{"id":"https://openalex.org/W2051086261","doi":"https://doi.org/10.1109/icassp.2002.5743814","title":"Combining stochastic feature transformation and handset identification for telephone-based speaker verification","display_name":"Combining stochastic feature transformation and handset identification for telephone-based speaker verification","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2051086261","doi":"https://doi.org/10.1109/icassp.2002.5743814","mag":"2051086261"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743814","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/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":["Center for Multimedia Signal Processing Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hung Hom, China","Center for Multimedia Signal Processing, Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Multimedia Signal Processing Department of Electronic and Information Engineering, Hong Kong Polytechnic University, Hung Hom, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Center for Multimedia Signal Processing, Dept. of Electronic and Information Engineering, The Hong Kong Polytechnic University, China#TAB#","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, USA","Dept. of Electrical Engineering, Princeton University, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Princeton University, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Dept. of Electrical Engineering, Princeton University, 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":null,"apc_paid":null,"fwci":3.6274,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93156544,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"I","last_page":"701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/T11309","display_name":"Music and Audio Processing","score":0.9854000210762024,"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":0.9826550483703613},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.7202385663986206},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.7064857482910156},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6791819930076599},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6390929222106934},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5348087549209595},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5010762214660645},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4473963975906372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3855074942111969},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36222904920578003},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.21535912156105042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15137538313865662},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07513570785522461}],"concepts":[{"id":"https://openalex.org/C2779971919","wikidata":"https://www.wikidata.org/wiki/Q1378949","display_name":"Handset","level":2,"score":0.9826550483703613},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.7202385663986206},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.7064857482910156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791819930076599},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6390929222106934},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5348087549209595},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5010762214660645},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4473963975906372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3855074942111969},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36222904920578003},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.21535912156105042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15137538313865662},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07513570785522461},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","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},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2002.5743814","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743814","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.14.8424","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.8424","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/icassp2002.pdf","raw_type":"text"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/27033","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/27033","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1565765593","https://openalex.org/W1869017930","https://openalex.org/W1893243848","https://openalex.org/W2050693797","https://openalex.org/W2082474452","https://openalex.org/W2119902929","https://openalex.org/W2128279985","https://openalex.org/W2129967803","https://openalex.org/W2157590573","https://openalex.org/W2162125266","https://openalex.org/W2167152389","https://openalex.org/W3141839452","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/W2058771885"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,101],"telephone-based":[3],"speaker":[4],"verification":[5],"systems":[6],"can":[7],"be":[8],"severely":[9],"degraded":[10],"by":[11,16,49,71],"the":[12,33,44,50,61,67,85,90,102,107,114,126],"acoustic":[13],"mismatch":[14],"caused":[15],"telephone":[17,72],"handsets.":[18],"This":[19],"paper":[20],"proposes":[21],"to":[22,31,42,60,112,132],"combine":[23],"a":[24,36,74],"handset":[25,38,47,108],"selector":[26,39,109],"with":[27],"stochastic":[28,55,76,86],"feature":[29,56,63,77],"transformation":[30,78,124],"reduce":[32,125],"mismatch.":[34],"Specifically,":[35],"GMM-based":[37],"is":[40,79,110],"trained":[41],"identify":[43,113],"most":[45],"likely":[46],"used":[48],"claimants,":[51],"and":[52,89,118,122],"then":[53],"handset-specific":[54],"transformations":[57],"are":[58,93],"applied":[59],"distorted":[62],"vectors.":[64],"To":[65],"overcome":[66],"non-linear":[68,123],"distortion":[69],"introduced":[70],"handsets,":[73],"2nd-order":[75],"proposed.":[80],"Estimation":[81],"algorithms":[82],"based":[83,97],"on":[84,98],"matching":[87],"technique":[88],"EM":[91],"algorithm":[92],"derived.":[94],"Experimental":[95],"results":[96],"150":[99],"speakers":[100],"HTIMIT":[103],"corpus":[104],"show":[105],"that":[106,119],"able":[111],"handsets":[115],"accurately":[116],"(98.3%),":[117],"both":[120],"linear":[121],"error":[127],"rate":[128],"significantly":[129],"(from":[130],"12.37%":[131],"5.49%).":[133]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}