{"id":"https://openalex.org/W2405354182","doi":"https://doi.org/10.1109/icassp.2016.7472742","title":"SNR-invariant PLDA with multiple speaker subspaces","display_name":"SNR-invariant PLDA with multiple speaker subspaces","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2405354182","doi":"https://doi.org/10.1109/icassp.2016.7472742","mag":"2405354182"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5100368199","display_name":"Na Li","orcid":"https://orcid.org/0000-0003-2669-0233"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Na Li","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100368199"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":2.6504,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91885056,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5565","last_page":"5569"},"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":0.9969000220298767,"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":0.9603999853134155,"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/computer-science","display_name":"Computer science","score":0.6991990804672241},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6791622638702393},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.6673511266708374},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5969057083129883},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5553523302078247},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.5519600510597229},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4637473225593567},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45608943700790405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44478002190589905},{"id":"https://openalex.org/keywords/likelihood-ratio-test","display_name":"Likelihood-ratio test","score":0.42601609230041504},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42114028334617615},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.41221657395362854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36752206087112427},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32243409752845764},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2543741762638092},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15364041924476624}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991990804672241},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6791622638702393},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6673511266708374},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5969057083129883},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5553523302078247},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.5519600510597229},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4637473225593567},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45608943700790405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44478002190589905},{"id":"https://openalex.org/C9483764","wikidata":"https://www.wikidata.org/wiki/Q585740","display_name":"Likelihood-ratio test","level":2,"score":0.42601609230041504},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42114028334617615},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.41221657395362854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36752206087112427},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32243409752845764},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2543741762638092},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15364041924476624},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2016.7472742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/107270","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/107270","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Paper"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/67034","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/67034","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W82277249","https://openalex.org/W775331923","https://openalex.org/W1501458753","https://openalex.org/W1540327379","https://openalex.org/W1662191912","https://openalex.org/W1663973292","https://openalex.org/W1968709559","https://openalex.org/W1970872899","https://openalex.org/W1994244061","https://openalex.org/W2023831651","https://openalex.org/W2037786411","https://openalex.org/W2121812409","https://openalex.org/W2129379984","https://openalex.org/W2143054781","https://openalex.org/W2145846419","https://openalex.org/W2150769028","https://openalex.org/W2159736522","https://openalex.org/W2168959749","https://openalex.org/W2288252882","https://openalex.org/W2295897503","https://openalex.org/W2396361679","https://openalex.org/W2397634864","https://openalex.org/W2400085354","https://openalex.org/W2400341349","https://openalex.org/W2405476549","https://openalex.org/W2405505124","https://openalex.org/W2406312423","https://openalex.org/W2406454439","https://openalex.org/W2406521968","https://openalex.org/W2407342067","https://openalex.org/W2594639291","https://openalex.org/W3145164839","https://openalex.org/W4246070010","https://openalex.org/W6603346014","https://openalex.org/W6622345507","https://openalex.org/W6632370842","https://openalex.org/W6637034065","https://openalex.org/W6697233748","https://openalex.org/W6712315371","https://openalex.org/W6712325649","https://openalex.org/W6713383670","https://openalex.org/W6713590052","https://openalex.org/W6713727690","https://openalex.org/W6713776800"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W2051274299","https://openalex.org/W1521299571","https://openalex.org/W468945283","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W3096066489"],"abstract_inverted_index":{"To":[0],"deal":[1],"with":[2,14,86,163],"the":[3,6,32,44,48,69,73,96,124,164],"mismatch":[4],"between":[5],"enrollment":[7],"and":[8,99,128,148,154,167],"test":[9],"utterances":[10,85,104],"caused":[11],"by":[12,62],"noise":[13,70,88],"different":[15,87,93],"signal-to-noise":[16],"ratios":[17],"(SNR),":[18],"we":[19,117],"have":[20],"recently":[21],"proposed":[22],"an":[23],"SNR-invariant":[24,168],"PLDA":[25,126,166],"model":[26,127],"for":[27],"robust":[28],"speaker":[29,57,65,121,153],"verification.":[30],"In":[31,112],"model,":[33],"SNR-specific":[34],"information":[35,40],"were":[36],"separated":[37],"from":[38,84,103],"speaker-specific":[39],"through":[41],"marginalizing":[42],"out":[43],"SNR":[45,107,155],"factors":[46],"during":[47],"scoring":[49],"process.":[50],"However,":[51],"this":[52,79,115,142,146],"modeling":[53,151],"approach":[54],"assumes":[55],"that":[56,81,100,145],"variabilities":[58,156],"can":[59],"be":[60],"captured":[61],"a":[63],"single":[64],"subspace":[66],"regardless":[67],"of":[68,72,95,114,152],"level":[71],"utterances.":[74],"We":[75],"will":[76,90],"show":[77],"in":[78],"paper":[80,143],"i-vectors":[82,101],"extracted":[83,102],"levels":[89],"shift":[91],"to":[92,109,123,133,158],"regions":[94],"i-vector":[97],"space":[98],"having":[105],"similar":[106],"tend":[108],"cluster":[110],"together.":[111],"view":[113],"observation,":[116],"propose":[118],"introducing":[119],"multiple":[120,130],"subspaces":[122],"SNR-invariance":[125],"use":[129],"covariance":[131],"matrices":[132],"represent":[134],"SNR-dependent":[135],"channel":[136],"variability.":[137],"Through":[138],"NIST":[139],"2012":[140],"SRE,":[141],"demonstrates":[144],"finer":[147],"more":[149],"precise":[150],"leads":[157],"better":[159],"performance":[160],"when":[161],"compared":[162],"conventional":[165],"PLDA.":[169]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}