{"id":"https://openalex.org/W2008786334","doi":"https://doi.org/10.1109/icassp.2002.5743736","title":"Acoustic analysis and recognition of whispered speech","display_name":"Acoustic analysis and recognition of whispered speech","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2008786334","doi":"https://doi.org/10.1109/icassp.2002.5743736","mag":"2008786334"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743736","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"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/A5109237505","display_name":"Taisuke Itoh","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Taisuke Itoh","raw_affiliation_strings":["Center for Integrated Acoustic Information Research, University of Nagoya, Nagoya, Japan","Center for Integrated Acoustic Information Research, Nagoya University, 464-8603 Japan"],"affiliations":[{"raw_affiliation_string":"Center for Integrated Acoustic Information Research, University of Nagoya, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Center for Integrated Acoustic Information Research, Nagoya University, 464-8603 Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101685454","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0003-0452-9844"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuya Takeda","raw_affiliation_strings":["Center for Integrated Acoustic Information Research, University of Nagoya, Nagoya, Japan","Center for Integrated Acoustic Information Research, Nagoya University, 464-8603 Japan"],"affiliations":[{"raw_affiliation_string":"Center for Integrated Acoustic Information Research, University of Nagoya, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Center for Integrated Acoustic Information Research, Nagoya University, 464-8603 Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021756192","display_name":"Fumitada Itakura","orcid":null},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumitada Itakura","raw_affiliation_strings":["Center for Integrated Acoustic Information Research, University of Nagoya, Nagoya, Japan","Center for Integrated Acoustic Information Research, Nagoya University, 464-8603 Japan"],"affiliations":[{"raw_affiliation_string":"Center for Integrated Acoustic Information Research, University of Nagoya, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Center for Integrated Acoustic Information Research, Nagoya University, 464-8603 Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109237505"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":0.3241,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.4295246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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":0.9950000047683716,"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":0.9628999829292297,"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/T11448","display_name":"Face recognition and analysis","score":0.9585999846458435,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.82748943567276},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.7366636991500854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.688240110874176},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6299055814743042},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.6107511520385742},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.541199266910553},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5149577260017395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.282619446516037},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.22155609726905823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11872461438179016},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.10156148672103882}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.82748943567276},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.7366636991500854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.688240110874176},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6299055814743042},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.6107511520385742},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.541199266910553},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5149577260017395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.282619446516037},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.22155609726905823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11872461438179016},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.10156148672103882},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743736","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1545923985","https://openalex.org/W1967722854","https://openalex.org/W2006046472","https://openalex.org/W2061881822","https://openalex.org/W2087335130","https://openalex.org/W4234890202","https://openalex.org/W6632612480"],"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/W2018086531","https://openalex.org/W2005300405","https://openalex.org/W1980297060","https://openalex.org/W2019183077"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,50,68,72,79,84,87,98,106,132,138],"acoustic":[4],"properties":[5],"and":[6,24,44,60,82],"recognition":[7,117],"of":[8,19,30,71,86,97,113],"whispered":[9,14,20,43,73,107,139],"speech":[10,15,23,74,81,108,134,140],"is":[11,55,75,93,129],"discussed,":[12],"A":[13],"database":[16,109],"that":[17,48,96],"consists":[18],"speech,":[21,100],"nonnal":[22,45,80,99,133],"their":[25],"corresponding":[26],"facial":[27],"video":[28],"images":[29],"more":[31],"than":[32,78,95],"6,000":[33],"sentences":[34],"from":[35],"100":[36],"speakers":[37],"was":[38],"prepared.":[39],"The":[40],"comparison":[41],"between":[42,53],"utterances":[46],"show":[47],"1)":[49],"cepstrum":[51],"distance":[52],"them":[54],"4":[56],"dB":[57,62],"for":[58,63],"voiced":[59],"2":[61],"unvoiced":[64],"phonemes,":[65],"respectively,":[66],"2)":[67],"spectral":[69],"tilt":[70],"less":[76],"sloped":[77],"3)":[83],"frequency":[85],"lower":[88],"formants":[89],"(below":[90],"1.5":[91],"kHz)":[92],"higher":[94],"Acoustic":[101],"models":[102],"(HMM)":[103],"trained":[104],"by":[105],"attain":[110,141],"an":[111],"accuracy":[112,120],"68%":[114],"in":[115],"word":[116,145],"experiments.":[118],"This":[119],"can":[121],"be":[122],"improved":[123],"to":[124],"78%":[125],"when":[126],"MLLR":[127],"adaptation":[128],"applied,":[130],"while":[131],"HMM":[135],"adapted":[136],"with":[137],"only":[142],"62":[143],"%":[144],"accuracy.":[146]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}