{"id":"https://openalex.org/W2396877712","doi":"https://doi.org/10.21437/interspeech.2014-290","title":"Performance factor analysis for the 2012 NIST speaker recognition evaluation","display_name":"Performance factor analysis for the 2012 NIST speaker recognition evaluation","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2396877712","doi":"https://doi.org/10.21437/interspeech.2014-290","mag":"2396877712"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-290","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5109812070","display_name":"Alvin F. Mart\u00edn","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alvin F. Martin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084239176","display_name":"Craig S. Greenberg","orcid":"https://orcid.org/0000-0002-6005-8189"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Craig S. Greenberg","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051802422","display_name":"Vincent M. Stanford","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent M. Stanford","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062755751","display_name":"John M. Howard","orcid":"https://orcid.org/0000-0002-3990-5478"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John M. Howard","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082356959","display_name":"George R. Doddington","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George R. Doddington","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110383045","display_name":"John J. Godfrey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John J. Godfrey","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109812070"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.818,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.82570527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1135","last_page":"1138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.993399977684021,"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":0.993399977684021,"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":0.9901000261306763,"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/nist","display_name":"NIST","score":0.8062552213668823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.797308623790741},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6949679851531982},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6569402813911438},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6258298754692078},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5635330080986023},{"id":"https://openalex.org/keywords/environmental-noise","display_name":"Environmental noise","score":0.5114747285842896},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4347954988479614},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4288710057735443},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.4161507189273834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27536624670028687},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1730956733226776},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14719459414482117},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07182788848876953}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8062552213668823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.797308623790741},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949679851531982},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6569402813911438},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6258298754692078},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5635330080986023},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.5114747285842896},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4347954988479614},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4288710057735443},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.4161507189273834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27536624670028687},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1730956733226776},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14719459414482117},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07182788848876953},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-290","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-290","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1586405805","https://openalex.org/W2396887242","https://openalex.org/W2917756095","https://openalex.org/W2942313289"],"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/W2938358845","https://openalex.org/W2997340161"],"abstract_inverted_index":{"The":[0,131],"2012":[1],"NIST":[2],"Speaker":[3],"Recognition":[4],"Evaluation,":[5],"held":[6],"in":[7,36,50,97,116],"the":[8,21,39,48,73,79,82,90,93,102,105,114,117,123],"autumn":[9],"of":[10,18,23,44,54,58,62,64,69,75,85,92,104,122,127,134,142],"2012,":[11],"was":[12],"designed":[13],"to":[14,119,138,147],"examine":[15],"a":[16],"variety":[17],"factors":[19],"affecting":[20],"performance":[22,43,126],"automatic":[24],"systems":[25,34],"for":[26,32,112],"speaker":[27,87,144],"recognition.":[28],"Here":[29],"we":[30],"examine,":[31],"leading":[33],"included":[35],"this":[37],"evaluation,":[38],"observed":[40],"effects":[41,124],"on":[42,125],"five":[45],"such":[46],"factors:":[47],"inclusion":[49],"test":[51,76,98],"segment":[52,77,99],"speech":[53],"environmental":[55],"noise":[56,61,136,145,149],"or":[57],"added":[59,129],"synthetic":[60,128],"one":[63,68],"three":[65],"types":[66],"and":[67,81,101,141],"two":[70],"intensity":[71],"levels,":[72],"duration":[74],"speech,":[78,100],"number":[80],"channel":[83,95],"type":[84,91],"target":[86,106],"training":[88],"sessions,":[89],"microphone":[94],"used":[96],"sex":[103],"speaker.":[107],"This":[108],"evaluation":[109,153],"is":[110,150],"notable":[111],"being":[113],"first":[115],"series":[118],"include":[120],"examination":[121],"noise.":[130],"greater":[132],"impact":[133],"crowd":[135,148],"compared":[137,146],"HVAC":[139],"noise,":[140],"single":[143],"observed.":[151],"Future":[152],"plans":[154],"are":[155],"also":[156],"discussed.":[157]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}