{"id":"https://openalex.org/W4302589540","doi":"https://doi.org/10.21437/interspeech.2009-230","title":"Multimodal HMM-based NAM-to-speech conversion","display_name":"Multimodal HMM-based NAM-to-speech conversion","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W4302589540","doi":"https://doi.org/10.21437/interspeech.2009-230"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-230","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://naist.repo.nii.ac.jp/records/4736","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065106530","display_name":"Viet-Anh Tran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Viet-Anh Tran","raw_affiliation_strings":["Grenoble Images Parole Signal Automatique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grenoble Images Parole Signal Automatique","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071432574","display_name":"G\u00e9rard Bailly","orcid":"https://orcid.org/0000-0002-6053-0818"},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"G\u00e9rard Bailly","raw_affiliation_strings":["GIPSA - Machines Parlantes, Agents Communicants & Interaction Face-\u00e0-face"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA - Machines Parlantes, Agents Communicants & Interaction Face-\u00e0-face","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000635753","display_name":"H\u00e9l\u00e8ne L\u0153venbruck","orcid":"https://orcid.org/0000-0003-4015-3565"},"institutions":[{"id":"https://openalex.org/I2800493309","display_name":"Grain Inspection, Packers and Stockyards Administration","ror":"https://ror.org/056mcm922","country_code":"US","type":"government","lineage":["https://openalex.org/I1336096307","https://openalex.org/I2800493309"]},{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"H\u00e9l\u00e8ne L\u0153venbruck","raw_affiliation_strings":["GIPSA - Parole, Multimodalit\u00e9, D\u00e9veloppement"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA - Parole, Multimodalit\u00e9, D\u00e9veloppement","institution_ids":["https://openalex.org/I2800493309","https://openalex.org/I4210124956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Speech and Acoustics Processing Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Acoustics Processing Laboratory","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7309,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.72762784,"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":"656","last_page":"659"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.991100013256073,"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":0.991100013256073,"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/T12031","display_name":"Speech and dialogue systems","score":0.9009000062942505,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8245174884796143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6945145726203918},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6237621307373047},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41282880306243896},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38514813780784607}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8245174884796143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6945145726203918},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6237621307373047},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41282880306243896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38514813780784607}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.21437/interspeech.2009-230","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783187","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4736","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},{"id":"pmh:oai:HAL:hal-00419232v1","is_oa":true,"landing_page_url":"https://hal.science/hal-00419232","pdf_url":"https://hal.science/hal-00419232/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2009 - 10th Annual Conference of the International Speech Communication Association, Sep 2009, Brighton, United Kingdom. pp.656-659","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.210.5265","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.210.5265","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://spalab.naist.jp/~tomoki/Tomoki/Conferences/IS2009_BTWC-HMM.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.401.5327","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.401.5327","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.archives-ouvertes.fr/docs/00/41/92/32/PDF/vat_IS09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.459.4711","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.459.4711","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.archives-ouvertes.fr/docs/00/41/92/32/PDF/vat_IS09.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005783187","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4736","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"conference paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W1987783679","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Although":[0],"the":[1,29,83,97,113,124],"segmental":[2],"intelligibility":[3],"of":[4,86,99,123],"converted":[5],"speech":[6,9,30,54,69,156],"from":[7],"silent":[8,68,155],"using":[10],"direct":[11,135],"signal-to-signal":[12,136],"mapping":[13],"proposed":[14],"by":[15,41,116,127],"Toda":[16],"et":[17],"al.":[18],"[1]":[19],"is":[20,130,140],"quite":[21],"acceptable,":[22],"listeners":[23],"have":[24],"sometimes":[25],"difficulty":[26],"in":[27,50,93,143],"chunking":[28],"continuum":[31],"into":[32],"meaningful":[33],"words":[34],"due":[35],"to":[36,66,70,81,95],"incomplete":[37],"phonetic":[38,84],"cues":[39],"provided":[40],"output":[42,87],"signals.":[43,88],"This":[44],"paper":[45],"studies":[46],"another":[47],"approach":[48],"consisting":[49],"combining":[51],"HMM-based":[52],"statistical":[53],"recognition":[55,101,114],"and":[56,102,119,137],"synthesis":[57,103],"techniques,":[58],"as":[59,61],"well":[60],"training":[62],"on":[63],"aligned":[64],"corpora,":[65],"convert":[67],"audible":[71],"voice.":[72],"By":[73],"introducing":[74],"phonological":[75],"constraints,":[76],"such":[77],"systems":[78],"are":[79,91],"expected":[80],"improve":[82,96],"consistency":[85],"Facial":[89],"movements":[90,111],"used":[92],"order":[94],"performance":[98],"both":[100],"procedures.":[104],"The":[105,132],"results":[106],"show":[107],"that":[108],"including":[109],"these":[110],"improves":[112],"rate":[115],"6.2":[117],"%":[118,129],"a":[120],"final":[121],"improvement":[122],"spectral":[125],"distortion":[126],"2.7":[128],"observed.":[131],"comparison":[133],"between":[134],"phonetic-based":[138],"mappings":[139],"finally":[141],"commented":[142],"this":[144],"paper.":[145],"Index":[146],"Terms:":[147],"audiovisual":[148],"voice":[149],"conversion,":[150],"non-audible":[151],"murmur,":[152],"whispered":[153],"speech,":[154],"interface,":[157],"HMM-":[158]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
