{"id":"https://openalex.org/W2194257527","doi":"https://doi.org/10.21437/interspeech.2015-602","title":"Feature-space speaker adaptation for probabilistic linear discriminant analysis acoustic models","display_name":"Feature-space speaker adaptation for probabilistic linear discriminant analysis acoustic models","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W2194257527","doi":"https://doi.org/10.21437/interspeech.2015-602","mag":"2194257527"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-602","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","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/portal/en/publications/featurespace-speaker-adaptation-for-probabilistic-linear-discriminant-analysis-acoustic-models(d76f15d9-47bf-4768-8213-48ad41c78ee0).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"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":"Liang Lu","raw_affiliation_strings":["Centre for Speech Technology Research, University 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"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Speech Technology Research, University 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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2862","last_page":"2866"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.998199999332428,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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/speech-recognition","display_name":"Speech recognition","score":0.6956530809402466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6796948909759521},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6038221120834351},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5983080863952637},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5676962733268738},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.5660189986228943},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.558380126953125},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.549892246723175},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4815685749053955},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4765760898590088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45811596512794495},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4270830750465393},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4135872423648834},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3536806106567383},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.27409589290618896},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1322072446346283},{"id":"https://openalex.org/keywords/acoustic-wave","display_name":"Acoustic wave","score":0.09566456079483032}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6956530809402466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6796948909759521},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6038221120834351},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5983080863952637},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5676962733268738},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.5660189986228943},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.558380126953125},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.549892246723175},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4815685749053955},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4765760898590088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45811596512794495},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4270830750465393},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4135872423648834},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3536806106567383},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.27409589290618896},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1322072446346283},{"id":"https://openalex.org/C204723758","wikidata":"https://www.wikidata.org/wiki/Q3882459","display_name":"Acoustic wave","level":2,"score":0.09566456079483032},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2015-602","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-602","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/d76f15d9-47bf-4768-8213-48ad41c78ee0","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2015/i15_2862.html","pdf_url":"https://www.research.ed.ac.uk/portal/en/publications/featurespace-speaker-adaptation-for-probabilistic-linear-discriminant-analysis-acoustic-models(d76f15d9-47bf-4768-8213-48ad41c78ee0).html","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:10.1.1.716.6352","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.716.6352","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/2015/liang_is15b.pdf","raw_type":"text"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/d76f15d9-47bf-4768-8213-48ad41c78ee0","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/d76f15d9-47bf-4768-8213-48ad41c78ee0","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":"Lu, L & Renals, S 2015, Feature-space Speaker Adaptation for Probabilistic Linear Discriminant Analysis Acoustic Models. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. pp. 2862-2866. < http://www.isca-speech.org/archive/interspeech_2015/i15_2862.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/d76f15d9-47bf-4768-8213-48ad41c78ee0","is_oa":true,"landing_page_url":"http://www.isca-speech.org/archive/interspeech_2015/i15_2862.html","pdf_url":"https://www.research.ed.ac.uk/portal/en/publications/featurespace-speaker-adaptation-for-probabilistic-linear-discriminant-analysis-acoustic-models(d76f15d9-47bf-4768-8213-48ad41c78ee0).html","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/10","score":0.75,"display_name":"Reduced inequalities"}],"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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2194257527.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W9486812","https://openalex.org/W72757270","https://openalex.org/W1502469360","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1599512239","https://openalex.org/W1967940534","https://openalex.org/W1981706894","https://openalex.org/W1981910148","https://openalex.org/W1984541135","https://openalex.org/W1993721840","https://openalex.org/W2002342963","https://openalex.org/W2012897754","https://openalex.org/W2014966567","https://openalex.org/W2095705004","https://openalex.org/W2101261946","https://openalex.org/W2106554350","https://openalex.org/W2110862220","https://openalex.org/W2121812409","https://openalex.org/W2123237149","https://openalex.org/W2123487311","https://openalex.org/W2125234026","https://openalex.org/W2131342762","https://openalex.org/W2134260474","https://openalex.org/W2142980177","https://openalex.org/W2146871184","https://openalex.org/W2147768505","https://openalex.org/W2150769028","https://openalex.org/W2159786793","https://openalex.org/W2160815625","https://openalex.org/W2165053039","https://openalex.org/W2166637769","https://openalex.org/W2169189000","https://openalex.org/W2172130635","https://openalex.org/W2403195671","https://openalex.org/W2407726486","https://openalex.org/W2793131830","https://openalex.org/W2963963943","https://openalex.org/W3099938644","https://openalex.org/W4302557958"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2048014685","https://openalex.org/W4385672897","https://openalex.org/W2370972896","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W2074132948"],"abstract_inverted_index":{"Probabilistic":[0],"linear":[1,128],"discriminant":[2],"analysis":[3],"(PLDA)":[4],"acoustic":[5,14,28,56,74,81],"models":[6,10,75,94],"extend":[7],"Gaussian":[8],"mixture":[9],"by":[11,112],"factorizing":[12],"the":[13,23,31,42,70,100,103,115],"variability":[15],"using":[16,113],"state-dependent":[17],"and":[18,30,106,119],"observation-dependent":[19],"variables.":[20],"This":[21,58],"enables":[22],"use":[24,77],"of":[25,33,44,72,80],"higher":[26],"dimensional":[27],"features,":[29,82],"capture":[32],"intra-frame":[34],"feature":[35],"corre-lations.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"investigate":[41],"estimation":[43,62],"speaker":[45,60,131],"adaptive":[46],"feature-space":[47,59],"(constrained)":[48],"maximum":[49],"likelihood":[50],"lin-ear":[51],"regression":[52],"transforms":[53,87],"from":[54],"PLDA-based":[55],"models.":[57],"transformation":[61],"approach":[63,101],"is":[64],"potentially":[65],"very":[66],"useful":[67],"due":[68],"to":[69,76,88],"ability":[71],"PLDA":[73,134],"different":[78],"types":[79],"for":[83,95],"example":[84],"applying":[85],"these":[86],"deep":[89],"neural":[90],"network":[91],"(DNN)":[92],"acous-tic":[93],"cross":[96],"adaptation.":[97],"We":[98],"evaluated":[99],"on":[102],"Switchboard":[104],"corpus,":[105],"observe":[107],"significant":[108],"word":[109],"error":[110],"re-duction":[111],"both":[114],"mel-frequency":[116],"cepstral":[117],"coefficients":[118],"DNN":[120],"bottleneck":[121],"features.":[122],"Index":[123],"Terms:":[124],"speech":[125],"recognition,":[126],"probabilistic":[127],"discrim-inant":[129],"analysis,":[130],"adaptation,":[132],"fMLLR,":[133]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}