{"id":"https://openalex.org/W2160003195","doi":"https://doi.org/10.1109/taslp.2014.2319159","title":"Non-Negative Factor Analysis of Gaussian Mixture Model Weight Adaptation for Language and Dialect Recognition","display_name":"Non-Negative Factor Analysis of Gaussian Mixture Model Weight Adaptation for Language and Dialect Recognition","publication_year":2014,"publication_date":"2014-04-22","ids":{"openalex":"https://openalex.org/W2160003195","doi":"https://doi.org/10.1109/taslp.2014.2319159","mag":"2160003195"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2014.2319159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2319159","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://lirias.kuleuven.be/handle/123456789/443906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041322208","display_name":"Mohamad Hasan Bahari","orcid":"https://orcid.org/0000-0002-4068-449X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamad Hasan Bahari","raw_affiliation_strings":["Center for processing speech and images, Leuven, KU, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for processing speech and images, Leuven, KU, Belgium","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087514947","display_name":"Hugo Van hamme","orcid":"https://orcid.org/0000-0003-1331-5186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo Van hamme","raw_affiliation_strings":["Center for processing speech and images, Leuven, KU, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for processing speech and images, Leuven, KU, Belgium","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Speech@FIT, Brno University of Technology, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech@FIT, Brno University of Technology, Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693435","display_name":"Ahmed Ali","orcid":"https://orcid.org/0000-0002-9186-7544"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed M. Ali","raw_affiliation_strings":["Qatar computing research institute, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qatar computing research institute, Qatar","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073966667","display_name":"Jim Glass","orcid":"https://orcid.org/0000-0002-0148-0224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jim Glass","raw_affiliation_strings":["MIT Computer Science and Artificial Intelligence Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Computer Science and Artificial Intelligence Laboratory, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.5262,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.98053509,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":"7","first_page":"1117","last_page":"1129"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9905999898910522,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9890000224113464,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7145552635192871},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.6317903995513916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.590967059135437},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5822303295135498},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5374048352241516},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5372488498687744},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.49773290753364563},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4853934049606323},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.483218789100647},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47476673126220703},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.460074245929718},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.45182982087135315},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.43669313192367554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37386178970336914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7145552635192871},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6317903995513916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590967059135437},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5822303295135498},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5374048352241516},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5372488498687744},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.49773290753364563},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4853934049606323},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.483218789100647},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47476673126220703},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.460074245929718},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.45182982087135315},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.43669313192367554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37386178970336914},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2014.2319159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2014.2319159","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.470.9374","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.470.9374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://groups.csail.mit.edu/sls//publications/2014/Bahari_IEEE_July2014.pdf","raw_type":"text"},{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/443906","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/443906","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":"IEEE Transactions on Audio Speech and Language Processing, vol. 22 (7), Art.No. 7, (1117-1129)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:lirias2repo.kuleuven.be:123456789/443906","is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/123456789/443906","pdf_url":null,"source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","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":"IEEE Transactions on Audio Speech and Language Processing, vol. 22 (7), Art.No. 7, (1117-1129)","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W153567543","https://openalex.org/W187869248","https://openalex.org/W307699962","https://openalex.org/W1529116532","https://openalex.org/W1576997668","https://openalex.org/W1902027874","https://openalex.org/W1916834241","https://openalex.org/W1970481385","https://openalex.org/W1971273973","https://openalex.org/W1973706390","https://openalex.org/W1983072039","https://openalex.org/W1996601463","https://openalex.org/W2003573652","https://openalex.org/W2023238506","https://openalex.org/W2038262612","https://openalex.org/W2041823554","https://openalex.org/W2049633694","https://openalex.org/W2069620976","https://openalex.org/W2079076391","https://openalex.org/W2082313642","https://openalex.org/W2107455326","https://openalex.org/W2128383159","https://openalex.org/W2136879537","https://openalex.org/W2136922672","https://openalex.org/W2137075158","https://openalex.org/W2139749422","https://openalex.org/W2147147599","https://openalex.org/W2150769028","https://openalex.org/W2172287020","https://openalex.org/W2189248916","https://openalex.org/W2402735123","https://openalex.org/W2403186097","https://openalex.org/W2408021097","https://openalex.org/W2408208090","https://openalex.org/W2594095402","https://openalex.org/W2887979278","https://openalex.org/W2916510398","https://openalex.org/W3017143921","https://openalex.org/W4285072721","https://openalex.org/W4285719527","https://openalex.org/W6606132431","https://openalex.org/W6610794077","https://openalex.org/W6753916174","https://openalex.org/W6759825495"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2151402979","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W2129090883","https://openalex.org/W1516392727","https://openalex.org/W2379906719","https://openalex.org/W2412815366","https://openalex.org/W2181956362"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"show":[2,122,155],"that":[3,72,123,156],"Gaussian":[4],"mixture":[5],"model":[6],"(GMM)":[7],"weights":[8],"carry":[9],"less,":[10],"yet":[11],"complimentary,":[12],"information":[13],"to":[14,71,88,134],"GMM":[15,45],"means":[16],"for":[17,44,175],"language":[18,24,104],"and":[19,48,56,102,109,147,162],"dialect":[20,114],"recognition.":[21],"However,":[22],"state-of-the-art":[23,171],"recognition":[25,91,105,115,131],"systems":[26],"usually":[27],"do":[28],"not":[29],"use":[30],"this":[31,34],"information.":[32],"In":[33],"research,":[35],"a":[36,60,67,148],"non-negative":[37,144],"factor":[38,68],"analysis":[39,69],"(NFA)":[40],"approach":[41,95],"is":[42,53,96],"developed":[43],"weight":[46,137],"decomposition":[47],"adaptation.":[49],"This":[50],"modeling,":[51],"which":[52],"conceptually":[54],"simple":[55],"computationally":[57],"inexpensive,":[58],"suggests":[59],"new":[61],"low-dimensional":[62],"utterance":[63],"representation":[64],"method":[65,127],"using":[66],"similar":[70],"of":[73,160,169,178],"the":[74,89,99,111,124,157,167,170,176],"i-vector":[75,172],"framework.":[76],"The":[77,93,119],"obtained":[78],"subspace":[79,149,164],"vectors":[80,165],"are":[81],"then":[82],"applied":[83],"in":[84],"conjunction":[85],"with":[86],"i-vectors":[87,161],"language/dialect":[90],"problem.":[92],"suggested":[94],"evaluated":[97],"on":[98,110],"NIST":[100],"2011":[101],"RATS":[103],"evaluation":[106,116],"(LRE)":[107],"corpora":[108],"QCRI":[112],"Arabic":[113],"(DRE)":[117],"corpus.":[118],"assessment":[120],"results":[121,132,153],"proposed":[125],"adaptation":[126,138],"yields":[128],"more":[129],"accurate":[130],"compared":[133],"three":[135],"conventional":[136],"approaches,":[139],"namely":[140],"maximum":[141],"likelihood":[142],"re-estimation,":[143],"matrix":[145],"factorization,":[146],"multinomial":[150],"model.":[151],"Experimental":[152],"also":[154],"intermediate-level":[158],"fusion":[159],"NFA":[163],"improves":[166],"performance":[168],"framework":[173],"especially":[174],"case":[177],"short":[179],"utterances.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}