{"id":"https://openalex.org/W1981617403","doi":"https://doi.org/10.1109/hscma.2014.6843274","title":"Neural networks for distant speech recognition","display_name":"Neural networks for distant speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1981617403","doi":"https://doi.org/10.1109/hscma.2014.6843274","mag":"1981617403"},"language":"en","primary_location":{"id":"doi:10.1109/hscma.2014.6843274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2014.6843274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/92ac9bba-471d-40f9-bf5c-d60bdfa9833a","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","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, UK","Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"Centre for Speech Technol. Res., Univ. of Edinburgh, Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"172","last_page":"176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7974080443382263},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7747718095779419},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6623702049255371},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5881941914558411},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5742201209068298},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5192082524299622},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.4680107831954956},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.46498391032218933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4379800856113434},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.4312475621700287},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4091424345970154},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39111998677253723},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12819638848304749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7974080443382263},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7747718095779419},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6623702049255371},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5881941914558411},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5742201209068298},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5192082524299622},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.4680107831954956},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.46498391032218933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4379800856113434},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.4312475621700287},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4091424345970154},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39111998677253723},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12819638848304749},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/hscma.2014.6843274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hscma.2014.6843274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 4th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.589.6568","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.589.6568","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/2014/srenals-hscma2014.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/92ac9bba-471d-40f9-bf5c-d60bdfa9833a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/92ac9bba-471d-40f9-bf5c-d60bdfa9833a","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":"Renals, S & Swietojanski, P 2014, Neural networks for distant speech recognition. in Proceedings 2014 Workshop on Hands-Free Speech Communication and Microphone Arrays . Institute of Electrical and Electronics Engineers, pp. 172-176. https://doi.org/10.1109/HSCMA.2014.6843274","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/92ac9bba-471d-40f9-bf5c-d60bdfa9833a","is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6843274","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/92ac9bba-471d-40f9-bf5c-d60bdfa9833a","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/92ac9bba-471d-40f9-bf5c-d60bdfa9833a","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":"Renals, S & Swietojanski, P 2014, Neural networks for distant speech recognition. in Proceedings 2014 Workshop on Hands-Free Speech Communication and Microphone Arrays . Institute of Electrical and Electronics Engineers, pp. 172-176. https://doi.org/10.1109/HSCMA.2014.6843274","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7400000095367432}],"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":63,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W811578723","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1538131130","https://openalex.org/W1553004968","https://openalex.org/W1591607137","https://openalex.org/W1599512239","https://openalex.org/W1665214252","https://openalex.org/W1872489089","https://openalex.org/W1968419113","https://openalex.org/W1973669708","https://openalex.org/W1982728343","https://openalex.org/W2012897754","https://openalex.org/W2013598660","https://openalex.org/W2032595071","https://openalex.org/W2035424729","https://openalex.org/W2037769258","https://openalex.org/W2048060899","https://openalex.org/W2061305730","https://openalex.org/W2070725064","https://openalex.org/W2076794394","https://openalex.org/W2083751884","https://openalex.org/W2089917322","https://openalex.org/W2100772283","https://openalex.org/W2103088716","https://openalex.org/W2106554350","https://openalex.org/W2107789863","https://openalex.org/W2109417541","https://openalex.org/W2110798204","https://openalex.org/W2112796928","https://openalex.org/W2113556376","https://openalex.org/W2119203697","https://openalex.org/W2121573996","https://openalex.org/W2125234026","https://openalex.org/W2130361043","https://openalex.org/W2136922672","https://openalex.org/W2147166770","https://openalex.org/W2147768505","https://openalex.org/W2148613904","https://openalex.org/W2150907703","https://openalex.org/W2151046798","https://openalex.org/W2155273149","https://openalex.org/W2160815625","https://openalex.org/W2165869870","https://openalex.org/W2169189000","https://openalex.org/W2294059674","https://openalex.org/W2399877729","https://openalex.org/W2616139854","https://openalex.org/W2757672955","https://openalex.org/W2962719052","https://openalex.org/W4206633762","https://openalex.org/W4293460823","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6632100814","https://openalex.org/W6637242042","https://openalex.org/W6672625215","https://openalex.org/W6676071220","https://openalex.org/W6676481782","https://openalex.org/W6677005164","https://openalex.org/W6682398751","https://openalex.org/W6696761078"],"related_works":["https://openalex.org/W1562475690","https://openalex.org/W1488529827","https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W642007152","https://openalex.org/W2122233706","https://openalex.org/W2105439218","https://openalex.org/W3143423642","https://openalex.org/W2131711534","https://openalex.org/W2341426843"],"abstract_inverted_index":{"Distant":[0],"conversational":[1],"speech":[2,31,62],"recognition":[3,63],"is":[4],"challenging":[5],"owing":[6],"to":[7],"the":[8,19,48,74,95],"presence":[9],"of":[10,21,50,64,76,110],"multiple,":[11],"overlapping":[12],"talkers,":[13],"additional":[14],"non-speech":[15],"acoustic":[16,44,58],"sources,":[17],"and":[18,46,78,89,97],"effects":[20],"reverberation.":[22],"In":[23,70],"this":[24],"paper":[25],"we":[26,72],"review":[27],"work":[28],"on":[29,36,94],"distant":[30,61],"recognition,":[32],"with":[33,43,82,101,116],"an":[34],"emphasis":[35],"approaches":[37],"which":[38],"combine":[39],"multichannel":[40],"signal":[41],"processing":[42],"modelling,":[45],"investigate":[47,73],"use":[49,75],"hybrid":[51],"neural":[52,80,105],"network":[53,106],"/":[54],"hidden":[55],"Markov":[56],"model":[57],"models":[59,107],"for":[60],"meetings":[65],"recorded":[66],"using":[67],"microphone":[68],"arrays.":[69],"particular":[71],"convolutional":[77],"fully-connected":[79],"networks":[81],"different":[83],"activation":[84],"functions":[85],"(sigmoid,":[86],"rectified":[87],"linear,":[88],"maxout).":[90],"We":[91],"performed":[92],"experiments":[93],"AMI":[96],"ICSI":[98],"meeting":[99],"corpora,":[100],"results":[102],"indicating":[103],"that":[104],"are":[108],"capable":[109],"significant":[111],"improvements":[112],"in":[113],"accuracy":[114],"compared":[115],"discriminatively":[117],"trained":[118],"Gaussian":[119],"mixture":[120],"models.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}