{"id":"https://openalex.org/W2398054607","doi":"https://doi.org/10.1109/icassp.2016.7472631","title":"SAT-LHUC: Speaker adaptive training for learning hidden unit contributions","display_name":"SAT-LHUC: Speaker adaptive training for learning hidden unit contributions","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2398054607","doi":"https://doi.org/10.1109/icassp.2016.7472631","mag":"2398054607"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/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":["The Centre for Speech Technology Research, University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110383860","display_name":"Steve Renais","orcid":null},"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 Renais","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh","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":5.5702,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96024917,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5010","last_page":"5014"},"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":0.9991999864578247,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9972000122070312,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.7337346076965332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6852303743362427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6573913097381592},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5777440667152405},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5495334267616272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5002446174621582},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48150429129600525},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4700269401073456},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4655284285545349},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4430033266544342},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42026519775390625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21293696761131287},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1446046233177185}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7337346076965332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6852303743362427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6573913097381592},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5777440667152405},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5495334267616272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5002446174621582},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48150429129600525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4700269401073456},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4655284285545349},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4430033266544342},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42026519775390625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21293696761131287},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1446046233177185},{"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},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2016.7472631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/08f637e3-552a-47b6-895e-9b61c7b3153f","is_oa":false,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/08f637e3-552a-47b6-895e-9b61c7b3153f","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":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"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":51,"referenced_works":["https://openalex.org/W567546468","https://openalex.org/W1513820424","https://openalex.org/W1513862252","https://openalex.org/W1524333225","https://openalex.org/W1537275613","https://openalex.org/W1538611796","https://openalex.org/W1567690964","https://openalex.org/W1571447047","https://openalex.org/W1599512239","https://openalex.org/W1719257971","https://openalex.org/W1722135069","https://openalex.org/W1943324956","https://openalex.org/W1961429348","https://openalex.org/W1989549063","https://openalex.org/W1993409002","https://openalex.org/W2002342963","https://openalex.org/W2010362084","https://openalex.org/W2069631319","https://openalex.org/W2079623482","https://openalex.org/W2083751884","https://openalex.org/W2087006792","https://openalex.org/W2094147890","https://openalex.org/W2106051978","https://openalex.org/W2114016253","https://openalex.org/W2131342762","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2153773386","https://openalex.org/W2156692643","https://openalex.org/W2160306971","https://openalex.org/W2160650576","https://openalex.org/W2160815625","https://openalex.org/W2164240571","https://openalex.org/W2166637769","https://openalex.org/W2172130635","https://openalex.org/W2184135559","https://openalex.org/W2239847623","https://openalex.org/W2401396087","https://openalex.org/W2403731734","https://openalex.org/W2616139854","https://openalex.org/W3125118953","https://openalex.org/W3141933106","https://openalex.org/W6615969787","https://openalex.org/W6631362777","https://openalex.org/W6632379913","https://openalex.org/W6637667618","https://openalex.org/W6679429981","https://openalex.org/W6683161958","https://openalex.org/W6686282164","https://openalex.org/W6713250295"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W2380970022","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162"],"abstract_inverted_index":{"This":[0,117],"paper":[1],"extends":[2],"learning":[3],"hidden":[4],"unit":[5],"contributions":[6],"(LHUC)":[7],"unsupervised":[8],"speaker":[9,12],"adaptation":[10],"with":[11,128,141],"adaptive":[13],"training":[14,91],"(SAT).":[15],"Contrary":[16],"to":[17,35,44,106,119,136,139],"other":[18],"SAT":[19,140],"approaches,":[20],"the":[21,29,45,54,66,85],"proposed":[22],"technique":[23,68],"does":[24],"not":[25],"require":[26],"speaker-dependent":[27,39,61],"features,":[28],"generation":[30],"of":[31,122],"auxiliary":[32],"generative":[33],"models":[34,108],"estimate":[36],"or":[37,41],"extract":[38],"information,":[40],"any":[42],"changes":[43],"speaker-independent":[46,59,107],"model":[47],"structure.":[48],"SAT-LHUC":[49,67,132],"is":[50],"directly":[51],"integrated":[52],"into":[53],"objective":[55],"and":[56,60,78,98,113,125],"jointly":[57],"learns":[58],"representations.":[62],"We":[63,93],"demonstrate":[64],"that":[65],"can":[69],"match":[70],"feature-space":[71,142],"regression":[72,146],"transforms":[73],"for":[74],"matched":[75],"narrow-band":[76],"data":[77,83],"outperform":[79],"it":[80],"on":[81,109],"wide-band":[82],"when":[84],"runtime":[86],"distribution":[87],"differs":[88],"significantly":[89],"from":[90],"one.":[92],"have":[94],"obtained":[95],"6.5%,":[96],"10%":[97],"18.5%":[99],"relative":[100,120],"word":[101],"error":[102],"rate":[103],"reductions":[104],"compared":[105,127],"Switchboard,":[110],"AMI":[111],"meetings":[112],"TED":[114],"lectures,":[115],"respectively.":[116],"corresponds":[118],"gains":[121],"2%,":[123],"4%":[124],"6%":[126],"non-SAT":[129],"LHUC":[130],"adaptation.":[131],"was":[133],"also":[134],"found":[135],"be":[137],"complementary":[138],"maximum":[143],"likelihood":[144],"linear":[145],"transforms.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}