{"id":"https://openalex.org/W2161804528","doi":"https://doi.org/10.1155/s1110865704308048","title":"Stochastic Feature Transformation with Divergence-Based Out-of-Handset Rejection for Robust Speaker Verification","display_name":"Stochastic Feature Transformation with Divergence-Based Out-of-Handset Rejection for Robust Speaker Verification","publication_year":2004,"publication_date":"2004-04-21","ids":{"openalex":"https://openalex.org/W2161804528","doi":"https://doi.org/10.1155/s1110865704308048","mag":"2161804528"},"language":"en","primary_location":{"id":"doi:10.1155/s1110865704308048","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865704308048","pdf_url":null,"source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1155/s1110865704308048","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Centre for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113495286","display_name":"Chi-Leung Tsang","orcid":null},"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":"Chi-Leung Tsang","raw_affiliation_strings":["Centre for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Multimedia Signal Processing, Department of Electronic and Information Engineering, The Hong Kong Polytechnic University, Hung Hom, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072714962","display_name":"Sun\u2010Yuan Kung","orcid":"https://orcid.org/0000-0002-7314-0720"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun-Yuan Kung","raw_affiliation_strings":["Department of Electrical Engineering, Princeton University, NJ, 08544, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, NJ, 08544, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5068768998"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":{"value":1665,"currency":"USD","value_usd":1665},"apc_paid":{"value":1665,"currency":"USD","value_usd":1665},"fwci":5.4251,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.95609167,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2004","issue":"4","first_page":null,"last_page":null},"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":0.9990000128746033,"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":0.9886000156402588,"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/handset","display_name":"Handset","score":0.969256579875946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.638349711894989},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6339575052261353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6255066990852356},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5359792113304138},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4870450794696808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4544556140899658},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3450223207473755},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.19030794501304626},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.07099783420562744}],"concepts":[{"id":"https://openalex.org/C2779971919","wikidata":"https://www.wikidata.org/wiki/Q1378949","display_name":"Handset","level":2,"score":0.969256579875946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.638349711894989},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6339575052261353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6255066990852356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5359792113304138},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4870450794696808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4544556140899658},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3450223207473755},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.19030794501304626},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.07099783420562744},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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:10.1155/s1110865704308048","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865704308048","pdf_url":null,"source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.2.5794","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.2.5794","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eie.polyu.edu.hk/~mwmak/papers/jasp03.pdf","raw_type":"text"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/25406","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/25406","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":"Journal/Magazine Article"}],"best_oa_location":{"id":"doi:10.1155/s1110865704308048","is_oa":true,"landing_page_url":"https://doi.org/10.1155/s1110865704308048","pdf_url":null,"source":{"id":"https://openalex.org/S35920007","display_name":"EURASIP Journal on Advances in Signal Processing","issn_l":"1687-6172","issn":["1687-6172","1687-6180"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Advances in Signal Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1504694836","https://openalex.org/W1558946078","https://openalex.org/W1565765593","https://openalex.org/W1586405805","https://openalex.org/W1869017930","https://openalex.org/W1893243848","https://openalex.org/W2002342963","https://openalex.org/W2050693797","https://openalex.org/W2051086261","https://openalex.org/W2070134780","https://openalex.org/W2082474452","https://openalex.org/W2098692363","https://openalex.org/W2104687512","https://openalex.org/W2111420786","https://openalex.org/W2119902929","https://openalex.org/W2121981798","https://openalex.org/W2125055259","https://openalex.org/W2128279985","https://openalex.org/W2129967803","https://openalex.org/W2138084857","https://openalex.org/W2138534187","https://openalex.org/W2145868107","https://openalex.org/W2146871184","https://openalex.org/W2149115660","https://openalex.org/W2157590573","https://openalex.org/W2160246131","https://openalex.org/W2162125266","https://openalex.org/W2165880886","https://openalex.org/W2167152389","https://openalex.org/W3141839452","https://openalex.org/W4246444635","https://openalex.org/W6991405043"],"related_works":["https://openalex.org/W2361118838","https://openalex.org/W2371584508","https://openalex.org/W3018813917","https://openalex.org/W1975534105","https://openalex.org/W2473734690","https://openalex.org/W2591726676","https://openalex.org/W2045738866","https://openalex.org/W2288493811","https://openalex.org/W4235273077","https://openalex.org/W1976824589"],"abstract_inverted_index":{"The":[0,107],"performance":[1],"of":[2,129,179],"telephone-based":[3,120],"speaker":[4,121],"verification":[5,203],"systems":[6],"can":[7],"be":[8],"severely":[9],"degraded":[10],"by":[11,18,54,91,174,198],"linear":[12],"and":[13,57,100,191],"nonlinear":[14],"acoustic":[15],"distortion":[16],"caused":[17],"telephone":[19],"handsets.":[20,87],"This":[21,70,88],"paper":[22,71],"proposes":[23,73],"to":[24,33,47,65,83,147,183,211],"combine":[25],"a":[26,38,74,101],"handset":[27,43,52,76,109,136],"selector":[28,44,77,110],"with":[29,78,104,113,139,187,195],"stochastic":[30,60],"feature":[31,61,68,116,161],"transformation":[32,117,162,177],"reduce":[34],"the":[35,49,55,66,85,93,97,114,130,135,149,167,176,180,185],"distortion.":[36],"Specifically,":[37],"Gaussian":[39],"mixture":[40],"model":[41],"(GMM)-based":[42],"is":[45,89,111,145],"trained":[46],"identify":[48,84,148],"most":[50],"likely":[51],"used":[53],"claimants,":[56],"then":[58],"handset-specific":[59],"transformations":[62],"are":[63,206],"applied":[64],"distorted":[67],"vectors.":[69],"also":[72,158],"divergence-based":[75],"out-of-handset":[79],"(OOH)":[80],"rejection":[81,143],"capability":[82],"\"unseen\"":[86],"achieved":[90],"measuring":[92],"Jensen":[94],"difference":[95],"between":[96],"selector's":[98],"output":[99],"constant":[102],"vector":[103],"identical":[105],"elements.":[106],"resulting":[108],"combined":[112],"proposed":[115],"technique":[118],"for":[119],"verification.":[122],"Experimental":[123],"results":[124],"based":[125],"on":[126,213],"150":[127],"speakers":[128],"HTIMIT":[131],"corpus":[132],"show":[133],"that":[134,160],"selector,":[137],"either":[138],"or":[140],"without":[141],"OOH":[142],"capability,":[144],"able":[146],"\"seen\"":[150],"handsets":[151,182,190,197],"accurately":[152],"(98.3%":[153],"in":[154],"both":[155],"cases).":[156],"Results":[157],"demonstrate":[159],"performs":[163],"significantly":[164,208],"better":[165],"than":[166],"classical":[168],"cepstral":[169,199],"mean":[170,200],"normalization":[171],"approach.":[172],"Finally,":[173],"using":[175],"parameters":[178],"seen":[181],"transform":[184],"utterances":[186,194],"correctly":[188],"identified":[189],"processing":[192],"those":[193],"unseen":[196],"subtraction":[201],"(CMS),":[202],"error":[204],"rates":[205],"reduced":[207],"(from":[209],"12.41%":[210],"6.59%":[212],"average).":[214]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}