{"id":"https://openalex.org/W2103611452","doi":"https://doi.org/10.1109/icassp.2012.6288891","title":"MLLR transforms of self-organized units as features in speaker recognition","display_name":"MLLR transforms of self-organized units as features in speaker recognition","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2103611452","doi":"https://doi.org/10.1109/icassp.2012.6288891","mag":"2103611452"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 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/A5067041166","display_name":"Man-Hung Siu","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Man-hung Siu","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA","Raytheon BBN Technologies Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN Technologies Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017506600","display_name":"Omer Lang","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omer Lang","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA","Raytheon BBN Technologies Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN Technologies Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065713279","display_name":"H. Gish","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Herbert Gish","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA","Raytheon BBN Technologies Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN Technologies Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001969512","display_name":"Steve Lowe","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steve Lowe","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA","Raytheon BBN Technologies Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN Technologies Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108477624","display_name":"Arthur Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arthur Chan","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA","Raytheon BBN Technologies Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN Technologies Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1306686416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110205522","display_name":"Owen Kimball","orcid":null},"institutions":[{"id":"https://openalex.org/I1306686416","display_name":"RTX (United States)","ror":"https://ror.org/0354t7b78","country_code":"US","type":"company","lineage":["https://openalex.org/I1306686416"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Owen Kimball","raw_affiliation_strings":["Raytheon BBN Technologies, Cambridge, MA, USA","Raytheon BBN Technologies Cambridge, MA 02138, USA"],"affiliations":[{"raw_affiliation_string":"Raytheon BBN Technologies, Cambridge, MA, USA","institution_ids":["https://openalex.org/I1306686416"]},{"raw_affiliation_string":"Raytheon BBN Technologies Cambridge, MA 02138, USA","institution_ids":["https://openalex.org/I1306686416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5067041166"],"corresponding_institution_ids":["https://openalex.org/I1306686416"],"apc_list":null,"apc_paid":null,"fwci":0.8563,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.79684359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4385","last_page":"4388"},"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":0.9993000030517578,"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":0.9980000257492065,"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":0.8315511345863342},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.8168533444404602},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8018408417701721},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6227519512176514},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5815985202789307},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5626053214073181},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5626046061515808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5584457516670227},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.537307620048523},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49135342240333557},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46635380387306213},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4653433561325073},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4530940651893616},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43366900086402893},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4291730523109436},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09022578597068787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8315511345863342},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8168533444404602},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8018408417701721},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6227519512176514},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5815985202789307},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5626053214073181},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5626046061515808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5584457516670227},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.537307620048523},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49135342240333557},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46635380387306213},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4653433561325073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4530940651893616},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43366900086402893},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4291730523109436},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09022578597068787},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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},{"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/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"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":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W51277926","https://openalex.org/W82886505","https://openalex.org/W308497914","https://openalex.org/W1513618424","https://openalex.org/W1553271421","https://openalex.org/W1576520375","https://openalex.org/W2002342963","https://openalex.org/W2087863531","https://openalex.org/W2099424804","https://openalex.org/W2151402979","https://openalex.org/W2167845555","https://openalex.org/W2168561756","https://openalex.org/W2399869768","https://openalex.org/W6633168720","https://openalex.org/W6634442568"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2938358845"],"abstract_inverted_index":{"Using":[0],"speaker":[1,16,114],"adaptation":[2,11,47,83],"parameters,":[3,48],"such":[4,38],"as":[5,13,39],"maximum":[6],"likelihood":[7],"linear":[8],"regression":[9],"(MLLR)":[10],"matrices,":[12],"features":[14],"for":[15,31,65,179],"recognition":[17,115,180],"(SR)":[18],"has":[19],"been":[20],"shown":[21],"to":[22,44,73,86,134],"perform":[23],"well":[24],"and":[25,121,153],"can":[26,99,161,171],"also":[27,142],"provide":[28],"complementary":[29],"information":[30],"fusion":[32],"with":[33],"other":[34],"acoustic-based":[35],"SR":[36,54,156],"systems,":[37],"GMM-based":[40],"systems.":[41],"In":[42],"order":[43],"estimate":[45],"the":[46,53,70,82,92,111,151],"a":[49,137],"speech":[50],"recognizer":[51,66],"in":[52,59],"domain":[55],"is":[56],"required":[57],"which":[58],"turn":[60],"requires":[61],"transcribed":[62,105,177],"training":[63,76,181],"data":[64,119,178],"training.":[67],"This":[68,167],"limits":[69],"approach":[71,85],"only":[72],"domains":[74,87],"where":[75],"transcriptions":[77],"are":[78,182],"available.":[79,183],"To":[80],"generalize":[81],"parameter":[84],"without":[88,102],"transcriptions,":[89],"we":[90,149],"propose":[91],"use":[93],"of":[94],"self-organized":[95],"unit":[96],"recognizers":[97,130,141,170],"that":[98,123],"be":[100,162,172],"trained":[101],"supervision":[103],"(or":[104],"data).":[106],"We":[107],"report":[108],"results":[109],"on":[110],"2002":[112],"NIST":[113],"evaluation":[116],"(SRE2002)":[117],"extended":[118],"set":[120],"show":[122],"using":[124,136,145],"MLLR":[125],"parameters":[126],"estimated":[127],"from":[128],"SOU":[129,140,169],"give":[131],"comparable":[132],"performance":[133],"systems":[135],"matched":[138],"recognizers.":[139,147],"outperform":[143],"those":[144],"cross-lingual":[146],"When":[148],"fused":[150],"SOU-":[152],"word":[154],"recognizers,":[155],"equal":[157],"error":[158],"rate":[159],"(EER)":[160],"reduced":[163],"by":[164],"another":[165],"15%.":[166],"suggests":[168],"useful":[173],"whether":[174],"or":[175],"not":[176]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}