{"id":"https://openalex.org/W2088067539","doi":"https://doi.org/10.1109/icassp.2010.5495059","title":"Acoustic analysis for speaker identification of whispered speech","display_name":"Acoustic analysis for speaker identification of whispered speech","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2088067539","doi":"https://doi.org/10.1109/icassp.2010.5495059","mag":"2088067539"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495059","doi":"https://doi.org/10.1109/icassp.2010.5495059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495059","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","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":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","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":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","Center for Robust Speech Systems(CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75083, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems(CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75083, USA","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 for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","Center for Robust Speech Systems(CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75083, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems(CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75083, USA","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":1.5515,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83878276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"84","issue":null,"first_page":"5046","last_page":"5049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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":0.9951000213623047,"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":0.002899999963119626,"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":0.0007999999797903001,"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":0.972000002861023},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"speaker identification","score":0.9620000123977661},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.5699999928474426},{"id":"https://openalex.org/keywords/acoustic-analysis","display_name":"acoustic analysis","score":0.6620000004768372},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"vocal tract","score":0.46000000834465027}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8254847526550293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619566917419434},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6232221126556396},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5924591422080994},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5544266700744629},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5255888104438782},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47512274980545044},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.47378942370414734},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.4215801954269409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22442874312400818},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.19638830423355103},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07664906978607178},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/icassp.2010.5495059","doi":"https://doi.org/10.1109/icassp.2010.5495059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495059","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","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":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-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":10,"referenced_works":["https://openalex.org/W5014987","https://openalex.org/W32775615","https://openalex.org/W40959531","https://openalex.org/W41355022","https://openalex.org/W1493163583","https://openalex.org/W2022047569","https://openalex.org/W2117045222","https://openalex.org/W2119648481","https://openalex.org/W2151046079","https://openalex.org/W6629341784"],"related_works":["https://openalex.org/W2106790438","https://openalex.org/W54514134","https://openalex.org/W2039331999","https://openalex.org/W2293955729","https://openalex.org/W2117045222","https://openalex.org/W2008497289","https://openalex.org/W2443249738","https://openalex.org/W2151046079","https://openalex.org/W1986142770","https://openalex.org/W2911510444"],"abstract_inverted_index":{"Whisper":[0],"is":[1,11,68,71,80,92,110],"an":[2,89],"alternative":[3],"speech":[4,35,52,118],"production":[5],"mode":[6],"from":[7],"neutral":[8,34,51,59,172],"speech,":[9],"which":[10],"used":[12],"by":[13],"talkers":[14],"intentionally":[15],"in":[16,36,94,133],"natural":[17],"conversational":[18],"scenarios":[19],"to":[20,29,96,112,154,164],"protect":[21],"personal":[22],"privacy":[23],"and":[24,33,39],"avoid":[25],"being":[26],"overheard.":[27],"Due":[28],"differences":[30],"between":[31],"whispered":[32,117,135],"vocal":[37,40],"excitation":[38],"tract":[41],"function,":[42],"the":[43,78,98,101,114,120,128,169],"performance":[44,170],"of":[45,86,116,122,130,171],"speaker":[46,62,76,123,139,145,173],"ID":[47,63,146,174],"systems":[48],"trained":[49,60],"with":[50,137],"degrades":[53],"significantly.":[54],"In":[55],"this":[56,131],"study,":[57],"a":[58,83,107,142],"closed-set":[61],"task":[64,121],"based":[65],"on":[66],"MFCC-GMM":[67],"considered.":[69],"It":[70],"observed":[72],"that":[73,167],"for":[74,82,103,119,141,156],"whisper":[75],"recognition,":[77],"degradation":[79,102],"concentrated":[81],"certain":[84],"number":[85],"speakers.":[87,105],"Next,":[88],"acoustic":[90],"analysis":[91],"conducted":[93],"order":[95],"determine":[97],"reason":[99],"affecting":[100],"those":[104,157],"Finally,":[106],"confidence":[108],"space":[109],"proposed":[111,149],"measure":[113],"quality":[115],"ID.":[124],"Experimental":[125],"evaluations":[126],"demonstrate":[127],"effectiveness":[129],"method":[132,150],"searching":[134],"utterances":[136,166],"poor":[138,158],"information":[140],"neutral/whisper":[143],"mismatch":[144],"system.":[147],"The":[148],"makes":[151],"it":[152],"possible":[153],"compensate":[155],"utterances,":[159],"meanwhile":[160],"avoiding":[161],"any":[162],"harm":[163],"other":[165],"remain":[168],"task.":[175]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}