{"id":"https://openalex.org/W2054060258","doi":"https://doi.org/10.1109/icassp.2014.6853889","title":"JFA-based front ends for speaker recognition","display_name":"JFA-based front ends for speaker recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2054060258","doi":"https://doi.org/10.1109/icassp.2014.6853889","mag":"2054060258"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 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/A5036466893","display_name":"Patrick Kenny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Patrick Kenny","raw_affiliation_strings":["Centre de recherche informatique de Montr\u00e9al (CRIM)","[Centre de recherche informatique de Montr\u00e9al (CRIM)]"],"affiliations":[{"raw_affiliation_string":"Centre de recherche informatique de Montr\u00e9al (CRIM)","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"[Centre de recherche informatique de Montr\u00e9al (CRIM)]","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061939508","display_name":"Themos Stafylakis","orcid":"https://orcid.org/0000-0002-9227-3588"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Themos Stafylakis","raw_affiliation_strings":["Centre de recherche informatique de Montr\u00e9al (CRIM)","[Centre de recherche informatique de Montr\u00e9al (CRIM)]"],"affiliations":[{"raw_affiliation_string":"Centre de recherche informatique de Montr\u00e9al (CRIM)","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"[Centre de recherche informatique de Montr\u00e9al (CRIM)]","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061517549","display_name":"Pierre Ouellet","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pierre Ouellet","raw_affiliation_strings":["Centre de recherche informatique de Montr\u00e9al (CRIM)","[Centre de recherche informatique de Montr\u00e9al (CRIM)]"],"affiliations":[{"raw_affiliation_string":"Centre de recherche informatique de Montr\u00e9al (CRIM)","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"[Centre de recherche informatique de Montr\u00e9al (CRIM)]","institution_ids":["https://openalex.org/I4210111842"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100737270","display_name":"Md. Jahangir Alam","orcid":"https://orcid.org/0000-0002-3743-9661"},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Md. Jahangir Alam","raw_affiliation_strings":["Centre de recherche informatique de Montr\u00e9al (CRIM)","[Centre de recherche informatique de Montr\u00e9al (CRIM)]"],"affiliations":[{"raw_affiliation_string":"Centre de recherche informatique de Montr\u00e9al (CRIM)","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"[Centre de recherche informatique de Montr\u00e9al (CRIM)]","institution_ids":["https://openalex.org/I4210111842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036466893"],"corresponding_institution_ids":["https://openalex.org/I4210111842"],"apc_list":null,"apc_paid":null,"fwci":8.8258,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.97757964,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1705","last_page":"1709"},"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":0.9987000226974487,"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":0.9957000017166138,"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":0.781470537185669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7495194673538208},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.7491765022277832},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7351728677749634},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7202752828598022},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.48548319935798645},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.46699845790863037},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.44016069173812866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40923693776130676},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3957032561302185},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1308887004852295}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.781470537185669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495194673538208},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.7491765022277832},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7351728677749634},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7202752828598022},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.48548319935798645},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.46699845790863037},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.44016069173812866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40923693776130676},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3957032561302185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1308887004852295},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6853889","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W72086072","https://openalex.org/W181305587","https://openalex.org/W182365161","https://openalex.org/W204053250","https://openalex.org/W1981706894","https://openalex.org/W2040105822","https://openalex.org/W2046069883","https://openalex.org/W2064364374","https://openalex.org/W2090716422","https://openalex.org/W2121415728","https://openalex.org/W2136879537","https://openalex.org/W2150769028","https://openalex.org/W2168561756","https://openalex.org/W2186774823","https://openalex.org/W2396511675","https://openalex.org/W2404632011","https://openalex.org/W2406312423","https://openalex.org/W2941234773","https://openalex.org/W6602938086","https://openalex.org/W6607467483","https://openalex.org/W6660815749","https://openalex.org/W6712575916","https://openalex.org/W6713617475","https://openalex.org/W6713727690"],"related_works":["https://openalex.org/W2158491338","https://openalex.org/W2807901368","https://openalex.org/W2133733652","https://openalex.org/W2072658171","https://openalex.org/W2606392311","https://openalex.org/W2320042380","https://openalex.org/W4385956668","https://openalex.org/W2900895161","https://openalex.org/W4380838366","https://openalex.org/W1560125148"],"abstract_inverted_index":{"We":[0,92,128,212],"discuss":[1],"the":[2,5,35,124,218,234],"limitations":[3],"of":[4,8,31,37,47,52,69,203,217],"i-vector":[6],"representation":[7],"speech":[9],"segments":[10],"in":[11,28,57,79,89,95,113,231],"speaker":[12,72,74,97,140,150,173],"recognition":[13,151],"and":[14,39,76,85,197],"explain":[15],"how":[16],"Joint":[17],"Factor":[18],"Analysis":[19],"(JFA)":[20],"can":[21],"serve":[22],"as":[23,146,175,189],"an":[24],"alternative":[25],"feature":[26,177],"extractor":[27],"a":[29,43,58,110,130,135,165,176,215],"variety":[30],"ways.":[32],"Building":[33],"on":[34,100,153,201],"work":[36],"Zhao":[38],"Dong,":[40],"we":[41,156],"implemented":[42],"variational":[44],"Bayes":[45],"treatment":[46],"JFA":[48,166,184],"which":[49,226],"accommodates":[50],"adaptation":[51,88,107,145],"universal":[53],"background":[54],"models":[55],"(UBMs)":[56],"natural":[59],"way.":[60],"This":[61],"allows":[62],"us":[63],"to":[64,81,109,159,180,190,228],"experiment":[65],"with":[66,84,105,143,168],"several":[67],"types":[68],"features":[70],"for":[71],"recognition:":[73],"factors":[75,78,141,170,174],"diagonal":[77,169],"addition":[80],"i-vectors,":[82],"extracted":[83,142],"without":[86],"UBM":[87,106,144],"each":[90],"case.":[91],"found":[93],"that,":[94],"text-independent":[96],"verification":[98],"experiments":[99,152],"NIST":[101],"data,":[102,155],"extracting":[103],"i-vectors":[104],"led":[108],"10%":[111,132],"reduction":[112,133],"equal":[114],"error":[115],"rates":[116],"although":[117],"performance":[118,163,232],"did":[119],"not":[120],"improve":[121],"consistently":[122],"over":[123,233],"whole":[125,209,235],"DET":[126,236],"curve.":[127,237],"achieved":[129],"further":[131],"(with":[134],"similar":[136],"inconsistency)":[137],"by":[138,223],"using":[139,164],"features.":[147],"In":[148],"text-dependent":[149],"RSR2015":[154],"were":[157],"able":[158],"achieve":[160],"very":[161,204],"good":[162],"model":[167,185,191],"but":[171],"no":[172],"extractor.":[178],"Contrary":[179],"standard":[181],"practice,":[182],"this":[183],"was":[186,199],"configured":[187],"so":[188],"speakerphrase":[192],"combinations":[193],"(rather":[194,207],"than":[195,208],"speakers)":[196],"it":[198],"trained":[200],"utterances":[202],"short":[205],"duration":[206],"recording":[210],"sessions).":[211],"also":[213],"present":[214],"variant":[216],"length":[219],"normalization":[220],"trick":[221],"inspired":[222],"uncertainty":[224],"propagation":[225],"leads":[227],"substantial":[229],"gains":[230]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}