{"id":"https://openalex.org/W2094147890","doi":"https://doi.org/10.1109/slt.2014.7078569","title":"Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models","display_name":"Learning hidden unit contributions for unsupervised speaker adaptation of neural network acoustic models","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2094147890","doi":"https://doi.org/10.1109/slt.2014.7078569","mag":"2094147890"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/20.500.11820/15aadd75-2511-4b40-b3b5-27c3c791b6d5","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, UK","Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK"],"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 Technology Research, University of Edinburgh, EH8 9AB, UK","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, UK","Centre for Speech Technology Research, University of Edinburgh, EH8 9AB, UK"],"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 Technology Research, University of Edinburgh, EH8 9AB, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084169592"],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":45.2437,"has_fulltext":true,"cited_by_count":227,"citation_normalized_percentile":{"value":0.99852086,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"171","last_page":"176"},"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/T11309","display_name":"Music and Audio Processing","score":0.9976000189781189,"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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":0.7566800713539124},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6900371313095093},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6703691482543945},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6635633707046509},{"id":"https://openalex.org/keywords/sigmoid-function","display_name":"Sigmoid function","score":0.5544502139091492},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5243192911148071},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.458332359790802},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.44482994079589844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4335671067237854},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.42505115270614624},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41534528136253357},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3388761878013611}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7566800713539124},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6900371313095093},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6703691482543945},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6635633707046509},{"id":"https://openalex.org/C81388566","wikidata":"https://www.wikidata.org/wiki/Q526668","display_name":"Sigmoid function","level":3,"score":0.5544502139091492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5243192911148071},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.458332359790802},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.44482994079589844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4335671067237854},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.42505115270614624},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41534528136253357},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3388761878013611},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/slt.2014.7078569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078569","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/15aadd75-2511-4b40-b3b5-27c3c791b6d5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/15aadd75-2511-4b40-b3b5-27c3c791b6d5","pdf_url":"http://hdl.handle.net/20.500.11820/15aadd75-2511-4b40-b3b5-27c3c791b6d5","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":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.708.6003","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.708.6003","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://homepages.inf.ed.ac.uk/srenals/ps-slt14.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/15aadd75-2511-4b40-b3b5-27c3c791b6d5","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/15aadd75-2511-4b40-b3b5-27c3c791b6d5","pdf_url":"http://hdl.handle.net/20.500.11820/15aadd75-2511-4b40-b3b5-27c3c791b6d5","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":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"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"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2094147890.pdf","grobid_xml":"https://content.openalex.org/works/W2094147890.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W811578723","https://openalex.org/W1487724677","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1537275613","https://openalex.org/W1553004968","https://openalex.org/W1665214252","https://openalex.org/W1872489089","https://openalex.org/W1968706335","https://openalex.org/W1985368711","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2012897754","https://openalex.org/W2015633636","https://openalex.org/W2036351241","https://openalex.org/W2056738732","https://openalex.org/W2056825827","https://openalex.org/W2060277733","https://openalex.org/W2061305730","https://openalex.org/W2062164080","https://openalex.org/W2079623482","https://openalex.org/W2080005694","https://openalex.org/W2087006792","https://openalex.org/W2105099419","https://openalex.org/W2119203697","https://openalex.org/W2146871184","https://openalex.org/W2147786979","https://openalex.org/W2149194912","https://openalex.org/W2150769028","https://openalex.org/W2156692643","https://openalex.org/W2160306971","https://openalex.org/W2160650576","https://openalex.org/W2160815625","https://openalex.org/W2164240571","https://openalex.org/W2165712214","https://openalex.org/W2169189000","https://openalex.org/W2172130635","https://openalex.org/W2251645580","https://openalex.org/W2294059674","https://openalex.org/W2403307129","https://openalex.org/W2484208911","https://openalex.org/W2917668649","https://openalex.org/W4293460823","https://openalex.org/W6629045631","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6637242042","https://openalex.org/W6639260565","https://openalex.org/W6683161958","https://openalex.org/W6696761078","https://openalex.org/W6713701104","https://openalex.org/W6759815381"],"related_works":["https://openalex.org/W4385957115","https://openalex.org/W2061372042","https://openalex.org/W3047779762","https://openalex.org/W1520030019","https://openalex.org/W2071654592","https://openalex.org/W3104477175","https://openalex.org/W2088157920","https://openalex.org/W4313324256","https://openalex.org/W2019022049","https://openalex.org/W2380970022"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,102],"simple":[4],"yet":[5],"effective":[6],"model-based":[7],"neural":[8,126],"network":[9,127],"speaker":[10],"adaptation":[11,20,31],"technique":[12],"that":[13,80],"learns":[14],"speaker-specific":[15],"hidden":[16,41,135],"unit":[17,136],"contributions":[18],"given":[19],"data,":[21,64],"without":[22],"requiring":[23],"any":[24],"form":[25],"of":[26,105],"speaker-adaptive":[27],"training,":[28],"or":[29],"labelled":[30],"data.":[32],"An":[33],"additional":[34],"amplitude":[35,44],"parameter":[36],"is":[37],"defined":[38],"for":[39,48],"each":[40,49],"unit;":[42],"the":[43,61,68,81],"parameters":[45],"are":[46,52],"tied":[47],"speaker,":[50],"and":[51,129,141],"learned":[53],"using":[54,133],"unsupervised":[55],"adaptation.":[56],"We":[57],"conducted":[58],"experiments":[59],"on":[60,71,88],"TED":[62],"talks":[63],"as":[65],"used":[66],"in":[67,122],"International":[69],"Workshop":[70],"Spoken":[72],"Language":[73],"Translation":[74],"(IWSLT)":[75],"evaluations.":[76],"Our":[77],"results":[78,132],"indicate":[79],"approach":[82,118],"can":[83,119],"reduce":[84],"word":[85],"error":[86],"rates":[87],"standard":[89],"IWSLT":[90],"test":[91],"sets":[92],"by":[93],"about":[94],"8-15%":[95],"relative":[96,107],"compared":[97],"to":[98],"unadapted":[99],"systems,":[100],"with":[101,110],"further":[103],"reduction":[104],"4-6%":[106],"when":[108],"combined":[109],"feature-space":[111],"maximum":[112],"likelihood":[113],"linear":[114,143],"regression":[115],"(fMLLR).":[116],"The":[117],"be":[120],"employed":[121],"most":[123],"existing":[124],"feed-forward":[125],"architectures,":[128],"we":[130],"report":[131],"various":[134],"activation":[137],"functions:":[138],"sigmoid,":[139],"maxout,":[140],"rectifying":[142],"units":[144],"(ReLU).":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":24},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":40},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":46},{"year":2015,"cited_by_count":26},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}