{"id":"https://openalex.org/W2157084746","doi":"https://doi.org/10.1109/icassp.2004.1325987","title":"MPE-based discriminative linear transform for speaker adaptation","display_name":"MPE-based discriminative linear transform for speaker adaptation","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2157084746","doi":"https://doi.org/10.1109/icassp.2004.1325987","mag":"2157084746"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5016797233","display_name":"L. Wang","orcid":"https://orcid.org/0000-0002-5189-7562"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"L. Wang","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P. Woodland","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016797233"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":4.9467,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95230367,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"321"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9900000095367432,"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/discriminative-model","display_name":"Discriminative model","score":0.9314329624176025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7547963857650757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6554357409477234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5345404148101807},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.5095193982124329},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5065099000930786},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4888266921043396},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4729970097541809},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.462496280670166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2243623435497284},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07760298252105713},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07492190599441528}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9314329624176025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7547963857650757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6554357409477234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5345404148101807},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.5095193982124329},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5065099000930786},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4888266921043396},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4729970097541809},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.462496280670166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2243623435497284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07760298252105713},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07492190599441528},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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:10.1109/icassp.2004.1325987","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325987","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.5968","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.5968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mi.eng.cam.ac.uk/reports/svr-ftp/wang_icassp2004.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W127575240","https://openalex.org/W184549729","https://openalex.org/W233468731","https://openalex.org/W2002342963","https://openalex.org/W2003123121","https://openalex.org/W2036089637","https://openalex.org/W2114973313","https://openalex.org/W2126033156","https://openalex.org/W2146871184","https://openalex.org/W2150907703","https://openalex.org/W3139760602","https://openalex.org/W3149335959","https://openalex.org/W6608993760"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W1482209366","https://openalex.org/W2110523656","https://openalex.org/W2521627374","https://openalex.org/W2981954115"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,66],"discriminative":[3,20,69],"method":[4,70],"for":[5,46,71,83],"speaker":[6],"adaptation,":[7],"where":[8],"the":[9,19,38,50],"minimum":[10],"phone":[11],"error":[12],"(MPE)":[13],"criterion":[14],"is":[15,34],"used":[16],"to":[17,36],"estimate":[18],"linear":[21],"transforms":[22],"(DLTs),":[23],"including":[24],"both":[25,63],"mean":[26],"and":[27,65],"diagonal":[28],"variance":[29],"transforms.":[30],"The":[31],"I-smoothing":[32],"technique":[33],"essential":[35],"improve":[37],"generalization":[39],"of":[40],"DLTs.":[41],"Experiments":[42],"on":[43,49,76],"supervised":[44],"adaptation":[45],"non-native":[47],"speakers":[48],"North":[51],"American":[52],"Business":[53],"(NAB)":[54],"Spoke":[55],"3":[56],"task":[57],"show":[58],"that":[59],"MPE-based":[60],"DLT":[61,78],"outperforms":[62],"MLLR":[64],"previously":[67],"proposed":[68],"transform":[72],"estimation.":[73],"Preliminary":[74],"experiments":[75],"unsupervised":[77],"estimation":[79],"are":[80],"also":[81],"reported":[82],"conversational":[84],"telephone":[85],"speech":[86],"transcription.":[87]},"counts_by_year":[{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}