{"id":"https://openalex.org/W2106790438","doi":"https://doi.org/10.1109/tasl.2010.2091631","title":"Speaker Identification Within Whispered Speech Audio Streams","display_name":"Speaker Identification Within Whispered Speech Audio Streams","publication_year":2011,"publication_date":"2011-05-13","ids":{"openalex":"https://openalex.org/W2106790438","doi":"https://doi.org/10.1109/tasl.2010.2091631","mag":"2106790438"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2091631","doi":"https://doi.org/10.1109/tasl.2010.2091631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2091631","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"volume":null,"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/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":["Center of Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","Dept. of Electr. Eng., Univ. of Texas at Dallas, Richardson, TX, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Texas at Dallas, Richardson, TX, USA#TAB#","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":[{"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":"John H. L. Hansen","raw_affiliation_strings":["Center of Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","Dept. of Electr. Eng., Univ. of Texas at Dallas, Richardson, TX, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Robust Speech Systems (CRSS), Erik Jonsson School of Engineering and Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Univ. of Texas at Dallas, Richardson, TX, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":5.0094,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.95617307,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"19","issue":"5","first_page":"1408","last_page":"1421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9961000084877014,"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":0.9961000084877014,"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":0.002199999988079071,"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":0.00039999998989515007,"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":0.8579999804496765},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.9729999899864197},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"feature extraction","score":0.6299999952316284},{"id":"https://openalex.org/keywords/speech-privacy","display_name":"speech privacy","score":0.37700000405311584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8268747329711914},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8109077215194702},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7396166324615479},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6488701701164246},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.5471261739730835},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5128984451293945},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.49459120631217957},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4565749168395996},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.436087965965271},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.413351833820343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2789643108844757},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2091631","doi":"https://doi.org/10.1109/tasl.2010.2091631","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2091631","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W5014987","https://openalex.org/W32775615","https://openalex.org/W40959531","https://openalex.org/W41355022","https://openalex.org/W144370208","https://openalex.org/W177407077","https://openalex.org/W341711312","https://openalex.org/W1967722854","https://openalex.org/W1991590998","https://openalex.org/W2006046472","https://openalex.org/W2011440797","https://openalex.org/W2022047569","https://openalex.org/W2023850592","https://openalex.org/W2038875793","https://openalex.org/W2059857061","https://openalex.org/W2087335130","https://openalex.org/W2090861223","https://openalex.org/W2096503735","https://openalex.org/W2117045222","https://openalex.org/W2119648481","https://openalex.org/W2123838014","https://openalex.org/W2143905102","https://openalex.org/W2145404233","https://openalex.org/W2151046079","https://openalex.org/W4234890202","https://openalex.org/W4300906944"],"related_works":["https://openalex.org/W2008497289","https://openalex.org/W2088067539","https://openalex.org/W54514134","https://openalex.org/W2293955729","https://openalex.org/W2117045222","https://openalex.org/W2443249738","https://openalex.org/W2039331999","https://openalex.org/W1986142770","https://openalex.org/W2151046079","https://openalex.org/W2911510444"],"abstract_inverted_index":{"Whisper":[0],"is":[1,57,80,83,92,102,115,145,170,203],"an":[2,72,133,207],"alternative":[3,134],"speech":[4,26,43],"production":[5],"mode":[6],"used":[7],"by":[8],"subjects":[9],"in":[10,27,111,158,172,206],"natural":[11],"conversation":[12],"to":[13,18,126,160,174,188],"protect":[14],"the":[15,19,34,105,180,190,216],"privacy.":[16],"Due":[17],"profound":[20],"differences":[21],"between":[22],"whisper":[23,87,155,232,243],"and":[24,30,141,152,235],"neutral":[25,42,64],"both":[28],"excitation":[29],"vocal":[31],"tract":[32],"function,":[33],"performance":[35,60,90,106,129,222],"of":[36,62,98,150,192,210,223,229,240],"speaker":[37,54,67,88,109,201,213,220],"identification":[38,110,202],"systems":[39],"trained":[40,65],"with":[41,185,215],"degrades":[44],"significantly.":[45],"In":[46,124],"this":[47],"paper,":[48],"a":[49,63,96,196,227,238],"seamless":[50,199],"neutral/whisper":[51,112,200],"mismatched":[52,113],"closed-set":[53,66],"recognition":[55],"system":[56,69,128,181,197],"developed.":[58],"First,":[59],"characteristics":[61],"ID":[68,221],"based":[70,138],"on":[71,117,139,176],"Mel-frequency":[73],"cepstral":[74],"coefficient-Gaussian":[75],"mixture":[76],"model":[77],"(MFCC-GMM)":[78],"framework":[79],"considered.":[81],"It":[82],"observed":[84],"that":[85,104],"for":[86,94,108,130,198,212,226],"recognition,":[89,214],"degradation":[91],"concentrated":[93],"only":[95],"subset":[97],"speakers.":[99],"Next,":[100],"it":[101],"shown":[103],"loss":[107],"conditions":[114],"focused":[116],"phonemes":[118],"other":[119],"than":[120],"low-energy":[121],"unvoiced":[122,131],"consonants.":[123],"order":[125,159,173],"increase":[127],"consonants,":[132],"feature":[135,168],"extraction":[136],"algorithm":[137],"linear":[140],"exponential":[142],"frequency":[143],"scales":[144],"applied.":[146],"The":[147],"acoustic":[148],"properties":[149],"misrecognized":[151],"correctly":[153],"recognized":[154],"are":[156],"analyzed":[157],"develop":[161],"more":[162],"effective":[163],"processing":[164],"schemes.":[165],"A":[166],"two-dimensional":[167],"space":[169],"proposed":[171],"predict":[175],"which":[177],"whispered":[178,193],"utterances":[179],"will":[182],"perform":[183],"poorly,":[184],"evaluations":[186],"conducted":[187],"measure":[189],"quality":[191],"speech.":[194],"Finally,":[195],"proposed,":[204],"resulting":[205],"absolute":[208],"improvement":[209],"8.85%-10.30%":[211],"best":[217],"closed":[218],"set":[219],"88.35%":[224],"obtained":[225],"total":[228,239],"961":[230],"read":[231],"test":[233,244],"utterances,":[234],"83.84%":[236],"using":[237],"495":[241],"spontaneous":[242],"utterances.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-06-24T00:00:00"}