{"id":"https://openalex.org/W2043994950","doi":"https://doi.org/10.1109/icassp.2014.6854358","title":"Effective use of DCTS for contextualizing features for speaker recognition","display_name":"Effective use of DCTS for contextualizing features for speaker recognition","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2043994950","doi":"https://doi.org/10.1109/icassp.2014.6854358","mag":"2043994950"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5060382325","display_name":"Mitchell McLaren","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mitchell McLaren","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103585404","display_name":"Nicolas Scheffer","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicolas Scheffer","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Luciana Ferrer","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101648572","display_name":"Yun Lei","orcid":"https://orcid.org/0000-0003-4572-6078"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]},{"id":"https://openalex.org/I4210099336","display_name":"Menlo School","ror":"https://ror.org/01240pn49","country_code":"US","type":"education","lineage":["https://openalex.org/I4210099336"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yun Lei","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, California, USA","Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, California, USA","institution_ids":["https://openalex.org/I1298353152"]},{"raw_affiliation_string":"Speech Technol. & Res. Lab., SRI Int., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152","https://openalex.org/I4210099336"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2004","issue":null,"first_page":"4027","last_page":"4031"},"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":0.9979000091552734,"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":0.9925000071525574,"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":0.6252664923667908},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5987748503684998},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5262792706489563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35480064153671265},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33259889483451843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6252664923667908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5987748503684998},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5262792706489563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35480064153671265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33259889483451843}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854358","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W651157033","https://openalex.org/W1481676178","https://openalex.org/W1492380776","https://openalex.org/W2089213408","https://openalex.org/W2096472660","https://openalex.org/W2121750345","https://openalex.org/W2121812409","https://openalex.org/W2130105997","https://openalex.org/W2140836279","https://openalex.org/W2150769028","https://openalex.org/W2157821739","https://openalex.org/W2159948109","https://openalex.org/W2295098554","https://openalex.org/W2396197757","https://openalex.org/W2397474108","https://openalex.org/W2917583897","https://openalex.org/W3145829579","https://openalex.org/W4245657124","https://openalex.org/W6621565597","https://openalex.org/W6674330524","https://openalex.org/W6697089127","https://openalex.org/W6712105053","https://openalex.org/W6712467859","https://openalex.org/W6827741400"],"related_works":["https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W4313854686","https://openalex.org/W321304764","https://openalex.org/W2249138175","https://openalex.org/W2611678594","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2029134149"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"a":[3,21,80],"new":[4],"approach":[5,82,103],"for":[6,9,49,55],"contextualizing":[7],"features":[8],"speaker":[10,56,121],"recognition":[11,57,122],"through":[12],"the":[13,25,31,61,65,91,105,118],"discrete":[14],"cosine":[15],"transform":[16,23],"(DCT).":[17],"Specifically,":[18],"we":[19],"apply":[20],"2D-DCT":[22,77],"on":[24,117],"Mel":[26,33],"filterbank":[27],"outputs":[28],"to":[29,114,140],"replace":[30],"common":[32],"frequency":[34],"cepstral":[35],"coefficients":[36,78,99,136],"(MFCCs)":[37],"appended":[38,108],"by":[39,112],"deltas":[40,111],"and":[41,52,60,129],"double":[42,110],"deltas.":[43],"A":[44],"thorough":[45],"comparison":[46],"of":[47,63,67,76,85],"algorithms":[48],"delta":[50],"computation":[51],"DCT-based":[53],"contextualization":[54],"is":[58,73],"provided":[59],"effect":[62],"varying":[64],"size":[66],"analysis":[68],"window":[69],"in":[70,126],"each":[71],"case":[72],"considered.":[74],"Selection":[75],"using":[79,90,101],"zig-zag":[81],"permits":[83],"definition":[84],"an":[86],"arbitrary":[87],"feature":[88],"dimension":[89],"most":[92],"energized":[93],"coefficients.":[94],"We":[95],"show":[96],"that":[97],"60":[98],"computed":[100],"our":[102],"outperforms":[104],"standard":[106],"MFCCs":[107],"with":[109],"up":[113],"25%":[115],"relative":[116],"NIST":[119],"2012":[120],"evaluation":[123],"(SRE)":[124],"corpus":[125],"both":[127],"Cprimary":[128],"equal":[130],"error":[131],"rate":[132],"(EER)":[133],"while":[134],"additional":[135],"increase":[137],"system":[138],"robustness":[139],"noise.":[141]},"counts_by_year":[{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}