{"id":"https://openalex.org/W2397271426","doi":"https://doi.org/10.21437/interspeech.2011-43","title":"Speech synthesis based on articulatory-movement HMMs with voice-source codebooks","display_name":"Speech synthesis based on articulatory-movement HMMs with voice-source codebooks","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2397271426","doi":"https://doi.org/10.21437/interspeech.2011-43","mag":"2397271426"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-43","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-43","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5109901270","display_name":"Tsuneo Nitta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsuneo Nitta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088029190","display_name":"Takayuki Onoda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takayuki Onoda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051342257","display_name":"Masashi Kimura","orcid":"https://orcid.org/0000-0001-5427-5593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masashi Kimura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112017946","display_name":"Yurie Iribe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yurie Iribe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108640197","display_name":"Kouichi Katsurada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kouichi Katsurada","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32404583,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1841","last_page":"1844"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9991000294685364,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9958000183105469,"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":0.82795250415802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686389088630676},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5809216499328613},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.49012598395347595},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4901145398616791},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45327556133270264},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4448259472846985},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4119175970554352},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4108414649963379}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.82795250415802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686389088630676},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5809216499328613},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.49012598395347595},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4901145398616791},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45327556133270264},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4448259472846985},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4119175970554352},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4108414649963379}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-43","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-43","pdf_url":null,"source":null,"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":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W94226176","https://openalex.org/W292592186","https://openalex.org/W1994477412","https://openalex.org/W2009674825","https://openalex.org/W2134383396","https://openalex.org/W2148228080","https://openalex.org/W2151626637","https://openalex.org/W2154920538","https://openalex.org/W3036802551"],"related_works":["https://openalex.org/W2020989338","https://openalex.org/W1823617068","https://openalex.org/W2147126679","https://openalex.org/W4300049944","https://openalex.org/W2115039802","https://openalex.org/W2740630172","https://openalex.org/W2496295964","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1984921740"],"abstract_inverted_index":{"Speech":[0],"synthesis":[1,20],"based":[2],"on":[3],"one-model":[4],"of":[5,85,97,112,129,134,152,166],"articulatory":[6,35],"movement":[7],"HMMs,":[8],"that":[9,142],"are":[10,30],"commonly":[11],"applied":[12,31,70],"to":[13,32,71],"both":[14,128],"speech":[15,19,56,113,151],"recognition":[16],"(SR)":[17],"and":[18,39,94,126,132],"(SS),":[21],"is":[22,58,69],"described.":[23],"In":[24,115],"an":[25,34,61],"SS":[26,89,145],"module,":[27],"speaker-invariant":[28],"HMMs":[29],"generate":[33],"feature":[36],"(AF)":[37],"sequence,":[38],"then,":[40],"after":[41],"converting":[42],"AFs":[43],"into":[44],"vocal":[45],"tract":[46],"parameters":[47],"by":[48],"using":[49],"a":[50,55,98,109,138],"multilayer":[51],"neural":[52],"network":[53],"(MLN),":[54],"signal":[57],"synthesized":[59,107,135],"through":[60],"LSP":[62],"digital":[63],"filter.":[64],"The":[65,87],"CELP":[66],"coding":[67],"technique":[68],"improve":[72],"voice-sources":[73],"when":[74,157],"generating":[75],"these":[76],"sources":[77],"from":[78],"embedded":[79],"codes":[80],"in":[81],"the":[82,95,101,116,143,153,158,163],"corresponding":[83],"state":[84],"HMMs.":[86],"proposed":[88,144],"module":[90,146],"separates":[91],"phonetic":[92],"information":[93],"individuality":[96,133],"speaker.":[99],"Therefore,":[100],"targeted":[102,154],"speaker\u2019s":[103],"voice":[104],"can":[105],"be":[106],"with":[108,162],"small":[110],"amount":[111],"data.":[114],"experiments,":[117],"we":[118,140],"carried":[119],"out":[120],"listening":[121],"tests":[122],"for":[123],"ten":[124],"subjects":[125],"evaluated":[127],"sound":[130],"quality":[131,150],"speech.":[136],"As":[137],"result,":[139],"confirmed":[141],"could":[147],"produce":[148],"good":[149],"speaker":[155],"even":[156],"training":[159],"was":[160],"done":[161],"data":[164],"set":[165],"two-sentences.":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
