{"id":"https://openalex.org/W2004497042","doi":"https://doi.org/10.1109/slt.2014.7078604","title":"Improving speaker recognition performance in the domain adaptation challenge using deep neural networks","display_name":"Improving speaker recognition performance in the domain adaptation challenge using deep neural networks","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2004497042","doi":"https://doi.org/10.1109/slt.2014.7078604","mag":"2004497042"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2014.7078604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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/A5000143881","display_name":"Daniel Garcia-Romero","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Garcia-Romero","raw_affiliation_strings":["Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD 21218, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074213973","display_name":"Xiaohui Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaohui Zhang","raw_affiliation_strings":["Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD 21218, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047531480","display_name":"Alan McCree","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan McCree","raw_affiliation_strings":["Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD 21218, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD 21218, USA"],"affiliations":[{"raw_affiliation_string":"Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Human Language Technology Center of Excellence & Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD 21218, USA","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000143881"],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":null,"apc_paid":null,"fwci":18.35327997,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.99125322,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"378","last_page":"383"},"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":0.9980000257492065,"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":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.8221715688705444},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6416449546813965},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6277058720588684},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6165568828582764},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5958455801010132},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5864152908325195},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5827099680900574},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5751389861106873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5406595468521118},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5303317308425903},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4726856052875519},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4261012077331543},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.4243162274360657},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35815948247909546},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07487750053405762}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221715688705444},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6416449546813965},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6277058720588684},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6165568828582764},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5958455801010132},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5864152908325195},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5827099680900574},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5751389861106873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5406595468521118},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5303317308425903},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4726856052875519},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4261012077331543},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.4243162274360657},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35815948247909546},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07487750053405762},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2014.7078604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2014.7078604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Spoken Language Technology Workshop (SLT)","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":29,"referenced_works":["https://openalex.org/W1221962394","https://openalex.org/W1999033484","https://openalex.org/W2026369565","https://openalex.org/W2039057510","https://openalex.org/W2046015436","https://openalex.org/W2067301010","https://openalex.org/W2073017590","https://openalex.org/W2101587318","https://openalex.org/W2121812409","https://openalex.org/W2129379984","https://openalex.org/W2144411866","https://openalex.org/W2150769028","https://openalex.org/W2181594395","https://openalex.org/W2183016404","https://openalex.org/W2186162535","https://openalex.org/W2186517251","https://openalex.org/W2186645306","https://openalex.org/W2294814385","https://openalex.org/W2360384684","https://openalex.org/W2395750323","https://openalex.org/W2401594978","https://openalex.org/W2403282961","https://openalex.org/W2406312423","https://openalex.org/W2901716104","https://openalex.org/W2941689885","https://openalex.org/W2941774902","https://openalex.org/W6686850381","https://openalex.org/W6713727690","https://openalex.org/W6982185968"],"related_works":["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/W2970987681","https://openalex.org/W2181956362","https://openalex.org/W2136153680"],"abstract_inverted_index":{"Traditional":[0],"i-vector":[1],"speaker":[2,67],"recognition":[3,68],"systems":[4],"use":[5,36],"a":[6,21,59,94,135],"Gaussian":[7],"mixture":[8],"model":[9],"(GMM)":[10],"to":[11,39,113,144],"collect":[12,40],"sufficient":[13],"statistics":[14],"(SS).":[15],"Recently,":[16],"replacing":[17],"this":[18,31,150],"GMM":[19],"with":[20,58,93,142],"deep":[22],"neural":[23],"network":[24],"(DNN)":[25],"has":[26],"shown":[27],"promising":[28],"results.":[29],"In":[30],"paper,":[32],"we":[33,79],"explore":[34],"the":[35,43,49,66,81,104,108,114,119,122,127,130,145],"of":[37,48,70,107,138],"DNNs":[38],"SS":[41,57],"for":[42],"unsupervised":[44,85,99],"domain":[45],"adaptation":[46,86],"task":[47],"Domain":[50],"Adaptation":[51],"Challenge":[52],"(DAC).We":[53],"show":[54,102],"that":[55,88,103,121],"collecting":[56],"DNN":[60,82,123],"trained":[61,125],"on":[62,98,126,149],"out-of-domain":[63,72,109,128],"data":[64],"boosts":[65],"performance":[69],"an":[71,84],"system":[73,110,133],"by":[74],"more":[75,139],"than":[76,140],"25%.":[77],"Moreover,":[78],"integrate":[80],"in":[83],"framework,":[87],"uses":[89],"agglomerative":[90],"hierarchical":[91],"clustering":[92],"stopping":[95],"criterion":[96],"based":[97],"calibration,":[100],"and":[101],"initial":[105],"gains":[106],"carry":[111],"over":[112],"final":[115,131],"adapted":[116,132],"system.":[117],"Despite":[118],"fact":[120],"is":[124],"data,":[129],"produces":[134],"relative":[136],"improvement":[137],"30%":[141],"respect":[143],"best":[146],"published":[147],"results":[148],"task.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":18},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":8}],"updated_date":"2026-02-20T08:17:22.645390","created_date":"2025-10-10T00:00:00"}