{"id":"https://openalex.org/W2117045222","doi":"https://doi.org/10.1109/icassp.2009.4960643","title":"Speaker identification with whispered speech based on modified LFCC parameters and feature mapping","display_name":"Speaker identification with whispered speech based on modified LFCC parameters and feature mapping","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2117045222","doi":"https://doi.org/10.1109/icassp.2009.4960643","mag":"2117045222"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"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"},"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":true,"raw_author_name":"Xing Fan","raw_affiliation_strings":["Center of 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"],"affiliations":[{"raw_affiliation_string":"Center of 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"},"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 & 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"],"affiliations":[{"raw_affiliation_string":"Center of 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":2,"corresponding_author_ids":["https://openalex.org/A5018483554"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":4.3618,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.94514846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4553","last_page":"4556"},"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":0.9994000196456909,"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":0.9775999784469604,"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/speech-recognition","display_name":"Speech recognition","score":0.8257448673248291},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7833267450332642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7342397570610046},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6491745114326477},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5660157203674316},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5525906085968018},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5514605045318604},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5149834752082825},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5097972750663757},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.44812577962875366},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4384881556034088},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4066355228424072},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40359532833099365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3497059941291809},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.0845898687839508}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8257448673248291},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7833267450332642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342397570610046},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6491745114326477},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5660157203674316},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5525906085968018},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5514605045318604},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5149834752082825},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5097972750663757},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.44812577962875366},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4384881556034088},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4066355228424072},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40359532833099365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3497059941291809},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0845898687839508},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960643","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960643","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W5014987","https://openalex.org/W40959531","https://openalex.org/W177407077","https://openalex.org/W2022047569","https://openalex.org/W2093985521","https://openalex.org/W2101272095","https://openalex.org/W2105393821","https://openalex.org/W2151046079"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2373675101","https://openalex.org/W2048014685","https://openalex.org/W4385672897","https://openalex.org/W2370972896","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082"],"abstract_inverted_index":{"Much":[0],"research":[1],"recently":[2],"in":[3,19,28,40,45,125,161],"speaker":[4,55,83,126,138,153,180],"recognition":[5,84],"has":[6],"been":[7],"devoted":[8],"to":[9,12,33,81,178],"robustness":[10],"due":[11],"microphone":[13],"and":[14,47,146,185],"channel":[15],"effects.":[16],"However,":[17],"changes":[18],"vocal":[20],"effort,":[21],"especially":[22],"whispered":[23,79,145,186],"speech,":[24],"present":[25],"significant":[26],"challenges":[27],"maintaining":[29],"system":[30],"performance.":[31],"Due":[32],"the":[34,42,113],"absence":[35],"of":[36,54,144],"any":[37],"periodic":[38],"excitation":[39],"whisper,":[41],"spectral":[43,105],"structure":[44],"whisper":[46],"neutral":[48,87,147,184],"speech":[49,80,109,187],"will":[50],"differ.":[51],"Therefore,":[52],"performance":[53,182],"ID":[56,154,181],"systems,":[57],"trained":[58,88],"mainly":[59],"with":[60,68,95,165],"high":[61],"energy":[62],"voiced":[63],"phonemes,":[64],"degrades":[65],"when":[66,163],"tested":[67],"whisper.":[69],"This":[70,172],"study":[71],"considers":[72],"a":[73,86,116,133,166,175],"front-end":[74],"feature":[75,93,117,169],"compensation":[76],"method":[77],"for":[78,112,121],"improve":[82],"using":[85],"system.":[89,171],"First,":[90],"an":[91,157],"alternative":[92],"vector":[94],"linear":[96],"frequency":[97],"cepstral":[98],"coefficients":[99],"(LFCC)":[100],"is":[101,119,130],"introduced":[102],"based":[103,170],"on":[104,132],"analysis":[106],"from":[107],"both":[108],"modes.":[110],"Next,":[111],"first":[114],"time":[115],"mapping":[118,129],"proposed":[120],"reducing":[122],"whisper/neutral":[123],"mismatch":[124],"ID.":[127],"Feature":[128],"applied":[131],"frame-by-frame":[134],"basis":[135],"between":[136,183],"two":[137],"independent":[139,150],"GMMs":[140],"(Gaussian":[141],"Mixture":[142],"Models)":[143],"speech.":[148],"Text":[149],"closed":[151],"set":[152],"results":[155],"show":[156],"absolute":[158],"20%":[159],"improvement":[160],"accuracy":[162],"compared":[164],"traditional":[167],"MFCC":[168],"result":[173],"confirms":[174],"viable":[176],"approach":[177],"improving":[179],"conditions.":[188]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":7},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}