{"id":"https://openalex.org/W2108952984","doi":"https://doi.org/10.1109/icassp.2011.5947443","title":"Factored covariance modeling for text-independent speaker verification","display_name":"Factored covariance modeling for text-independent speaker verification","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2108952984","doi":"https://doi.org/10.1109/icassp.2011.5947443","mag":"2108952984"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5002548873","display_name":"Eryu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Eryu Wang","raw_affiliation_strings":["IFly Speech Laboratory, University of Science and Technology, China","iFly Speech Laboratory, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFly Speech Laboratory, University of Science and Technology, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFly Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Institute of Infocomm Research (I2R), Agency for Science, Technology and Research (ASTAR), Singapore","Institute for Infocomm Research (I2R), A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), Agency for Science, Technology and Research (ASTAR), Singapore","institution_ids":["https://openalex.org/I115228651"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749735","display_name":"Bin Ma","orcid":"https://orcid.org/0000-0002-9223-9654"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Bin Ma","raw_affiliation_strings":["Institute of Infocomm Research (I2R), Agency for Science, Technology and Research, Singapore","Institute for Infocomm Research (I2R), A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["Institute of Infocomm Research (I2R), Agency for Science, Technology and Research, Singapore","Institute for Infocomm Research (I2R), A*STAR, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Infocomm Research (I2R), Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]},{"raw_affiliation_string":"Institute for Infocomm Research (I2R), A*STAR, Singapore","institution_ids":["https://openalex.org/I115228651","https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["IFly Speech Laboratory, University of Science and Technology, China","iFly Speech Laboratory, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFly Speech Laboratory, University of Science and Technology, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFly Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lirong Dai","raw_affiliation_strings":["IFly Speech Laboratory, University of Science and Technology, China","iFly Speech Laboratory, University of Science and Technology of China, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IFly Speech Laboratory, University of Science and Technology, China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"iFly Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4856","last_page":"4859"},"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":0.9962000250816345,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9728999733924866,"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/covariance","display_name":"Covariance","score":0.7419399619102478},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6036929488182068},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.568985641002655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.557918906211853},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5515246391296387},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5231679081916809},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.5187156796455383},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.518543541431427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4960530698299408},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.4952053129673004},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4894351065158844},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.43077629804611206},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4158395528793335},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35788238048553467},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22227069735527039},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15439057350158691}],"concepts":[{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.7419399619102478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6036929488182068},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.568985641002655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.557918906211853},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5515246391296387},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5231679081916809},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.5187156796455383},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.518543541431427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4960530698299408},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.4952053129673004},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4894351065158844},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.43077629804611206},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4158395528793335},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35788238048553467},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22227069735527039},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15439057350158691},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/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.2011.5947443","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947443","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W103634231","https://openalex.org/W182831726","https://openalex.org/W1589717461","https://openalex.org/W1662191912","https://openalex.org/W1986964250","https://openalex.org/W2041823554","https://openalex.org/W2137944862","https://openalex.org/W2144760012","https://openalex.org/W2147147599","https://openalex.org/W2167022632","https://openalex.org/W6637034065","https://openalex.org/W6684413030"],"related_works":["https://openalex.org/W2118039276","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/W2148323604","https://openalex.org/W2181956362"],"abstract_inverted_index":{"Gaussian":[0,84],"mixture":[1],"models":[2],"(GMMs)":[3],"are":[4],"commonly":[5],"used":[6,24,91],"to":[7,34,43,92],"model":[8],"the":[9,22,44,50,67,94,101],"spectral":[10,53],"distribution":[11],"of":[12,21,69,75,103],"speech":[13,98],"signals":[14],"for":[15],"text-independent":[16],"speaker":[17,39,62,111],"verification.":[18],"Mean":[19],"vectors":[20],"GMM,":[23],"in":[25,37,100],"conjunction":[26],"with":[27],"support":[28],"vector":[29,77],"machine":[30],"(SVM),":[31],"have":[32],"shown":[33],"be":[35],"effective":[36],"characterizing":[38],"information.":[40],"In":[41],"addition":[42],"mean":[45],"vectors,":[46],"covariance":[47,104],"matrices":[48],"capture":[49],"correlation":[51,71],"between":[52,72,96],"features,":[54],"which":[55],"also":[56],"represent":[57],"some":[58],"salient":[59],"information":[60],"about":[61],"identity.":[63],"This":[64],"paper":[65],"investigates":[66],"use":[68],"local":[70],"different":[73],"dimensions":[74],"acoustic":[76],"by":[78],"using":[79],"factor":[80],"analysis":[81],"and":[82],"linear":[83],"model.":[85],"Log-Euclidean":[86],"inner":[87],"product":[88],"kernel":[89],"is":[90],"measure":[93],"similarity":[95],"two":[97],"utterances":[99],"form":[102],"matrices.":[105],"Experiments":[106],"carried":[107],"on":[108],"NIST":[109],"2006":[110],"verification":[112],"tasks":[113],"shows":[114],"promising":[115],"results.":[116]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}