{"id":"https://openalex.org/W100037950","doi":"https://doi.org/10.21437/eurospeech.2003-200","title":"Estimation of resonant characteristics based on AR-HMM modeling and spectral envelope conversion of vowel sounds","display_name":"Estimation of resonant characteristics based on AR-HMM modeling and spectral envelope conversion of vowel sounds","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W100037950","doi":"https://doi.org/10.21437/eurospeech.2003-200","mag":"100037950"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-200","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},"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/A5035313377","display_name":"Nobuyuki Nishizawa","orcid":"https://orcid.org/0009-0007-6242-5695"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuyuki Nishizawa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"885","last_page":"888"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9993000030517578,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8272697329521179},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6999470591545105},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6711046099662781},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6683767437934875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6249245405197144},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5974768996238708},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.5767465829849243},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.5485972166061401},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.5155158042907715},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.48626959323883057},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.47903934121131897},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.4529778063297272},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2026449739933014},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.13949650526046753},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1272295117378235}],"concepts":[{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8272697329521179},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6999470591545105},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6711046099662781},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6683767437934875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6249245405197144},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5974768996238708},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.5767465829849243},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.5485972166061401},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.5155158042907715},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.48626959323883057},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.47903934121131897},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.4529778063297272},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2026449739933014},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.13949650526046753},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1272295117378235},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-200","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W62884208","https://openalex.org/W140137236","https://openalex.org/W2164764235","https://openalex.org/W2169721396","https://openalex.org/W2428180336","https://openalex.org/W2742954640"],"related_works":["https://openalex.org/W2006355155","https://openalex.org/W2142764841","https://openalex.org/W1977809180","https://openalex.org/W2130727403","https://openalex.org/W2121231314","https://openalex.org/W4230284560","https://openalex.org/W1984149964","https://openalex.org/W2979985946","https://openalex.org/W2029618598","https://openalex.org/W2106696525"],"abstract_inverted_index":{"A":[0],"new":[1],"method":[2,16],"was":[3,47,97],"developed":[4],"for":[5],"accurately":[6],"separating":[7],"source":[8],"and":[9,90],"articulation":[10],"filter":[11],"characteristics":[12],"of":[13,43],"speech.":[14],"This":[15],"is":[17,27,70],"based":[18],"on":[19,80,107],"the":[20,24,30,51,57,67,73,77,81,108],"AR-HMM":[21],"modeling,":[22],"where":[23,66],"residual":[25,68],"waveform":[26,69,92],"expressed":[28],"as":[29,72],"output":[31],"sequence":[32],"from":[33,87,93],"an":[34,38],"HMM.":[35],"To":[36],"realize":[37],"accurate":[39],"analysis,":[40,58],"a":[41,62,88,100,104],"scheme":[42],"dividing":[44],"HMM":[45],"state":[46],"newly":[48],"introduced.":[49],"Using":[50],"AR-filter":[52,86],"parameter":[53],"values":[54],"obtained":[55],"through":[56],"we":[59],"can":[60],"construct":[61],"vocoder-type":[63],"formant":[64,115],"synthesizer,":[65],"used":[71],"excitation":[74,91],"source.":[75],"Through":[76],"listening":[78],"test":[79],"vowel":[82,89],"sounds":[83],"synthesized":[84],"using":[85],"another":[94],"vowel,":[95],"it":[96],"shown":[98],"that":[99],"\u201cflexible\u201d":[101],"synthesis":[102,116],"with":[103],"high":[105],"controllability":[106],"acoustic":[109],"parameters":[110],"were":[111],"possible":[112],"by":[113],"our":[114],"configuration.":[117]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}