{"id":"https://openalex.org/W2296084331","doi":"https://doi.org/10.21437/interspeech.2011-77","title":"Acoustic analysis of whispered speech for phoneme and speaker dependency","display_name":"Acoustic analysis of whispered speech for phoneme and speaker dependency","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2296084331","doi":"https://doi.org/10.21437/interspeech.2011-77","mag":"2296084331"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-77","doi":"https://doi.org/10.21437/interspeech.2011-77","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-77","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":"middle","author":{"id":"https://openalex.org/A5068934511","display_name":"Keith W. Godin","orcid":null,"observed_orcids":[]},"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":"Keith W. Godin","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":0.5007,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.64017143,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8476999998092651,"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":0.8476999998092651,"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":0.08089999854564667,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.06340000033378601,"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/whispered-speech","display_name":"whispered speech","score":1.0},{"id":"https://openalex.org/keywords/neutral-speech","display_name":"neutral speech","score":0.7149999737739563},{"id":"https://openalex.org/keywords/formant-shift","display_name":"formant shift","score":0.8109999895095825},{"id":"https://openalex.org/keywords/spectral-slope","display_name":"spectral slope","score":0.9129999876022339},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"speaker recognition","score":0.718999981880188},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"speech recognition","score":0.3659999966621399}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.786182165145874},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7681045532226562},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.7368910908699036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5902566313743591},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19225099682807922},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-77","doi":"https://doi.org/10.21437/interspeech.2011-77","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-77","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":7,"referenced_works":["https://openalex.org/W177407077","https://openalex.org/W2022047569","https://openalex.org/W2088067539","https://openalex.org/W2140595311","https://openalex.org/W2151046079","https://openalex.org/W2155445312","https://openalex.org/W3127686677"],"related_works":["https://openalex.org/W2294831733","https://openalex.org/W7008777630","https://openalex.org/W2039331999","https://openalex.org/W2055589033","https://openalex.org/W2022047569","https://openalex.org/W2008786334","https://openalex.org/W4234890202","https://openalex.org/W2293955729","https://openalex.org/W4383605208","https://openalex.org/W2021512166"],"abstract_inverted_index":{"Whisper":[0],"is":[1],"used":[2],"by":[3,58],"speakers":[4,55],"in":[5,16,43],"certain":[6],"circumstances":[7],"to":[8,13,66,109],"protect":[9],"personal":[10],"information.":[11],"Due":[12],"the":[14,29,49,70,80,99,105],"differences":[15,27,53],"production":[17],"mechanisms":[18],"between":[19,28],"neutral":[20,33,73,108],"and":[21,34,41,56,78,101,112],"whispered":[22,35,76,133],"speech,":[23,36,77,111,134],"there":[24],"are":[25],"considerable":[26],"spectral":[30,44],"structure":[31],"of":[32,51,69,72,82,104,107],"such":[37],"as":[38],"formant":[39],"shifts":[40,42,106],"slope.":[45],"This":[46],"study":[47,95],"analyzes":[48],"dependency":[50,103],"these":[52],"on":[54,98],"phonemes":[57],"applying":[59],"a":[60,67],"Vector":[61],"Taylor":[62],"Series":[63],"(VTS)":[64],"approximation":[65],"model":[68,84,117],"transformation":[71],"speech":[74,135],"into":[75],"estimating":[79],"parameters":[81],"this":[83,94],"using":[85],"an":[86],"Expectation":[87],"Maximization":[88],"(EM)":[89],"algorithm.":[90],"The":[91],"results":[92],"from":[93],"shed":[96],"light":[97],"speaker":[100,129],"phoneme":[102],"whisper":[110,123],"suggest":[113],"that":[114],"similarly":[115],"derived":[116],"adaptation":[118],"or":[119],"compensation":[120],"schemes":[121],"for":[122],"speech/speaker":[124],"recognition":[125],"will":[126],"be":[127],"highly":[128],"dependent.":[130],"Index":[131],"Terms:":[132],"analysis":[136]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}
