{"id":"https://openalex.org/W1985368711","doi":"https://doi.org/10.1109/icassp.2014.6854663","title":"Using neural network front-ends on far field multiple microphones based speech recognition","display_name":"Using neural network front-ends on far field multiple microphones based speech recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W1985368711","doi":"https://doi.org/10.1109/icassp.2014.6854663","mag":"1985368711"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5100768704","display_name":"Yulan Liu","orcid":"https://orcid.org/0000-0003-3320-2381"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yulan Liu","raw_affiliation_strings":["Speech and Hearing Research Group, The University of Sheffield, Sheffield, UK","Speech and Hearing Research Group, University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036446253","display_name":"Pengyuan Zhang","orcid":"https://orcid.org/0000-0001-6838-5160"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyuan Zhang","raw_affiliation_strings":["IACAS, Key Laboratory of Speech Acoustics and Content Understanding, Beijing, China","Key Lab. of Speech Acoust. & Content Understanding, IACAS, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IACAS, Key Laboratory of Speech Acoustics and Content Understanding, Beijing, China","institution_ids":["https://openalex.org/I4210099069"]},{"raw_affiliation_string":"Key Lab. of Speech Acoust. & Content Understanding, IACAS, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030528300","display_name":"Thomas Hain","orcid":"https://orcid.org/0000-0003-0939-3464"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Hain","raw_affiliation_strings":["Speech and Hearing Research Group, The University of Sheffield, Sheffield, UK","Speech and Hearing Research Group, University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Group, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Speech and Hearing Research Group, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.4414,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.98931743,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5542","last_page":"5546"},"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":0.9998999834060669,"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":0.9994999766349792,"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":0.7602677345275879},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7565680742263794},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7296236157417297},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6388953328132629},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6069017052650452},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5638390779495239},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.524027407169342},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.4969346821308136},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.48283204436302185},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4648157060146332},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4631938338279724},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4556584060192108},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44602102041244507},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.42850685119628906},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4231502413749695},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.41784554719924927},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.255204975605011},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10488194227218628},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07949095964431763}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7602677345275879},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7565680742263794},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7296236157417297},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6388953328132629},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6069017052650452},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5638390779495239},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.524027407169342},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.4969346821308136},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.48283204436302185},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4648157060146332},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4631938338279724},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4556584060192108},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44602102041244507},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42850685119628906},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4231502413749695},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41784554719924927},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.255204975605011},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10488194227218628},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07949095964431763},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2014.6854663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:78166","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.711.3117","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.711.3117","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staffwww.dcs.shef.ac.uk/people/Y.Liu/publications/pdf/Liu2014.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W102482883","https://openalex.org/W162588823","https://openalex.org/W1513862252","https://openalex.org/W1975138161","https://openalex.org/W1993409002","https://openalex.org/W2012897754","https://openalex.org/W2013863378","https://openalex.org/W2037769258","https://openalex.org/W2072349636","https://openalex.org/W2079623482","https://openalex.org/W2080400971","https://openalex.org/W2106554350","https://openalex.org/W2119203697","https://openalex.org/W2121147010","https://openalex.org/W2123237149","https://openalex.org/W2125336414","https://openalex.org/W2130361043","https://openalex.org/W2132056833","https://openalex.org/W2132122635","https://openalex.org/W2140833774","https://openalex.org/W2146871184","https://openalex.org/W2148613904","https://openalex.org/W2151046798","https://openalex.org/W2159948109","https://openalex.org/W2164240571","https://openalex.org/W2394932179","https://openalex.org/W2398569491","https://openalex.org/W2399877729","https://openalex.org/W2616139854","https://openalex.org/W4206633762","https://openalex.org/W6677540458","https://openalex.org/W6678251047","https://openalex.org/W6680887930"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4221148444","https://openalex.org/W4387678054","https://openalex.org/W2389596151","https://openalex.org/W3095575180","https://openalex.org/W4306784355","https://openalex.org/W2169308097","https://openalex.org/W4246226292","https://openalex.org/W2401089611","https://openalex.org/W4367598165"],"abstract_inverted_index":{"This":[0],"paper":[1,61],"presents":[2],"an":[3],"investigation":[4],"of":[5,18,45],"far":[6,131],"field":[7,132],"speech":[8,27,133],"recognition":[9,124],"using":[10],"beamforming":[11,30,51],"and":[12,126],"channel":[13,55,64],"concatenation":[14,65],"in":[15,59,81,93],"the":[16,33,42,73,99,104,120],"context":[17],"Deep":[19,111],"Neural":[20,112],"Network":[21,113],"(DNN)":[22],"based":[23,123],"feature":[24,106],"extraction.":[25],"While":[26],"enhancement":[28],"with":[29,38,103],"is":[31,52],"attractive,":[32],"algorithms":[34],"are":[35],"typically":[36],"signal-based":[37],"no":[39],"information":[40,92],"about":[41],"special":[43],"properties":[44],"speech.":[46],"A":[47],"simple":[48],"alternative":[49],"to":[50],"concatenating":[53],"multiple":[54],"features.":[56,97],"Results":[57],"presented":[58],"this":[60],"indicate":[62],"that":[63],"gives":[66],"similar":[67],"or":[68],"better":[69],"results.":[70],"On":[71],"average":[72],"DNN":[74,96,101,122],"front-end":[75],"yields":[76,127],"a":[77,108,116],"25%":[78],"relative":[79],"reduction":[80],"Word":[82],"Error":[83],"Rate":[84],"(WER).":[85],"Further":[86],"experiments":[87],"aim":[88],"at":[89],"including":[90],"relevant":[91],"training":[94],"adapted":[95],"Augmenting":[98],"standard":[100,121],"input":[102],"bottleneck":[105],"from":[107],"Speaker":[109],"Aware":[110],"(SADNN)":[114],"shows":[115],"general":[117],"advantage":[118],"over":[119],"system,":[125],"additional":[128],"improvements":[129],"for":[130],"recognition.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":12},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}