{"id":"https://openalex.org/W311996270","doi":"https://doi.org/10.21437/interspeech.2004-209","title":"Estimation of the vocal tract spectrum from articulatory movements using phoneme-dependent neural networks","display_name":"Estimation of the vocal tract spectrum from articulatory movements using phoneme-dependent neural networks","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W311996270","doi":"https://doi.org/10.21437/interspeech.2004-209","mag":"311996270"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-209","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5069436479","display_name":"Takuya Tsuji","orcid":"https://orcid.org/0000-0001-6366-2923"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takuya Tsuji","raw_affiliation_strings":["Kyushu University"],"affiliations":[{"raw_affiliation_string":"Kyushu University","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030837080","display_name":"Tokihiko Kaburagi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tokihiko Kaburagi","raw_affiliation_strings":["Communicative Acoustic Systems"],"affiliations":[{"raw_affiliation_string":"Communicative Acoustic Systems","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073627786","display_name":"Kohei Wakamiya","orcid":"https://orcid.org/0000-0001-9254-5910"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Wakamiya","raw_affiliation_strings":["Kyushu University"],"affiliations":[{"raw_affiliation_string":"Kyushu University","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089058185","display_name":"Jiji Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiji Kim","raw_affiliation_strings":["Kyushu University"],"affiliations":[{"raw_affiliation_string":"Kyushu University","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069436479"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03271693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"517","last_page":"520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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":0.9923999905586243,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/articulator","display_name":"Articulator","score":0.9771842360496521},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.9110297560691833},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.780877947807312},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6228718161582947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6186672449111938},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.615211546421051},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5880429148674011},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5809005498886108},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5780823230743408},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.4994192123413086},{"id":"https://openalex.org/keywords/spectrum","display_name":"Spectrum (functional analysis)","score":0.4430760443210602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38982710242271423},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.12554827332496643},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.1222984790802002},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07165062427520752},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05915534496307373}],"concepts":[{"id":"https://openalex.org/C2778415344","wikidata":"https://www.wikidata.org/wiki/Q443216","display_name":"Articulator","level":2,"score":0.9771842360496521},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.9110297560691833},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.780877947807312},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6228718161582947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6186672449111938},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.615211546421051},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5880429148674011},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5809005498886108},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5780823230743408},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.4994192123413086},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.4430760443210602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38982710242271423},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.12554827332496643},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.1222984790802002},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07165062427520752},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05915534496307373},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C29694066","wikidata":"https://www.wikidata.org/wiki/Q118301","display_name":"Orthodontics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2004-209","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1536990986","https://openalex.org/W1977591085","https://openalex.org/W2529103879"],"related_works":["https://openalex.org/W2046073792","https://openalex.org/W4254341835","https://openalex.org/W1748856376","https://openalex.org/W2086580720","https://openalex.org/W1909584822","https://openalex.org/W2001425423","https://openalex.org/W2061217898","https://openalex.org/W2025848302","https://openalex.org/W2894697037","https://openalex.org/W1975454382"],"abstract_inverted_index":{"This":[0,62],"paper":[1],"presents":[2],"an":[3,125],"estimation":[4,126],"method":[5,15,41],"of":[6,21,59,76,86,109],"the":[7,19,29,39,50,57,67,70,77,87,94,117,129],"vocal":[8,51],"tract":[9,52],"spectrum":[10,53],"from":[11],"articulatory":[12],"movements.":[13],"The":[14],"is":[16,54,64,90],"based":[17,65],"on":[18,66],"interpolation":[20,58,63,96],"spectra":[22],"obtained":[23],"by":[24,56,105],"phonemedependent":[25],"neural":[26,88],"networks.":[27],"Given":[28],"phonemic":[30],"context":[31],"and":[32,74,79,100,112,119],"articulation":[33],"timing":[34],"corresponding":[35],"to":[36,46],"each":[37],"phoneme,":[38],"proposed":[40,130],"first":[42],"transforms":[43],"articulator":[44,72,110],"positions":[45,111],"phoneme-dependent":[47],"spectra.":[48,61],"Then":[49],"estimated":[55],"transformed":[60],"distance":[68],"among":[69],"input":[71],"position":[73],"that":[75],"preceding":[78],"succeeding":[80],"phonemes.":[81],"Also,":[82],"a":[83,106],"training":[84,118],"procedure":[85],"networks":[89],"presented":[91],"while":[92],"taking":[93],"spectral":[95],"into":[97],"account.":[98],"Articulatory":[99],"acoustic":[101],"data":[102],"pairs":[103],"collected":[104],"simultaneous":[107],"recording":[108],"speech":[113],"were":[114],"used":[115],"as":[116],"test":[120],"data.":[121],"Finally,":[122],"we":[123],"showed":[124],"result":[127],"using":[128],"method.":[131]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
