{"id":"https://openalex.org/W173795834","doi":"https://doi.org/10.21437/interspeech.2004-507","title":"A new approach to channel robust speaker verification via constrained stochastic feature transformation","display_name":"A new approach to channel robust speaker verification via constrained stochastic feature transformation","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W173795834","doi":"https://doi.org/10.21437/interspeech.2004-507","mag":"173795834"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-507","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105933835","display_name":"Kwok-Kwong Yiu","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":"Kwok-kwong Yiu","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096860727","display_name":"Ming-Cheung Cheun","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":"Ming-Cheung Cheun","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun-Yuan Kung","raw_affiliation_strings":["Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1753","last_page":"1756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.97079998254776,"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":0.7539474368095398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7057794332504272},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6519125699996948},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.6181262135505676},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5032755732536316},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49805474281311035},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48693835735321045},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4710055887699127},{"id":"https://openalex.org/keywords/model-transformation","display_name":"Model transformation","score":0.46200084686279297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4352002739906311},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4336162805557251},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4262784421443939},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4183158278465271},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41342511773109436}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7539474368095398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7057794332504272},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6519125699996948},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.6181262135505676},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5032755732536316},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49805474281311035},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48693835735321045},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4710055887699127},{"id":"https://openalex.org/C2779791154","wikidata":"https://www.wikidata.org/wiki/Q258040","display_name":"Model transformation","level":3,"score":0.46200084686279297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4352002739906311},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4336162805557251},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4262784421443939},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4183158278465271},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41342511773109436},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-507","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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":10,"referenced_works":["https://openalex.org/W43959665","https://openalex.org/W97107628","https://openalex.org/W175297027","https://openalex.org/W2041823554","https://openalex.org/W2069976350","https://openalex.org/W2098692363","https://openalex.org/W2102063998","https://openalex.org/W2128391065","https://openalex.org/W2148154194","https://openalex.org/W2161804528"],"related_works":["https://openalex.org/W112947718","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W1998549096","https://openalex.org/W2767892728","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,26,30],"constrained":[4],"stochastic":[5],"feature":[6,17],"transformation":[7,18,42,114],"algorithm":[8,14],"for":[9],"robust":[10],"speaker":[11,37,55],"verification.":[12,61],"The":[13,41,109],"computes":[15],"the":[16,22,36,48,53,65,67,79,86,112,121],"parameters":[19],"based":[20,77],"on":[21,78],"statistical":[23],"difference":[24],"between":[25],"test":[27,49],"utterance":[28,50],"and":[29,38,57,97,107],"composite":[31],"GMM":[32],"formed":[33],"by":[34],"combining":[35],"background":[39,58],"models.":[40],"is":[43,116],"then":[44],"used":[45],"to":[46,51,103],"transform":[47],"fit":[52,71],"clean":[54],"model":[56,59],"before":[60],"By":[62],"implicitly":[63],"constraining":[64],"transformation,":[66],"transformed":[68],"features":[69],"can":[70],"both":[72,93],"models":[73],"simultaneously.":[74],"Experimental":[75],"results":[76],"2001":[80],"NIST":[81],"evaluation":[82],"set":[83],"show":[84],"that":[85],"proposed":[87,113,125],"algorithms":[88],"achieves":[89],"significant":[90],"improvement":[91],"in":[92,126],"equal":[94],"error":[95],"rate":[96],"minimum":[98],"detection":[99],"cost":[100],"when":[101],"compared":[102],"cepstral":[104],"mean":[105],"subtraction":[106],"Z-norm.":[108],"performance":[110],"of":[111],"approach":[115],"also":[117],"slightly":[118],"better":[119],"than":[120],"short-time":[122],"Gaussianization":[123],"method":[124],"[1].":[127]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}