{"id":"https://openalex.org/W1706950341","doi":"https://doi.org/10.21437/icslp.2002-514","title":"Separation of voiced source characteristics and vocal tract transfer function characteristics for speech sounds by iterative analysis based on AR-HMM model","display_name":"Separation of voiced source characteristics and vocal tract transfer function characteristics for speech sounds by iterative analysis based on AR-HMM model","publication_year":2002,"publication_date":"2002-09-16","ids":{"openalex":"https://openalex.org/W1706950341","doi":"https://doi.org/10.21437/icslp.2002-514","mag":"1706950341"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.2002-514","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","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":[{"id":"https://openalex.org/I4210102982","display_name":"Centre for Research in Engineering Surface Technology","ror":"https://ror.org/018q3fa22","country_code":"IE","type":"other","lineage":["https://openalex.org/I4210102982"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["IE","JP"],"is_corresponding":false,"raw_author_name":"Nobuyuki Nishizawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo / CREST","Graduate School of Engineering, University of Tokyo / CREST Graduate School of Frontier Sciences, University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo / CREST","institution_ids":["https://openalex.org/I4210102982","https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Engineering, University of Tokyo / CREST Graduate School of Frontier Sciences, University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108197272","display_name":"Keikichi Hirose","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102982","display_name":"Centre for Research in Engineering Surface Technology","ror":"https://ror.org/018q3fa22","country_code":"IE","type":"other","lineage":["https://openalex.org/I4210102982"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["IE","JP"],"is_corresponding":true,"raw_author_name":"Keikichi Hirose","raw_affiliation_strings":["Graduate School of Engineering, University of Tokyo / CREST Graduate School of Frontier Sciences, University of Tokyo","Graduate School of Information Science and Technology, University of Tokyo / CREST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, University of Tokyo / CREST Graduate School of Frontier Sciences, University of Tokyo","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo / CREST","institution_ids":["https://openalex.org/I4210102982","https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[{"id":"https://openalex.org/I4210102982","display_name":"Centre for Research in Engineering Surface Technology","ror":"https://ror.org/018q3fa22","country_code":"IE","type":"other","lineage":["https://openalex.org/I4210102982"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["IE","JP"],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo / CREST","Graduate School of Engineering, University of Tokyo / CREST Graduate School of Frontier Sciences, University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo / CREST","institution_ids":["https://openalex.org/I4210102982","https://openalex.org/I74801974"]},{"raw_affiliation_string":"Graduate School of Engineering, University of Tokyo / CREST Graduate School of Frontier Sciences, University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5108197272"],"corresponding_institution_ids":["https://openalex.org/I4210102982","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1721","last_page":"1724"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9873999953269958,"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/vocal-tract","display_name":"Vocal tract","score":0.8093864917755127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.781524121761322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6920591592788696},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6467489004135132},{"id":"https://openalex.org/keywords/transfer-function","display_name":"Transfer function","score":0.6408004760742188},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.6060609221458435},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41542840003967285},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.33897364139556885},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08362436294555664},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06856000423431396}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8093864917755127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.781524121761322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6920591592788696},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6467489004135132},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.6408004760742188},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.6060609221458435},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41542840003967285},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.33897364139556885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08362436294555664},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06856000423431396},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.2002-514","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.2002-514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"7th International Conference on Spoken Language Processing (ICSLP 2002)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.3170","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.3170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2002/ICSLP_p1721-1724_t2002-9.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W62884208","https://openalex.org/W140137236","https://openalex.org/W2049686551","https://openalex.org/W2164764235","https://openalex.org/W2169721396"],"related_works":["https://openalex.org/W2079194684","https://openalex.org/W2617269004","https://openalex.org/W35292311","https://openalex.org/W2803166627","https://openalex.org/W2046073792","https://openalex.org/W1748856376","https://openalex.org/W2097474189","https://openalex.org/W2400533375","https://openalex.org/W2470236000","https://openalex.org/W2097143083"],"abstract_inverted_index":{"A":[0],"new":[1],"method":[2,29,175],"was":[3],"developed":[4],"for":[5,62,107,151,157],"the":[6,43,94,115,158,168,173],"separation":[7,67],"of":[8,14,20,74,79,148,189,193],"source":[9,34,63,84,92,135,178],"and":[10,39,87,114,125,136,144,179],"transfer":[11,40,101,137,180],"function":[12,41,102,138,181],"characteristics":[13],"speech":[15,26,194,199],"sounds,":[16],"with":[17,119],"an":[18,37],"aim":[19],"utilizing":[21],"it":[22],"to":[23,50,197],"\u201cflexible":[24],"\u201d":[25],"synthesis.":[27,200],"The":[28,162],"is":[30,60,68],"based":[31,52],"on":[32,53],"representing":[33,133],"waveform":[35,85],"by":[36,42,121,167],"HMM,":[38],"AR":[44,80,96],"process":[45,73],"(AR-HMM":[46],"model).":[47],"As":[48],"compared":[49,118,156],"methods":[51],"ARX":[54],"model,":[55],"where":[56],"a":[57,65,72],"parametric":[58],"representation":[59],"assumed":[61],"waveform,":[64,93],"better":[66],"possible.":[69],"By":[70],"introducing":[71],"recursively":[75],"deleting":[76],"real":[77],"poles":[78],"filters,":[81],"which":[82],"represent":[83,100],"features,":[86],"including":[88],"them":[89],"into":[90],"HMM":[91],"resulting":[95],"filters":[97],"may":[98],"correctly":[99],"features.":[103],"Experiments":[104],"were":[105,117,155,165],"conducted":[106],"Japanese":[108],"vowel":[109,153],"sounds":[110],"in":[111],"continuous":[112],"speech,":[113],"results":[116],"those":[120],"conventional":[122],"LP":[123],"analysis":[124,128,160],"AR-HMM":[126],"model":[127],"without":[129],"recursive":[130],"process.":[131],"After":[132],"obtained":[134,166],"features":[139,182],"respectively":[140],"as":[141],"DFT":[142],"cepstrum":[143,149],"LPC":[145],"cepstrum,":[146],"variations":[147,164],"parameters":[150],"each":[152],"sound":[154],"three":[159],"methods.":[161],"smallest":[163],"proposed":[169,174],"method,":[170],"indicating":[171],"that":[172],"can":[176],"separate":[177],"well,":[183],"and,":[184],"thus,":[185],"has":[186],"potential":[187],"ability":[188],"generating":[190],"good":[191],"quality":[192],"when":[195],"applied":[196],"\u201cflexible\u201d":[198],"1.":[201]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}