290. https://doi.org/10.1109/ASRU.2013.6707744","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/3948a465-8e9c-46b9-81b3-f9d10f33655b","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6707744","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/3948a465-8e9c-46b9-81b3-f9d10f33655b","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/3948a465-8e9c-46b9-81b3-f9d10f33655b","pdf_url":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Swietojanski, P, Ghoshal, A & Renals, S 2013, Hybrid acoustic models for distant and multichannel large vocabulary speech recognition. in Automatic Speech Recognition and Understanding (ASRU), 2013 IEEE Workshop on. Institute of Electrical and Electronics Engineers, pp. 285-290. https://doi.org/10.1109/ASRU.2013.6707744","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[{"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/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W38938105","https://openalex.org/W41021157","https://openalex.org/W811578723","https://openalex.org/W1433844162","https://openalex.org/W1509052650","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1876378865","https://openalex.org/W1982728343","https://openalex.org/W1994606281","https://openalex.org/W2005733316","https://openalex.org/W2012897754","https://openalex.org/W2046317813","https://openalex.org/W2062164080","https://openalex.org/W2106554350","https://openalex.org/W2119203697","https://openalex.org/W2120209245","https://openalex.org/W2121573996","https://openalex.org/W2125234026","https://openalex.org/W2131342762","https://openalex.org/W2134533334","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2148613904","https://openalex.org/W2151046798","https://openalex.org/W2152175008","https://openalex.org/W2160306971","https://openalex.org/W2160815625","https://openalex.org/W2163922914","https://openalex.org/W2169189000","https://openalex.org/W2170222430","https://openalex.org/W2399877729","https://openalex.org/W2609747516","https://openalex.org/W2757672955","https://openalex.org/W3105118415","https://openalex.org/W4206633762","https://openalex.org/W4299585523","https://openalex.org/W6601719842","https://openalex.org/W6631362777","https://openalex.org/W6678429839","https://openalex.org/W6744711567"],"related_works":["https://openalex.org/W1879255185","https://openalex.org/W2120442551","https://openalex.org/W2769861442","https://openalex.org/W1980506188","https://openalex.org/W2900122540","https://openalex.org/W4240587264","https://openalex.org/W2011788874","https://openalex.org/W2041060376","https://openalex.org/W2963983801","https://openalex.org/W3119734852"],"abstract_inverted_index":{"We":[0,25,44],"investigate":[1],"the":[2,28,84,93,103,114],"application":[3],"of":[4,19,79,99,116,129],"deep":[5],"neural":[6],"network":[7,118],"(DNN)-hidden":[8],"Markov":[9],"model":[10],"(HMM)":[11],"hybrid":[12,29],"acoustic":[13],"models":[14,30,42],"for":[15],"far-field":[16],"speech":[17,120],"recognition":[18],"meetings":[20],"recorded":[21],"using":[22,62,74],"microphone":[23,106,125],"arrays.":[24],"show":[26,112],"that":[27,113,128],"achieve":[31],"significantly":[32],"better":[33],"accuracy":[34,100,115],"than":[35],"conventional":[36],"systems":[37],"based":[38],"on":[39,76,86],"Gaussian":[40],"mixture":[41],"(GMMs).":[43],"observe":[45],"up":[46],"to":[47],"8%":[48],"absolute":[49,70],"word":[50],"error":[51],"rate":[52],"(WER)":[53],"reduction":[54,72],"from":[55,88,121,137],"a":[56,63,117,122,130],"discriminatively":[57],"trained":[58],"GMM":[59],"baseline":[60],"when":[61,73],"single":[64,104,123],"distant":[65,105,124],"microphone,":[66],"and":[67,107],"between":[68,102],"4-6%":[69],"WER":[71],"beamforming":[75],"various":[77],"combinations":[78],"array":[80],"channels.":[81],"By":[82],"training":[83,134],"networks":[85,94],"audio":[87],"multiple":[89],"channels,":[90],"we":[91,111],"find":[92],"can":[95,126],"recover":[96],"significant":[97],"part":[98],"difference":[101],"beamformed":[108],"configurations.":[109],"Finally,":[110],"recognising":[119],"approach":[127],"multi-microphone":[131],"setup":[132],"by":[133],"with":[135],"data":[136],"other":[138],"microphones.":[139]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":25},{"year":2015,"cited_by_count":18},{"year":2014,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}