{"id":"https://openalex.org/W2165254250","doi":"https://doi.org/10.1109/icassp.2003.1198749","title":"Comparison of discriminative training methods for speaker verification","display_name":"Comparison of discriminative training methods for speaker verification","publication_year":2003,"publication_date":"2003-11-21","ids":{"openalex":"https://openalex.org/W2165254250","doi":"https://doi.org/10.1109/icassp.2003.1198749","mag":"2165254250"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198749","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5102725787","display_name":"Chengyuan Ma","orcid":"https://orcid.org/0000-0001-5126-5883"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengyuan Ma","raw_affiliation_strings":["Microsoft Research Asia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087298985","display_name":"Eric Chang","orcid":"https://orcid.org/0000-0002-9678-5994"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"E. Chang","raw_affiliation_strings":["Microsoft Research Asia, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":0.7661,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.73027851,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"192"},"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":0.9912999868392944,"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":0.9498000144958496,"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/discriminative-model","display_name":"Discriminative model","score":0.8919702768325806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7113932967185974},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6821123361587524},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6362349987030029},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.6289287805557251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6225552558898926},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6063013076782227},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5628979206085205},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5506533980369568},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.49487966299057007},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.36333224177360535},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20211848616600037},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.16335365176200867}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8919702768325806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7113932967185974},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6821123361587524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6362349987030029},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.6289287805557251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6225552558898926},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6063013076782227},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5628979206085205},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5506533980369568},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.49487966299057007},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.36333224177360535},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20211848616600037},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.16335365176200867},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1198749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198749","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1852256319","https://openalex.org/W2041823554","https://openalex.org/W2078953162","https://openalex.org/W2080861011","https://openalex.org/W2108072092","https://openalex.org/W2108105213","https://openalex.org/W2136859047","https://openalex.org/W6638924092"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W1503532423","https://openalex.org/W1197719229","https://openalex.org/W2381158726","https://openalex.org/W1992796048","https://openalex.org/W1967494390","https://openalex.org/W2129090883","https://openalex.org/W3013496002","https://openalex.org/W1516392727","https://openalex.org/W2465363361"],"abstract_inverted_index":{"The":[0],"maximum":[1,7,72],"likelihood":[2],"estimation":[3],"(MLE)":[4],"and":[5,22,80,119],"Bayesian":[6],"a-posteriori":[8],"(MAP)":[9],"adaptation":[10],"methods":[11,63,105],"for":[12,24,70,106],"Gaussian":[13],"mixture":[14],"models":[15],"(GMM)":[16],"have":[17],"proven":[18],"to":[19,64],"be":[20],"effective":[21],"efficient":[23],"speaker":[25,30,56,91,107],"verification,":[26],"even":[27],"though":[28],"each":[29],"model":[31],"is":[32,117],"trained":[33],"using":[34,47,59],"only":[35],"his":[36],"own":[37],"training":[38,62,99],"utterances.":[39],"Discriminative":[40],"criteria":[41],"aim":[42],"at":[43],"increasing":[44],"discriminability":[45],"by":[46],"out-of-class":[48],"data.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"consider":[54],"the":[55,71,88,102],"verification":[57,108],"task":[58],"three":[60],"discriminative":[61,124],"compare":[65],"performance.":[66,113],"Comparisons":[67],"are":[68],"discussed":[69],"mutual":[73],"information":[74],"(MMI),":[75],"minimum":[76],"classification":[77],"error":[78],"(MCE)":[79],"figure":[81],"of":[82,111],"merit":[83],"(FOM)":[84],"criteria.":[85],"Experiments":[86],"on":[87],"1996":[89],"NIST":[90],"recognition":[92],"evaluation":[93],"data":[94],"set":[95],"show":[96],"that":[97],"FOM":[98],"method":[100],"outperforms":[101],"other":[103],"two":[104],"in":[109],"terms":[110],"system":[112],"Meanwhile,":[114],"logistic":[115],"regression":[116],"investigated":[118],"successfully":[120],"employed":[121],"as":[122],"a":[123],"score-normalization":[125],"technique.":[126]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}