{"id":"https://openalex.org/W2055589033","doi":"https://doi.org/10.1109/icassp.2014.6854059","title":"UT-Vocal Effort II: Analysis and constrained-lexicon recognition of whispered speech","display_name":"UT-Vocal Effort II: Analysis and constrained-lexicon recognition of whispered speech","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2055589033","doi":"https://doi.org/10.1109/icassp.2014.6854059","mag":"2055589033"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854059","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":"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/A5040866561","display_name":"Shabnam Ghaffarzadegan","orcid":null},"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":"Shabnam Ghaffarzadegan","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009895165","display_name":"Hynek Bo\u0159il","orcid":null},"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":"Hynek Boril","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, US","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, US","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085723847","display_name":"John Hansen","orcid":"https://orcid.org/0000-0003-4989-8117"},"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), University of Texas at Dallas, Richardson, Texas, U.S.A","Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, Texas, U.S.A","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), University of Texas at Dallas, Richardson, TX, USA#TAB#","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040866561"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":4.1217,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94725438,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2544","last_page":"2548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9943000078201294,"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/speech-recognition","display_name":"Speech recognition","score":0.8266136646270752},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7414444088935852},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5414109826087952},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5233144760131836},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.510606586933136},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.47074729204177856},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46802622079849243},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.46104711294174194},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.42530032992362976},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.4126092195510864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3003029525279999},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.28792107105255127},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.26789289712905884},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.07417604327201843}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8266136646270752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414444088935852},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5414109826087952},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5233144760131836},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.510606586933136},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.47074729204177856},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46802622079849243},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.46104711294174194},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.42530032992362976},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.4126092195510864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3003029525279999},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28792107105255127},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.26789289712905884},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.07417604327201843},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2014.6854059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854059","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"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.642.7880","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.642.7880","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.utdallas.edu/~hynek/pdfs/ICASSP14_ShabnamHykJH.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W41355022","https://openalex.org/W96541173","https://openalex.org/W1574295218","https://openalex.org/W1979208971","https://openalex.org/W1981298914","https://openalex.org/W2006046472","https://openalex.org/W2022047569","https://openalex.org/W2033321754","https://openalex.org/W2039331999","https://openalex.org/W2045956438","https://openalex.org/W2047497400","https://openalex.org/W2072328708","https://openalex.org/W2080534788","https://openalex.org/W2088067539","https://openalex.org/W2090861223","https://openalex.org/W2096503735","https://openalex.org/W2100103540","https://openalex.org/W2106790438","https://openalex.org/W2117486215","https://openalex.org/W2125828495","https://openalex.org/W2142691710","https://openalex.org/W2146618065","https://openalex.org/W2148154194","https://openalex.org/W2161964681","https://openalex.org/W2303272654","https://openalex.org/W6634460432","https://openalex.org/W6645471240","https://openalex.org/W6678977797","https://openalex.org/W6683708376"],"related_works":["https://openalex.org/W2368661496","https://openalex.org/W2380156283","https://openalex.org/W2085241361","https://openalex.org/W2018337942","https://openalex.org/W2137133401","https://openalex.org/W2394579548","https://openalex.org/W2546026986","https://openalex.org/W11089689","https://openalex.org/W2018086531","https://openalex.org/W2766680336"],"abstract_inverted_index":{"This":[0],"study":[1],"focuses":[2],"on":[3,117],"acoustic":[4,27,131],"variations":[5],"in":[6,34,40,48,61],"speech":[7,20,24,38,66,74],"introduced":[8],"by":[9],"whispering,":[10],"and":[11,36,54,58,64,86,102,120],"proposes":[12],"several":[13,76],"strategies":[14,77],"to":[15,73],"improve":[16],"robustness":[17],"of":[18,22,50],"automatic":[19],"recognition":[21],"whispered":[23,37],"with":[25,129],"neutral-trained":[26,96],"models.":[28,132],"In":[29,69],"the":[30,41,70,113],"analysis":[31],"part,":[32],"differences":[33],"neutral":[35,118],"captured":[39],"UT-Vocal":[42],"Effort":[43],"II":[44],"corpus":[45],"are":[46,92],"studied":[47],"terms":[49],"energy,":[51],"spectral":[52],"slope,":[53],"formant":[55],"center":[56],"frequency":[57],"bandwidth":[59],"distributions":[60],"silence,":[62],"voiced,":[63],"unvoiced":[65],"signal":[67],"segments.":[68],"part":[71],"dedicated":[72],"recognition,":[75],"involving":[78],"front-end":[79],"filter":[80,100],"bank":[81,101],"redistribution,":[82],"cepstral":[83],"dimensionality":[84],"reduction,":[85],"lexicon":[87],"expansion":[88],"for":[89],"alternative":[90],"pronunciations":[91],"proposed.":[93],"The":[94],"proposed":[95],"system":[97,115,128],"employing":[98],"redistributed":[99],"reduced":[103],"features":[104],"provides":[105],"a":[106,121,126],"7.7":[107],"%":[108,123],"absolute":[109],"WER":[110],"reduction":[111,124],"over":[112,125],"baseline":[114,127],"trained":[116],"speech,":[119],"1.3":[122],"whisper-adapted":[130]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}