{"id":"https://openalex.org/W2403307129","doi":"https://doi.org/10.21437/interspeech.2014-488","title":"Adaptation of deep neural network acoustic models using factorised i-vectors","display_name":"Adaptation of deep neural network acoustic models using factorised i-vectors","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2403307129","doi":"https://doi.org/10.21437/interspeech.2014-488","mag":"2403307129"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-488","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5006537074","display_name":"Penny Karanasou","orcid":"https://orcid.org/0000-0003-1939-4161"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Penny Karanasou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mark J. F. Gales","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip C. Woodland","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2180","last_page":"2184"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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/orthogonality","display_name":"Orthogonality","score":0.7654096484184265},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7640056610107422},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7037882804870605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6256530284881592},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5850448608398438},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5344212651252747},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5230903625488281},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.486973375082016},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4789488911628723},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47368812561035156},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.46410927176475525},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43741464614868164},{"id":"https://openalex.org/keywords/loudspeaker","display_name":"Loudspeaker","score":0.4206653833389282},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.41060417890548706},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39616307616233826},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1379871964454651},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1199711263179779},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10012447834014893}],"concepts":[{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.7654096484184265},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640056610107422},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7037882804870605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6256530284881592},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5850448608398438},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5344212651252747},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5230903625488281},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.486973375082016},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4789488911628723},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47368812561035156},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.46410927176475525},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43741464614868164},{"id":"https://openalex.org/C157138929","wikidata":"https://www.wikidata.org/wiki/Q570","display_name":"Loudspeaker","level":2,"score":0.4206653833389282},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.41060417890548706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39616307616233826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1379871964454651},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1199711263179779},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10012447834014893},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.21437/interspeech.2014-488","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:661066","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/661066/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W85200642","https://openalex.org/W126988493","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2010362084","https://openalex.org/W2024490156","https://openalex.org/W2079623482","https://openalex.org/W2087006792","https://openalex.org/W2107638917","https://openalex.org/W2147768505","https://openalex.org/W2156692643","https://openalex.org/W2159138759","https://openalex.org/W2160306971","https://openalex.org/W2164240571","https://openalex.org/W2184045248","https://openalex.org/W2283817422","https://openalex.org/W2294327763","https://openalex.org/W2296319761","https://openalex.org/W2404147237"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"The":[0],"use":[1,59],"of":[2,60,98,125,162],"deep":[3],"neural":[4],"networks":[5],"(DNNs)":[6],"in":[7],"a":[8,95,108,112,126,158],"hybrid":[9],"configuration":[10],"is":[11,25,64,91],"becoming":[12],"increasingly":[13],"popular":[14],"and":[15,79,100,111],"successful":[16],"for":[17,51,62,147],"speech":[18],"recognition.":[19],"One":[20],"issue":[21],"with":[22],"these":[23],"systems":[24],"how":[26],"to":[27,31,66,76,93,149,167],"efficiently":[28],"adapt":[29],"them":[30],"reflect":[32],"an":[33,47],"individual":[34,87],"speaker":[35,40,53,78,99,110],"or":[36],"noise":[37,159],"condition.":[38],"Recently":[39],"i-vectors":[41,61,73,106,119,173],"have":[42],"been":[43],"successfully":[44],"used":[45],"as":[46,122],"additional":[48],"input":[49],"feature":[50],"unsupervised":[52],"adaptation.":[54],"In":[55,70,115],"this":[56,116],"work":[57],"the":[58,86,118,123,133,143,163],"adaptation":[63],"extended":[65],"incorporate":[67],"acoustic":[68,80],"factorisation.":[69],"particular,":[71],"separate":[72],"are":[74,120,136],"computed":[75],"represent":[77,94],"environment.":[81,114],"By":[82],"ensuring":[83],"\"orthogonality\"":[84],"between":[85],"factor":[88],"representations":[89],"it":[90],"possible":[92],"wide":[96],"range":[97],"environment":[101],"pairs":[102],"by":[103],"simply":[104],"combining":[105],"from":[107],"particular":[109,113],"paper":[117],"viewed":[121],"weights":[124],"cluster":[127],"adaptive":[128],"training":[129],"(CAT)":[130],"system,":[131],"where":[132],"underlying":[134],"models":[135],"GMMs":[137],"rather":[138],"than":[139],"HMMs.":[140],"This":[141],"allows":[142],"factorisation":[144],"approaches":[145],"developed":[146],"CAT":[148],"be":[150],"directly":[151],"applied.":[152],"Initial":[153],"experiments":[154],"were":[155],"conducted":[156],"on":[157],"distorted":[160],"version":[161],"WSJ":[164],"corpus.":[165],"Compared":[166],"standard":[168],"speaker-based":[169],"i-vector":[170],"adaptation,":[171],"factorised":[172],"showed":[174],"performance":[175],"gains.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}