{"id":"https://openalex.org/W2293955729","doi":"https://doi.org/10.21437/interspeech.2011-631","title":"Speaker identification for whispered speech using a training feature transformation from neutral to whisper","display_name":"Speaker identification for whispered speech using a training feature transformation from neutral to whisper","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2293955729","doi":"https://doi.org/10.21437/interspeech.2011-631","mag":"2293955729"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-631","doi":"https://doi.org/10.21437/interspeech.2011-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-631","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2011","raw_type":"proceedings-article"},"volume":null,"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/A5018483554","display_name":"Xing Fan","orcid":"https://orcid.org/0000-0002-0178-6442","observed_orcids":["https://orcid.org/0000-0002-0178-6442"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing Fan","raw_affiliation_strings":["University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929","observed_orcids":["https://orcid.org/0000-0003-1382-9929"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","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":0.2504,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.52801988,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2425","last_page":"2428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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":0.000699999975040555,"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/T10403","display_name":"Phonetics and Phonology Research","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/whispered-speech","display_name":"whispered speech","score":0.8740000128746033},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.984000027179718},{"id":"https://openalex.org/keywords/vocal-effort","display_name":"vocal effort","score":0.6299999952316284},{"id":"https://openalex.org/keywords/universal-background-model","display_name":"universal background model","score":0.7379999756813049},{"id":"https://openalex.org/keywords/vector-taylor-series","display_name":"vector Taylor series","score":0.8019999861717224},{"id":"https://openalex.org/keywords/text-independent-speaker-recognition","display_name":"text-independent speaker recognition","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8473103046417236},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7445375323295593},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6842386722564697},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6428742408752441},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5253840684890747},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5100739598274231},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5014784336090088},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.4300849437713623},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3624216318130493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3035259246826172},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07974165678024292},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-631","doi":"https://doi.org/10.21437/interspeech.2011-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-631","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"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":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W5014987","https://openalex.org/W32775615","https://openalex.org/W40959531","https://openalex.org/W41355022","https://openalex.org/W2022047569","https://openalex.org/W2037740282","https://openalex.org/W2097590279","https://openalex.org/W2126597753","https://openalex.org/W2151046079","https://openalex.org/W2161010732","https://openalex.org/W2296084331"],"related_works":["https://openalex.org/W2039331999","https://openalex.org/W2117045222","https://openalex.org/W2106790438","https://openalex.org/W2088067539","https://openalex.org/W2443249738","https://openalex.org/W2008497289","https://openalex.org/W54514134","https://openalex.org/W2151046079","https://openalex.org/W1986142770","https://openalex.org/W2896301926"],"abstract_inverted_index":{"A":[0],"number":[1],"of":[2,49,143,154,161],"research":[3],"studies":[4],"in":[5,23,32,71],"speaker":[6,50,81,84,132,173],"recognition":[7],"have":[8],"recently":[9],"focused":[10],"on":[11],"robustness":[12],"due":[13],"to":[14,37,77,171],"microphone":[15],"and":[16,109,178],"channel":[17],"mismatch(e.g.,":[18],"NIST":[19],"SRE).":[20],"However,":[21],"changes":[22],"vocal":[24],"effort,":[25],"especially":[26],"whispered":[27,62,87,111,179,185],"speech,":[28,186],"present":[29],"significant":[30],"challenges":[31],"maintaining":[33],"system":[34],"performance.":[35],"Due":[36],"the":[38,44,72,90,136,146,158,162],"mismatch":[39],"spectral":[40],"structure":[41],"resulting":[42],"from":[43],"different":[45],"production":[46],"mechanisms,":[47],"performance":[48,175],"identification":[51,188],"systems":[52],"trained":[53],"with":[54,61,86,114,157],"neutral":[55,107,177],"speech":[56,180,187],"degrades":[57],"significantly":[58],"when":[59],"tested":[60],"speech.":[63,88],"This":[64,165],"study":[65],"considers":[66],"a":[67,78,93,151,168],"feature":[68],"transformation":[69],"method":[70],"training":[73],"phase":[74],"that":[75],"leads":[76],"more":[79],"robust":[80],"model":[82,127],"for":[83,176],"ID":[85,133,174],"In":[89],"proposed":[91,147],"system,":[92],"Speech":[94],"Mode":[95],"Independent":[96],"(SMI)":[97],"Universal":[98],"Background":[99],"Model":[100],"(UBM)":[101],"is":[102],"built":[103],"using":[104,135,145],"collected":[105],"real":[106],"features":[108,112],"pseudo":[110],"generated":[113],"Vector":[115],"Taylor":[116],"Series":[117],"(VTS),":[118],"or":[119],"via":[120],"Constrained":[121],"Maximum":[122],"Likelihood":[123],"Linear":[124],"Regression":[125],"(CMLLR)":[126],"adaptation.":[128],"Text-independent":[129],"closed":[130],"set":[131],"results":[134],"UT-VocalEffort":[137],"II":[138],"corpus":[139],"show":[140],"an":[141],"accuracy":[142,160],"88.87%":[144],"method,":[148],"which":[149],"represents":[150],"relative":[152],"improvement":[153],"46.26%":[155],"compared":[156],"79.29%":[159],"baseline":[163],"system.":[164],"result":[166],"confirms":[167],"viable":[169],"approach":[170],"improving":[172],"mismatched":[181],"conditions.":[182],"Index":[183],"Terms:":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}